WO2012113069A1 - Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery - Google Patents
Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery Download PDFInfo
- Publication number
- WO2012113069A1 WO2012113069A1 PCT/CA2012/000172 CA2012000172W WO2012113069A1 WO 2012113069 A1 WO2012113069 A1 WO 2012113069A1 CA 2012000172 W CA2012000172 W CA 2012000172W WO 2012113069 A1 WO2012113069 A1 WO 2012113069A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- zone
- anomaly
- property
- group
- imaging data
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 148
- 238000003384 imaging method Methods 0.000 title claims abstract description 67
- 230000007704 transition Effects 0.000 claims abstract description 51
- 230000000875 corresponding effect Effects 0.000 claims abstract description 18
- 238000002955 isolation Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 52
- 238000009826 distribution Methods 0.000 claims description 11
- 230000004807 localization Effects 0.000 claims description 5
- 238000002595 magnetic resonance imaging Methods 0.000 claims description 5
- 239000002872 contrast media Substances 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 238000002600 positron emission tomography Methods 0.000 claims description 3
- 238000002604 ultrasonography Methods 0.000 claims description 3
- 210000001519 tissue Anatomy 0.000 description 49
- 238000004458 analytical method Methods 0.000 description 36
- 230000003902 lesion Effects 0.000 description 33
- 210000001072 colon Anatomy 0.000 description 31
- 238000001514 detection method Methods 0.000 description 29
- 230000011218 segmentation Effects 0.000 description 27
- 230000008569 process Effects 0.000 description 26
- 210000000056 organ Anatomy 0.000 description 21
- 208000037062 Polyps Diseases 0.000 description 20
- 230000000112 colonic effect Effects 0.000 description 19
- 210000004877 mucosa Anatomy 0.000 description 19
- 210000004872 soft tissue Anatomy 0.000 description 14
- 230000001427 coherent effect Effects 0.000 description 13
- 230000008901 benefit Effects 0.000 description 10
- 206010028980 Neoplasm Diseases 0.000 description 8
- 230000004907 flux Effects 0.000 description 8
- 238000013459 approach Methods 0.000 description 7
- 230000007423 decrease Effects 0.000 description 6
- 230000000877 morphologic effect Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 210000000988 bone and bone Anatomy 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000001419 dependent effect Effects 0.000 description 4
- 238000011835 investigation Methods 0.000 description 4
- 230000000670 limiting effect Effects 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000005266 casting Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 230000000414 obstructive effect Effects 0.000 description 3
- 230000036961 partial effect Effects 0.000 description 3
- 208000002223 abdominal aortic aneurysm Diseases 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000001990 intravenous administration Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 230000001766 physiological effect Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000035939 shock Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- ZCYVEMRRCGMTRW-UHFFFAOYSA-N 7553-56-2 Chemical compound [I] ZCYVEMRRCGMTRW-UHFFFAOYSA-N 0.000 description 1
- 206010009944 Colon cancer Diseases 0.000 description 1
- 208000001333 Colorectal Neoplasms Diseases 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 229910052788 barium Inorganic materials 0.000 description 1
- DSAJWYNOEDNPEQ-UHFFFAOYSA-N barium atom Chemical compound [Ba] DSAJWYNOEDNPEQ-UHFFFAOYSA-N 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000008984 colonic lesion Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 229910052740 iodine Inorganic materials 0.000 description 1
- 239000011630 iodine Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 208000014081 polyp of colon Diseases 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 238000002609 virtual colonoscopy Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/46—Arrangements for interfacing with the operator or the patient
- A61B6/461—Displaying means of special interest
- A61B6/463—Displaying means of special interest characterised by displaying multiple images or images and diagnostic data on one display
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
- A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30028—Colon; Small intestine
- G06T2207/30032—Colon polyp
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Definitions
- This invention relates to data processing. More precisely, the invention pertains to a method and a system for image processing, in particular to computer-aided detection and diagnosis (CADe and CADx respectively) of medical datasets, more specifically for the detection of anomalies in hollow organs such as, but not restricted to, colorectal lesions or abdominal aortic aneurysms.
- CADe and CADx computer-aided detection and diagnosis
- CAD systems are meant to ultimately output potential anomalies within medical images.
- Prior art methods and systems have typically gathered 2D and 3D approaches with a preferred and most successful process being a coarse to fine approach, detecting multiple "coarse" initial patches further refined by a classifier that only the "best” candidates may survive.
- a first method for polyp identification in the colon is disclosed in International PCT application No. WO 98/37517 entitled “Automatic analysis in virtual endoscopy".
- the proposed methods and systems require the segmentation of an organ of interest, typically a colon. Upon successful segmentation, a mesh, i.e.
- a set of isosurfaces oriented from normals is used to interactively visualize the colon, in addition to support a "shape characteristics analysis" comprising the step of determining a convexity value for each population representing an amount and direction of curvature.
- shape characteristics analysis comprising the step of determining a convexity value for each population representing an amount and direction of curvature.
- CT colonography also called virtual colonoscopy
- the skilled addressee will appreciate that most prior art methods are meant to identify polypoid anomalies (of spherical shapes), not cancers neither masses (of random shapes with potentially no spherical protuberance).
- detectors based on curvature calculation use derivative processes which are susceptible to produce spurious outputs due to noise in the input imagery.
- Such limitation also affect every equivalent method involving gradient and iso-surfaces considering that the zero value iso-surface of the distance map yields the object surface and the derivative of the distance map yields the surface normal, i.e. a mesh, as mentioned in 1998, Using distance maps for accurate surface representation in sampled volumes, Gibson Sarah F.F., Mitsubishi Electric Research Laboratory, IEEE. The skilled addressee will appreciate that any such distance map requires object segmentation, as stated in US Patent No.
- a method of generating a distance map includes the step of identifying a boundary curve of a source image.
- CAD methods in CT Colonography for example, prior art segmentation and distance map determinations rely on the accurate identification of the inner wall of the colonic mucosa on which surface normals are determined (such as mesh, gradient).
- surface normals such as mesh, gradient.
- '620 patent discloses a method based on simple spherical summations. The method requires a binary image, i.e.
- segmented to be input, from which a shape is defined based on the ratio of segmented elements falling within the ratio of two spherical summation processes, involving one 2D image at a time but overlooking a 3D region.
- Such methodology does reduce the amount of processing time required and is less susceptible to noise, but is still really dependent on the image segmentation processing. As such, it only decreases the processing time and complexity required, but does not improve the detection output as it shifts the difficulty toward the segmentation stage.
- Gokturk introduced a three-dimensional pattern recognition method to detect shapes in medical images at the Biomedical computation Stanford 2000 symposium proceedings entitled "recognizing polyps from 3D CT colon data” where a random slicing through a candidate volume is used in order to extract shape features from 2D slices, the latter being input in a support vector machine (SVM) classifier further in charge to identify polyp candidates.
- SVM support vector machine
- DGFR Divergence Gradient Field Response
- a method for isolating a potential anomaly in imaging data comprising providing a set of at least one given anomaly property representative of a given anomaly; providing an anomaly property identifier for identifying each of the at least one given anomaly property; in the imaging data, isolating a first zone having a first property and a group of at least one other zone, each of the at least one other zone having a corresponding property different than the first property; providing a transition zone resulting from the isolation of a first zone and a group of at least one other zone, the transition zone being selected from a group consisting of: a closed zone separating the first zone and the group of at least one other zone; and a closed zone extending in one of the first zone and the group of at least one other zone; applying the anomaly property identifier for identifying each of the
- the imaging data comprise a n-dimensional dataset originating from an imaging system, wherein n is greater or equal than two.
- the n-dimensional dataset is one of a 2- dimensional volumetric array of elements and a 3-dimensional volumetric array of elements.
- the n-dimensional dataset originates from a device selected from a group consisting of a magnetic resonance imaging (MRI) device, a positron emission tomography (PET) device, an X-Rays device, an ultrasound device and any combination thereof.
- MRI magnetic resonance imaging
- PET positron emission tomography
- X-Rays device an ultrasound device and any combination thereof.
- the set of at least one given anomaly property comprises at least one of composition related information, shape related information, spatial localization in the imaging data, and a combination thereof over time.
- the anomaly property identifier comprises at least one of tissue density determination, homogeneity of tissue gradient determination, determination of absence or presence of tissue properties, determination of water content/distribution, determination of presence and determination of a distribution of contrast agent at a given moment or over time.
- the first property of the first zone comprises certain air region
- the corresponding property of each of the at least one other zone comprises certain tissue region
- the first property of the first zone comprises certain tagged region; the corresponding property of each of the at least one other zone comprises certain tissue region.
- the method further comprises applying the anomaly property identifier to the selected zone.
- the method further comprises providing an indication of a potential anomaly.
- the providing of an indication of a potential anomaly comprises at least one of storing the indication of a potential anomaly and displaying the indication of a potential anomaly on a user interface.
- the method further comprises transmitting the indication of a potential anomaly to a remote location.
- the image data comprises a plurality of unitary image elements selected from the group consisting of pixels and voxels.
- a machine readable medium having instructions recorded thereon for performing the method for isolating a potential anomaly in imaging data.
- a method for isolating a potential anomaly in imaging data comprising receiving imaging data; isolating in the imaging data a first zone having a first property and a group of at least one other zone, each of the at least one other zone having a corresponding property different than the first property; providing a transition zone resulting from the isolation of a first zone and a group of at least one other zone, the transition zone being selected from a group consisting of a closed zone separating the first zone and the group of at least one other zone; and a closed zone extending in one of the first zone and the group of at least one other zone; applying an homogeneity of tissue gradient identifier on at least the transition zone for providing a computed indication for a selected zone, the selected zone being at least the transition zone; determining if the computed indication is concording for the selected zone; and if the computed indication for the selected zone is concording, assigning an indication of potential anomaly candidate zone to the selected zone to thereby isolate
- a system for isolating a potential anomaly in imaging data comprising a data bus; a central processing unit operatively connected to the data bus; an I/O device operatively connected to the data bus; a network interface circuit operatively connected to the data bus; and a memory operatively connected to the data bus, the memory comprising at least one program for isolating a potential anomaly in imaging data wherein the at least one program is configured to be executed by the central processing unit, the at least one program for isolating a potential anomaly in imaging data comprising: instructions for providing an anomaly property identifier for identifying each of the at least one given anomaly property; instructions for isolating, in the imaging data, a first zone having a first property and a group of at least one other zone, each of the at least one other zone having a corresponding property different than the first property; instructions for providing a transition zone resulting from the isolation of a first zone and a group of at least one other zone,
- a system for isolating a potential anomaly in imaging data wherein the memory further comprises the imaging data.
- the imaging data is received from the network interface circuit.
- the method may be used for providing initial candidates or a complete detection scheme with efficient computational complexity and without requiring the organ of interest to be accurately segmented. This is of great advantage since the method may enhance detection of obstructive anomalies in hollow organs as well as other lesions in tortuous regions where an accurate segmentation required by prior art CAD methods may be difficult to achieve.
- the method is not dependent on restrictive shape analysis, nor is it dependent on a strict morphological feature analysis, such as curvature. This is of great advantage over the current state-of-the-art methods as lesions may depict variable shape and size.
- the method may be combined with any of them as a subsequent classification process.
- the method may involve the use of uncertain regions, i.e. regions whose type is not known, also called transition regions, depicting partial volume artifact for example, by trying to extract some coherent information out-of it. This is of great advantage compared to prior art methods that aim at reducing, limiting or preventing any information from uncertain regions considering they carry predominantly presumably faulty signals.
- Figure 1 is a flow chart which shows a prior art method for providing final candidates in an anomalies detection scheme.
- Figure 2 is a flow chart which shows an embodiment of a method for isolating a potential anomaly in imaging data.
- Figure 3 is a CT scanned image showing a portion of a colon, according to one embodiment.
- Figure 4 is an enlarged view of Figure 3.
- Figure 5 is another CT scanned image showing a portion of a colon, according to another embodiment.
- Figure 6 is another CT scanned image showing a portion of a colon, according to another embodiment.
- Figures 7A to 7D show images representative of a portion of a colon, according to one embodiment.
- Figure 8 is another CT scanned image showing a portion of a colon, according to another embodiment.
- Figures 9A and 9B show images representative of another portion of a colon, according to another embodiment.
- Figure 10 is a block diagram showing an embodiment of a processing device in which the method for isolating a potential anomaly in imaging data may be implemented.
- Figure 1 1 is a schematic showing an embodiment in which a thick region of investigation is determined, for example extending from the certain air region toward the certain tissue region, for a distance ⁇ .
- Figure 12 is an enlarged view of a part of a CT scanned image showing a portion of a colon shown in Fig. 3.
- Figure 13 is an enlarged view of a part of a CT scanned image showing a portion of a colon shown in Fig. 3 wherein local maxima present in the extended thick region at a constant distance ⁇ from the certain air region are shown.
- Figure 14 shows the schematic of Fig. 1 1 with final singular points obtained by casting rays and performing a reduction process on local maxima by thresholding the accumulation of Ray-strength at a given magnitude.
- Figure 15 is an enlarged view of a part of a CT scanned image showing a portion of a colon shown in Fig. 3 wherein exemplary rays orthogonal to the certain air region and passing through singular points have been casted. It can be seen that these rays intersect at singular points most probably belonging to potential anomalies.
- Figure 16 is an enlarged view of a part of a CT scanned image showing a portion of a colon shown in Fig. 3 wherein singular points have been further discriminated by applying a "strength" threshold at each rays intersections; the more rays culminating at a singular point, the more strength, and the more probability of that singular points belonging to a potential anomaly
- Figure 17 is the schematic of Fig. 1 1 wherein singular points can be clustered so as to reconstruct portions of an approximate colonic mucosa at the potential anomaly location, casting outward rays from the clusters of at least one singular point, and involving the previously determined distance transform map. Such portions of approximate colonic mucosa at potential anomaly locations can be further used to determined an approximate center of gravity (for 3D evaluation using a center of rotation for example) and approximate measurement of potential lesions.
- Figure 18A is an enlarged view of a part of a CT scanned image showing a distance field extending from certain air regions toward certain tissue regions. Unlike traditional distance transform approaches that converge toward the center of an object, the extending distance objective is to provide information on how far certain tissue regions are from certain air regions. Such extension is constrained by a maximum penetration thickness depending on the "anomaly property size".
- Figure 18B is an enlarged view of a part of a CT scanned image showing a surface flux determined from, and extending within, a distance field extension such as presented in Fig. 18A. Such surface flux will provide information on the localization of local maxima. The person skilled in the art will appreciate that the combination of both information maps (i.e. Fig. 18a & Fig.18b) would discard false-positives due to air bubbles closed to the surface, potentially resulting from air in remnant stools for example.
- Figure 19 illustrates a 2-dimensional image originating from a CT Colonography exam.
- Figure 19 comprises a first image showing two regions under investigations, wherein one depicts a local maximum.
- Figure 19 comprises an enlarged image in which coarse pixels of an original image can be seen.
- CAD systems may be used in medicine for detecting potential anomalies on a given medical dataset.
- the present invention provides a method and an apparatus for isolating a potential anomaly in imaging data that may be particularly useful for detecting anomalies in hollow organs such as colorectal lesions or abdominal aortic aneurysms for non-limitative examples.
- Fig. 1 shows a prior art method used for providing final candidates in an anomalies detection scheme. The method comprises an initial process for detecting the initial candidates, followed by a second process for providing the final candidates.
- the second process enables to classify the final candidates while trying to eliminate the false-positive candidates.
- an input dataset is provided. It will be appreciated that the input dataset may comprise 2D as well as 3D images, as known by the skilled addressee.
- an organ segmentation is performed.
- the purpose of the organ segmentation is to suitably locate the border of the organ of interest.
- processing step 106 a detection based on sphere or curvature extraction is performed.
- processing step 108 initial candidates are provided. The initial candidates are provided following the detection.
- processing step 1 10 a feature extraction is performed on the set of initial candidates.
- processing step 1 12 a classification of initial candidates based on feature extraction is performed.
- processing step 1 14 a reduction of false-positives is performed.
- the method of the present invention does not rely on an accurate segmentation of the organ of interest.
- the method may be used for providing either initial candidates or for providing a complete detection scheme with efficient computational complexity, as detailed thereinafter.
- the described method does not depend on a restrictive shape analysis or a strict morphological feature analysis, both arising from the need of an accurate object segmentation for its potential detection, which is of great advantage since lesions to be found generally depict variable shape and size.
- the skilled addressee will nevertheless appreciate that the present method may be combined with any shape analysis or morphological feature analysis as a subsequent classification process, as it will become apparent below.
- FIG. 2 an embodiment of the method for isolating a potential anomaly in imaging data will now be described.
- the imaging data comprise a n- dimensional dataset (wherein n>2) originating from an imaging system and provided to a processing system.
- medical datasets are usually 2-dimensional or 3- dimensional volumetric array of elements, denoted as pixels and voxels respectively.
- a pixel element is represented along the axes (i,j) (respectively (i,j,k) for voxels) at the location (x,y) (respectively (x,y,z) for voxels). Consequently, a "slice" of a dataset may be selected by specifying a "z" location along the "k" axis of a 3-dimensional datasets.
- the datasets may be acquired from a device selected from a group consisting of a magnetic resonance imaging (MRI) device, a positron emission tomography (PET) device, an X-Rays device, an ultrasound device and any combination thereof.
- the acquired dataset comprises at least one portion of the organ of interest, for which each element can be related to a specific property of the human body.
- a medical dataset acquired by a X-Ray CT scanner comprising at least a portion of the colon, will depict elements with density values expressed in Hounsfield units and displayed in grayscaled colors, and where elements rendered in black will typically represent air-element of Hounsfield values below -400Hu, thus allowing the visualization of hollow organs, such as the colon.
- the method may involve the use of certain regions in the imaging data, i.e. regions which have been confidently detected as being of a particular known type such as bones, soft tissues, air regions and tagged regions, and the use of uncertain regions, i.e. regions depicting partial volume artifact for example.
- the method uses at least the uncertain regions, also called transition zones, originating from the identification of the adjacent certain regions neighboring the uncertain regions in order to extract some coherent information. This is unlike other methods that aim at reducing, limiting or preventing any information from "uncertain" regions considering they carry predominantly presumably faulty signals.
- the coherent information may be related to a property of a suspicious region to depict a concentric certain tissue type region surrounded by a certain air type region.
- Another exemplary property of a lesion is that it shows a homogeneous and concentric-denser tissue distribution.
- coherent information related to the properties of a potential lesion may be considered.
- the potential lesion depicts a coherent air density
- coherent information showing the presence of air bubbles may be used to discard the potential lesion and identify it as a false positive, as better illustrated thereinafter.
- they may depict denser tissue in their center than in their surrounding.
- Lesions may also depict continuous properties such as denser and denser tissues without any other tissue types shock.
- inhomogeneous remnant colonic fluids or fecal matter depict highly inhomogeneous tissue characteristics and the presence of trapped air bubbles.
- typical lesions may also, in some cases, feature a surrounding high density tissue if coated within a tagging agent, such as Barium or Iodine for example.
- a tagging agent such as Barium or Iodine for example.
- lesions may depict tissue shocks due to higher centric densities considering lesions may be highly vascularized.
- a set of at least one given anomaly property representative of an anomaly is provided.
- the set of at least one given anomaly property may comprise one given anomaly property that is representative of a lesion, for example the given anomaly property may describe a concentric certain tissue type region whose density increases inwardly, surrounded by a certain air type region.
- a given anomaly may be represented with a single one property as well as with a plurality of properties.
- the set of at least one given anomaly property may comprise at least one of composition related information, shape related information, spatial localization in the imaging data and a combination thereof over time.
- an anomaly property identifier for identifying each of the at least one given anomaly property is provided.
- the anomaly property identifier may comprise the determination of a gradient, as it will become apparent below.
- anomaly property identifier may be considered for the purpose of identifying a corresponding one anomaly property. It will also be appreciated that a combination of a plurality of anomaly property identifiers may be used according to a given application, as it will become apparent below. For example, in one embodiment, a first anomaly property identifier may be provided for identifying a first given anomaly property while a second anomaly property identifier may be provided for identifying a second given anomaly property.
- the anomaly property identifier may comprise at least one of tissue density determination, homogeneity of tissue gradient determination, tissue distribution for a given region, determination of absence or presence of certain tissue properties, determination of water content/distribution for the case of MRI images, presence and distribution of contrast agent at a given moment or over time of acquisitions featuring intra-venous contrast agent.
- intensity profile analysis comprising any derivative processes such as Gradient and Divergence analysis [Semi-Automatic Generation of Transfer Functions for Direct Volume Rendering, G. Kindlmann & J.W.
- the anomaly property identifier may be derived from the image acquisition physics, the given anomaly physiology or a combination thereof, as it will become apparent upon reading of the present description. It will be appreciated that in one embodiment the anomaly property identifier is applied over a region preventing further dependence from segmentation processes.
- tissue composition properties originate from the clinical understanding of any anomaly and the physics of image acquisitions, being density in Hounsfield values for CT scanners based on X-rays and water content in Magnetic Resonance Imaging as non limiting examples.
- a first zone and a group of at least one other zone are isolated in the imaging data.
- the first zone has a first property.
- each zone of the group of at least one other zone has a corresponding property different than the first property, as detailed below.
- the first zone may comprise a certain air region while the other zones of the group may comprise a certain tissue region.
- the first zone may comprise a certain tagged region, as it will be detailed thereinafter. It will be appreciated that certainty depends on the unambiguity of the information describing a given physical object (thus based on the physics of acquisition and understanding of the clinical aspects related such object). By means of non-exhaustive example, regions of Hounsfield vales below -500 most probably depict air regions.
- a transition zone is provided in the imaging data.
- the transition zone is selected from a group consisting of a closed zone separating the first zone and the group of at least one other zone and a closed zone extending in one of the first zone and the group of at least one other zone, as it will become apparent below.
- the transition zone may be an uncertain region whose type is not known.
- the transition zone is a closed zone in a 2D slice of imaging data.
- the process of isolating a potential anomaly may be stopped without further processing and without isolating any potential anomaly, as better detailed thereinafter.
- Fig. 3 shows an example of imaging data comprising a portion of a colon 300.
- the image data comprises a CT scanner Rx image which depicts a lesion 302.
- voxel elements which are darker depict air
- voxel elements of grey intensity depict soft tissues and whitish elements depict bones or tagged tissues.
- the imaging data comprise a first zone 304 having a first property, at least one other zone 306 having a corresponding property different than the first property and a transition zone 308.
- the first zone 304 is a certain air region totally surrounded by an adjacent closed transition zone 314.
- the other zone 306 is a certain tissue region entirely surrounded by the transition zone 308 which is a closed zone.
- the transition zones 308 and 314 comprise elements which have not been classified as belonging with certainty to a particular known type of elements.
- the anomaly property identifier used for identifying each of the at least one given anomaly property is applied on at least the transition zone for providing a computed indication for a selected zone, the selected zone being at least the transition zone.
- the anomaly property identifier may also be applied on at least one of the certain zones in addition to the transition zone.
- processing step 212 a determination is made as to whether the computed indication for the selected zone is concording with each of the at least one given anomaly property, as described below.
- an indication of potential anomaly candidate zone is assigned to the selected zone to thereby isolate the potential anomaly.
- the providing of the indication of a potential anomaly may comprise at least one of storing the indication of a potential anomaly and displaying the indication of a potential anomaly on a user interface.
- the indication of a potential anomaly may be further transmitted to a remote location.
- the object of interest i.e. the hollow organ
- the object of interest is defined and identified in the imaging data prior to isolating a potential anomaly.
- Prior art methods and systems mostly refer to such identification as a segmentation process, with purpose to isolate an organ and define with most accuracy its border (contour) such as the colonic mucosa.
- segmentation typically provides an object mask that may be binary with elements foreground representing the object and background representing a non-object zone [Fast image segmentation, P.I. Corke & H.I.
- Such embodiments may enable the providing of a complete CT Colonography system that does not introduce a segmentation process of the colon, but provide every information needed for the end-user to perform a colorectal cancer review on patient datasets, featuring state-of-the-art tools such as electronic colon cleansing.
- different masks using different Window/Levels may be used on the imaging data for isolating a first zone and a group of at least one other zone and providing at least one transition zone.
- four masks may be used, respectively a colon mask, a bone mask, a lung mask and an abdominal mask.
- the anomaly property identifiers used for identifying each of the at least one given anomaly property may be applied at each Window/Levels.
- the medical images may then be individually processed in order to identify disconnected non-air regions within air-regions, i.e. floating surfaces or unconnected regions. Potential anomaly detection may be performed as previously described for each such non-air region.
- the masks used for identifying the zones of interest may be obtained from certainty masks as provided in "Method for determining an estimation of a topological support or a tubular structure and use thereof in virtual endoscopy” and “Method and system for filtering image data and use thereof in virtual endoscopy” mentioned above.
- the following masks are provided: high certainty air mask, high certainty Tag/Bone mask, uncertain mask for interfaces air/soft tissue, uncertain mask for interfaces tag/bone-soft tissue, uncertain mask for interfaces tag-bone/air and certain mask for reduced colon datasets obtained using anatomical topology amongst the graph of the masks, as detailed in the previously cited co-pending applications.
- improved computational efficiency may be provided by scanning the elements of the certain soft-tissue mask belonging to the final colon identification mask subsequent to anatomical topology processing of the mask connectivity graph. The main reason for scanning this "layer" is the fact that any lesion will have a dense "inside” depicting characteristics similar to soft tissue, muscle, fat and so on.
- some resliced planes may be provided in order to investigate a potential trace of a lesion proximate the mucosa of the colon.
- a trace of a lesion is defined as a connected-labeled component surface not connected to other element belonging to the certain colonic mucosa (US Patent 7,447,342).
- a refined output may be obtained by detecting non-air surfaces depicting a topological hole due to the presence of air inside (typically air bubble inside a false-positive residual untagged stool), or the presence of tagged density within the surface.
- air inside typically air bubble inside a false-positive residual untagged stool
- the initial potential anomaly candidates may be input on top of any other current methods and systems in order to improve their sensitivity, specifically for the case of small lesions or obstructive lesions that are typically very difficult to identify from typical 3D schemes.
- the potential anomaly candidates may be further classified based on a set of features computed for each element of the non-air region.
- An example of such feature is the density distribution of each element of the non-air region as well as the non-air surface.
- each trace of a potential lesion may be analyzed at different window/level in order to increase the certainty of a potential candidate by observing its presence at different "tissue characteristic thresholds".
- the detected trace may be further analyzed.
- the analysis refers to looking for a topological ⁇ closed surface, with no hole. This may ensure no air-bubble is present inside the trace (false-positive), thereby reducing the occurrence of false-positives.
- the step of analyzing the trace comprises the use of a gradient field in order to detect closed surfaces.
- the analysis of traces may comprise the analysis of the neighboring masks.
- Neighboring masks determined from the connectivity graph tree as mentioned above, may be one of Tag/soft tissue or Air/soft tissue masks. On these masks, derivative features depicting the noise/environment behavior may be determined.
- the layer masks analysis may be used to detect an encircling layer around the initially detected surface.
- the certainty that the candidate is a relevant clinical finding is increased, despite the fact that the neighboring layer can be viewed as "blurry", in depicting an overall behavior encircling soft-tissue.
- Such behavior is defined as partial volume artifact around a lesion and reinforces the relevance of the trace, as it will be further detailed below.
- Figs. 3 to 9B show potential anomalies.
- the illustrated anomalies have either been optically confirmed polyps, cancers and obstructive cancers, of sizes of 4.5 mm to 40 mm or are false-positives.
- a first contouring 310 contouring a certain soft tissue region 306 and a second contouring 312 contouring a certain air tissue region 304 are shown.
- the region in between is a transition zone 308 which is a highly uncertain region.
- a property of a given suspicious region is to depict a concentric certain tissue type region surrounded by a certain air type region.
- a topological property expected for hollow organ is that there is no flying element inside the hollow tube, specifically during a 2D analysis. It may however be anticipated that the ileocaecal valve may most probably appear as such "flying object" as it is the only irregular colonic mucosa region of the colon, as it should be apparent to the skilled addressee. As such, it can be processed accordingly, as explained in US Patent No. 7,440,601.
- Fig. 4 sample elements in and around the uncertain region, i.e. the transition zone, have been illustrated. These sample points may be used for isolating the potential anomaly, as described below.
- Fig. 5 there is shown computed sampled gradient vectors originating from the sampled points presented in Figure 4 proximate the uncertain region.
- This computing enables to determine whether or not the property in the transition zone is concording in order to detect and isolate a potential anomaly.
- the objective of this processing step is to make the most out of the coherent information of the uncertain region.
- the uncertain region surrounding the colonic mucosa depicts a gradient going inward, i.e. penetrating inside the soft tissue and surrounding organs.
- the uncertain region 308 surrounding the lesion 306 indicates a coherent concentration of denser tissues inside the potential findings.
- the coherent information of the uncertain region it is possible to highlight physiological properties of lesions, e.g. homogeneous and coherent gradient property of concentric denser tissue originating from the uncertain region. The skilled addressee will therefore appreciate it may be possible to derive pertinent information using uncertain regions coherent information.
- this method is radically different from prior art methods which try, by every means, to decrease the impact of volume artifacts and develop processes of smoothing and summations to attenuate noise interferences.
- prior art methods try to detect a boundary and use these boundary points and possibly the enclosed points for the processing. These methods do not use the uncertain points.
- the gradient analysis of uncertain regions is used in order to extract, for example, potential coherent information of concentric denser tissue attenuation at specific locations.
- most of the elements of calculations for the gradient calculation originate from a thick-region of uncertain elements as opposed to the use of enclosed elements of segmented region (certain elements) for current state-of- the-art inventions.
- a property of a suspicious region may be to depict a concentric certain tissue type region surrounded by a certain tag type region, for which the property identifier could be an increasing concentric gradient on the region's voxels' density.
- This later embodiment is the earlier embodiment reciprocal for tagged-patient detection analysis that does not require electronic cleansing.
- FIG. 6 illustrates the application of the gradient analysis approach involved in Figure 5 that may prevent the accrual of false-positives requiring further false-positive-reduction processing steps.
- a "false-positive" element 600 mimicking a potential protuberance of the colonic mucosa in the colon lumen is shown.
- Such protuberance would be defined as a positive CAD finding by current methods based on shape analysis (curvature-based or gradient-shock-based).
- shape analysis curvature-based or gradient-shock-based
- the two certain layers do not end up to create a certain tissue region surrounded by a certain air region as it was presented in Figure 5 for example.
- This illustrates that the present method may enable combining detection and false-positive reduction processing steps during a single analysis, which is of great advantage.
- the skilled addressee will also appreciate that the method may reduce processing time, which is also of great advantage.
- a small 4.5 mm polyp 700 is illustrated.
- Fig. 7B shows that the raw axial image does not provide sufficient information to further identify this small polyp as the certain air layer does not encircle a certain tissue region, as it was illustrated in Fig. 5.
- a reslicing processing step that resliced planes at different angles at the certain air border may be implemented.
- One such resliced image is shown in Fig. 7C and in Fig. 7D as a white plane.
- Fig. 7C it is now possible to identify an air region encircling, not a tissue region but an uncertain region.
- gradient properties determined from this encompassed region shows a tendency of soft tissue, that was further validated by the Gradient certain threshold property.
- the information of the uncertain region provides enough properties to determine a true CAD positive finding revealing a true 4.5 mm polyp. Again, this is derived from the nature of one type of lesions and polyps that have soft tissue or denser tissue at their center, in a uniform distribution.
- FIG. 8 there is better illustrated the behavior of one embodiment of the present method involving the gradient property analysis.
- some small uncertain regions 800 are encircled by a certain air region.
- the analysis of the gradient of such regions revealed false positive findings.
- Such combination of two steps in one allows improving processing speed, which is of great advantage.
- FIG. 9A and 9B another embodiment of the method which helps avoiding pitfalls and false positives depicted by current state-of-the-art morphological CAD processes will be described.
- a spherical-like shape 900 in the colon lumen can be seen, and would further be reported as a CAD finding for current state-of-the-art strategies.
- the present method would inherently classify such region as being a false-positive considering the candidate region is filled with air, as illustrated in Fig. 9B.
- FIG. 10 there is shown an embodiment of a processing device 1000 in which the method for isolating a potential anomaly in imaging data may be advantageously used.
- the processing device 1000 comprises a central processing unit 1002, I/O devices 1004, a network interface circuit 1008, a data bus 1006 and a memory 1010.
- the central processing unit 1002, the I/O devices 1004, the network interface circuit 1008 and the memory 1010 are operatively coupled using the data bus 1006.
- the central processing unit 1002 is adapted for processing data instructions.
- the network interface circuit 1008 is adapted for operatively connecting the processing device 1000 to another processing device (not shown) via a data network (not shown).
- the skilled addressee will appreciate that various embodiments of the network interface circuit 1008 may be provided.
- the skilled addressee will also appreciate that the network interface circuit 1008 may operate according to various communication protocols such as TCP/IP for instance.
- the I/O devices 1004 are used for enabling a user to interact with the processing device 1000.
- the skilled addressee will appreciate that various embodiments of the I/O devices 1004 may be used.
- the I/O devices 1004 may comprise at least one of a keyboard, a screen and a mouse.
- the data bus 1006 may be provided.
- various embodiments of the memory 1010 may be provided.
- the memory 1010 may be used to store, in one embodiment, an operating system 1012, at least one program for isolating a potential anomaly in imaging data 1016, wherein the at least one program is configured to be executed by the central processing unit 1002, and databases 1014 used for operating the at least one program for isolating a potential anomaly in imaging data 1016.
- the at least one program for isolating a potential anomaly in imaging data 1016 comprises instructions for providing a set of at least one given anomaly property representative of a given anomaly.
- the at least one program for isolating a potential anomaly in imaging data 1016 further comprises instructions for providing an anomaly property identifier for identifying each of the at least one given anomaly property.
- the at least one program for isolating a potential anomaly in imaging data 1016 further comprises instructions for isolating, in the imaging data, a first zone having a first property and a group of at least one other zone, each of the at least one other zone having a corresponding property different than the first property.
- the imaging data may be stored in the databases 1014.
- the imaging data may be obtained from at least one of the I/O devices 1004 and the network interface circuit 1008.
- the at least one program for isolating a potential anomaly in imaging data 1016 further comprises instructions for providing a transition zone resulting from the isolation of a first zone and a group of at least one other zone, the transition zone being selected from a group consisting of a closed zone separating the first zone and the group of at least one other zone and a closed zone extending in one of the first zone and the group of at least one other zone.
- the at least one program for isolating a potential anomaly in imaging data 1016 further comprises instructions for applying the anomaly property identifier for identifying each of the at least one given anomaly property on at least the transition zone for providing a computed indication for a selected zone, the selected zone being at least the transition zone.
- the at least one program for isolating a potential anomaly in imaging data 1016 further comprises instructions for determining if the computed indication for the selected zone is concording with each of the at least one given anomaly property and if the computed indication for the selected zone is concording, for assigning an indication of potential anomaly candidate zone to the selected zone to thereby isolate the potential anomaly.
- a singularity analysis is performed to decrease the number of elements where cutting-planes analysis is performed as expressed above.
- a thick region of investigation is determined, for example extending from the certain air region toward the certain tissue region, for a distance ⁇ .
- ⁇ relates to the characteristic of the singularities to be identified. For the specific case of colorectal lesions, ⁇ is determined so that singularities would exist for both the smallest and the largest anomalies to be reported.
- the singularity analysis is a process optimizing the detection of potential anomalies while making sure that all of the potential anomalies to be reported are encompassed by the thick region under examination.
- Fig. 12 there is shown a 2D image of the colon, where the red border determines the certain air region, and the yellow border represents the ⁇ Thick region extending from the certain air region.
- the singularity analysis is performed through a distance transform process applied on the extended thick region.
- Such distance transform could be a Euclidean Distance Transform or a Weighted Transform as detailed in "R. Kimmel and al., Sub-pixel Distance Maps and Weighted Distance Transforms, Journal of Mathematical Imaging and Vision, 1994".
- the determination of singularities will comprise two processing steps.
- a first processing step is the identification of local maxima on the distance map while a second processing step is the discarding of local maxima with low potential of belonging to an anomaly.
- Fig. 13 there are illustrated local maxima present in the extended thick region at a constant distance ⁇ from the certain air region. It can be observed that such embodiment decreases dramatically the number of elements to be further analyzed through a cutting-planes methodology which is of great advantage.
- the number of local maxima may be further reduced using rays extending from the certain air region toward the certain tissue region. These rays carry intensity strength that decreases the further they extend from the certain air region. In a further embodiment, these rays may have strength profile accounting for the elements intensities along the rays. Each of these rays is normal to the certain air border. It is therefore possible to obtain final singular points, as shown in Fig. 14, by casting rays and performing a reduction process on the local maxima by thresholding the accumulation of Ray-strength at a given magnitude.
- the singularity analysis involves the processing step of extending a distance field from a first certain air region into a certain tissue region, constrained within a given thickness that is determined based on the anomaly property size.
- the resulting thick region carrying the distance field information would represent the transition zone in which potential anomalies could be identified.
- the singularity analysis would involve the determination of a surface flux extending within the thick distance field extending from certain air regions into certain tissue regions.
- the combination of both the distance field extension and the surface flux would allow the determination of local maxima at locations where the surface flux is singular and at a given distance representing the potential anomaly property size.
- Fig. 18A presents a distance field extending from certain air regions toward certain tissue regions. Unlike traditional distance transform approaches, the extending distance objective is to provide information on how far certain tissue regions are from certain air regions, and are extends constrained by a maximum penetration thickness depending on the "anomaly property size".
- Fig. 18B presents a surface flux determined from, and extending within, the distance field extension. Such surface flux will provide information on the localization of local maxima. The skilled in the art will understand that the combination of both information maps would discard false-positives due to air bubbles closed to the surface, potentially resulting from air in remnant stools for example.
- these local maxima may be used in order to address the issue of 3D camera positioning.
- positioning automatically a camera in 3D so as to support the reader's examination, is not possible since the colonic mucosa is not accurately determined and since the embodiments disclosed do not rely on, nor output, the accurate segmentation of the colonic mucosa, and thus that of potential anomalies.
- it is possible to support the review of radiologists by defining these final local maxima as center of rotations for 3D camera by leveraging on the fact that these final local maxima are within potential anomalies, specifically centered at their denser regions.
- an inverse problem is carried on the rays passing through each of the final local maxima or their clustering, if closed enough.
- This inverse problem is aimed at the reconstruction of at least one part of the colonic mucosa.
- multiple inverse approaches may be used such as an implicit surface problem based on the distance information of singular points that are defined as "most probably accurate”.
- these patches of surfaces are used to visually support the analysis of the potential anomaly by depicting specific colors on either 2D or 3D to mark such regions.
- Figure 19 illustrates a 2-dimensional image originating from a CT Colonography exam.
- the main image presents two regions under investigations (the two protuberant ones), wherein one depicts a local maxima. From that local maximum, an inverse problem is carried on in order to determine an implicit surface best representing a reconstructed colonic mucosa at that specific region.
- Such implicit surface is presented in the left enlarged image in which one can see the coarse pixels of the original image, and the refined reconstructed colonic mucosa implicit surface that may be used to determine the regions's of interests thickness and volume.
- the reconstructed patches of anomalies are used for determining an approximate measurement of the anomaly.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- High Energy & Nuclear Physics (AREA)
- General Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Theoretical Computer Science (AREA)
- Physiology (AREA)
- Quality & Reliability (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Endoscopes (AREA)
- Image Processing (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Facsimiles In General (AREA)
Abstract
Description
Claims
Priority Applications (9)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201280019261.7A CN103501699B (en) | 2011-02-24 | 2012-02-24 | For isolating potential abnormal method and apparatus in imaging data and it is to the application of medical image |
AU2012220301A AU2012220301B2 (en) | 2011-02-24 | 2012-02-24 | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery |
CA2827742A CA2827742C (en) | 2011-02-24 | 2012-02-24 | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery |
KR1020137025156A KR101967357B1 (en) | 2011-02-24 | 2012-02-24 | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery |
JP2013554763A JP6031454B2 (en) | 2011-02-24 | 2012-02-24 | Method and apparatus for identifying latent anomalies in imaging data and its application to medical images |
EP12748944.1A EP2678827A4 (en) | 2011-02-24 | 2012-02-24 | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery |
BR112013021657-3A BR112013021657B1 (en) | 2011-02-24 | 2012-02-24 | METHOD IMPLEMENTED BY COMPUTER AND SYSTEM TO ISOLATE A POTENTIAL ANOMALY IN IMAGE DATA, AND, MACHINE-READABLE MEDIA |
US14/001,628 US9717414B2 (en) | 2011-02-24 | 2012-02-24 | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery |
HK14104278.9A HK1190903A1 (en) | 2011-02-24 | 2014-05-05 | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201161446342P | 2011-02-24 | 2011-02-24 | |
US61/446,342 | 2011-02-24 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012113069A1 true WO2012113069A1 (en) | 2012-08-30 |
Family
ID=46720054
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CA2012/000172 WO2012113069A1 (en) | 2011-02-24 | 2012-02-24 | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery |
Country Status (10)
Country | Link |
---|---|
US (1) | US9717414B2 (en) |
EP (1) | EP2678827A4 (en) |
JP (1) | JP6031454B2 (en) |
KR (1) | KR101967357B1 (en) |
CN (1) | CN103501699B (en) |
AU (1) | AU2012220301B2 (en) |
BR (1) | BR112013021657B1 (en) |
CA (1) | CA2827742C (en) |
HK (1) | HK1190903A1 (en) |
WO (1) | WO2012113069A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11257210B2 (en) | 2018-06-25 | 2022-02-22 | The Royal Institution For The Advancement Of Learning / Mcgill University | Method and system of performing medical treatment outcome assessment or medical condition diagnostic |
Families Citing this family (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6235886B2 (en) * | 2013-01-08 | 2017-11-22 | キヤノン株式会社 | Biological tissue image reconstruction method and apparatus, and image display apparatus using the biological tissue image |
US9832447B2 (en) * | 2013-04-04 | 2017-11-28 | Amatel Inc. | Image processing system and image processing program |
US9940511B2 (en) * | 2014-05-30 | 2018-04-10 | Kofax, Inc. | Machine print, hand print, and signature discrimination |
US11213220B2 (en) | 2014-08-11 | 2022-01-04 | Cubisme, Inc. | Method for determining in vivo tissue biomarker characteristics using multiparameter MRI matrix creation and big data analytics |
US10133614B2 (en) * | 2015-03-24 | 2018-11-20 | Ca, Inc. | Anomaly classification, analytics and resolution based on annotated event logs |
US9922433B2 (en) | 2015-05-29 | 2018-03-20 | Moira F. Schieke | Method and system for identifying biomarkers using a probability map |
CN105748093B (en) * | 2015-12-28 | 2018-11-16 | 南京信息工程大学 | Cerebral gray matter makees the human brain part water distribution volume determination method of reference area |
CN105686844B (en) * | 2015-12-28 | 2018-11-16 | 南京信息工程大学 | Make the human brain part water distribution volume determination method of reference area in the preceding region A% |
US10339650B2 (en) | 2016-01-07 | 2019-07-02 | Koios Medical, Inc. | Method and means of CAD system personalization to reduce intraoperator and interoperator variation |
US9536054B1 (en) | 2016-01-07 | 2017-01-03 | ClearView Diagnostics Inc. | Method and means of CAD system personalization to provide a confidence level indicator for CAD system recommendations |
US10776963B2 (en) | 2016-07-01 | 2020-09-15 | Cubismi, Inc. | System and method for forming a super-resolution biomarker map image |
US10346982B2 (en) | 2016-08-22 | 2019-07-09 | Koios Medical, Inc. | Method and system of computer-aided detection using multiple images from different views of a region of interest to improve detection accuracy |
WO2018195501A2 (en) | 2017-04-21 | 2018-10-25 | Cubisme, Inc. | System and method for creating, querying, and displaying a miba master file |
US10593033B2 (en) * | 2017-06-27 | 2020-03-17 | Nec Corporation | Reconstructor and contrastor for medical anomaly detection |
EP3527137A1 (en) | 2018-02-14 | 2019-08-21 | Koninklijke Philips N.V. | Apparatus for iterative material decomposition of multispectral data |
JP7169235B2 (en) | 2018-03-15 | 2022-11-10 | 三ツ星ベルト株式会社 | counting device |
CN112070172B (en) * | 2020-09-11 | 2023-12-22 | 湖南人文科技学院 | Abnormal target detection method and device based on targeting analysis and computer equipment |
US12026874B2 (en) * | 2021-08-04 | 2024-07-02 | Magentiq Eye Ltd | Systems and methods for detection and analysis of polyps in colon images |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6549646B1 (en) * | 2000-02-15 | 2003-04-15 | Deus Technologies, Llc | Divide-and-conquer method and system for the detection of lung nodule in radiological images |
US20040064029A1 (en) * | 2002-09-30 | 2004-04-01 | The Government Of The Usa As Represented By The Secretary Of The Dept. Of Health & Human Services | Computer-aided classification of anomalies in anatomical structures |
Family Cites Families (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5920319A (en) | 1994-10-27 | 1999-07-06 | Wake Forest University | Automatic analysis in virtual endoscopy |
US6331116B1 (en) * | 1996-09-16 | 2001-12-18 | The Research Foundation Of State University Of New York | System and method for performing a three-dimensional virtual segmentation and examination |
US6947784B2 (en) * | 2000-04-07 | 2005-09-20 | The General Hospital Corporation | System for digital bowel subtraction and polyp detection and related techniques |
US7113617B2 (en) | 2000-12-12 | 2006-09-26 | Hewlett-Packard Development Company, L.P. | Method of computing sub-pixel Euclidean distance maps |
US7236620B1 (en) * | 2002-06-24 | 2007-06-26 | Icad, Inc. | Computer-aided detection methods in volumetric imagery |
US7346209B2 (en) | 2002-09-30 | 2008-03-18 | The Board Of Trustees Of The Leland Stanford Junior University | Three-dimensional pattern recognition method to detect shapes in medical images |
US7333644B2 (en) | 2003-03-11 | 2008-02-19 | Siemens Medical Solutions Usa, Inc. | Systems and methods for providing automatic 3D lesion segmentation and measurements |
WO2004081843A2 (en) * | 2003-03-11 | 2004-09-23 | Siemens Medical Solutions Usa Inc. | Computer-aided detection systems and methods for ensuring manual review of computer marks in medical images |
US7369638B2 (en) | 2003-07-11 | 2008-05-06 | Siemens Medical Solutions Usa, Inc. | System and method for detecting a protrusion in a medical image |
US7447342B2 (en) * | 2003-09-22 | 2008-11-04 | Siemens Medical Solutions Usa, Inc. | Method and system for using cutting planes for colon polyp detection |
US7440601B1 (en) | 2003-10-10 | 2008-10-21 | The United States Of America As Represented By The Department Of Health And Human Services | Automated identification of ileocecal valve |
JP4686279B2 (en) * | 2005-07-06 | 2011-05-25 | 株式会社東芝 | Medical diagnostic apparatus and diagnostic support apparatus |
US20090016583A1 (en) | 2007-07-10 | 2009-01-15 | Siemens Medical Solutions Usa, Inc. | System and Method for Detecting Spherical and Ellipsoidal Objects Using Cutting Planes |
WO2009084047A1 (en) * | 2007-12-28 | 2009-07-09 | Im3D S.P.A. | Method of classification of tagged material in a set of tomographic images of colorectal |
US8131036B2 (en) * | 2008-07-25 | 2012-03-06 | Icad, Inc. | Computer-aided detection and display of colonic residue in medical imagery of the colon |
US20100183210A1 (en) * | 2009-01-22 | 2010-07-22 | Van Uitert Robert L | Computer-assisted analysis of colonic polyps by morphology in medical images |
BR112012012819A2 (en) | 2009-11-27 | 2016-08-16 | Dog Microsystems Inc | method and system for filtering image data and use in virtual endoscopy |
AU2009355844B2 (en) | 2009-11-27 | 2015-07-30 | Cadens Medical Imaging Inc. | Method and system for determining an estimation of a topological support of a tubular structure and use thereof in virtual endoscopy |
US8724894B1 (en) * | 2012-12-03 | 2014-05-13 | Rockwell Collins, Inc. | Colorization of digital imagery |
-
2012
- 2012-02-24 JP JP2013554763A patent/JP6031454B2/en active Active
- 2012-02-24 EP EP12748944.1A patent/EP2678827A4/en not_active Ceased
- 2012-02-24 CA CA2827742A patent/CA2827742C/en active Active
- 2012-02-24 WO PCT/CA2012/000172 patent/WO2012113069A1/en active Application Filing
- 2012-02-24 BR BR112013021657-3A patent/BR112013021657B1/en active IP Right Grant
- 2012-02-24 KR KR1020137025156A patent/KR101967357B1/en active IP Right Grant
- 2012-02-24 CN CN201280019261.7A patent/CN103501699B/en active Active
- 2012-02-24 US US14/001,628 patent/US9717414B2/en active Active
- 2012-02-24 AU AU2012220301A patent/AU2012220301B2/en active Active
-
2014
- 2014-05-05 HK HK14104278.9A patent/HK1190903A1/en unknown
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6549646B1 (en) * | 2000-02-15 | 2003-04-15 | Deus Technologies, Llc | Divide-and-conquer method and system for the detection of lung nodule in radiological images |
US20040064029A1 (en) * | 2002-09-30 | 2004-04-01 | The Government Of The Usa As Represented By The Secretary Of The Dept. Of Health & Human Services | Computer-aided classification of anomalies in anatomical structures |
Non-Patent Citations (1)
Title |
---|
See also references of EP2678827A4 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11257210B2 (en) | 2018-06-25 | 2022-02-22 | The Royal Institution For The Advancement Of Learning / Mcgill University | Method and system of performing medical treatment outcome assessment or medical condition diagnostic |
Also Published As
Publication number | Publication date |
---|---|
US20140010430A1 (en) | 2014-01-09 |
HK1190903A1 (en) | 2014-07-18 |
CA2827742A1 (en) | 2012-08-30 |
US9717414B2 (en) | 2017-08-01 |
EP2678827A4 (en) | 2017-10-25 |
AU2012220301A1 (en) | 2013-09-12 |
CN103501699A (en) | 2014-01-08 |
CN103501699B (en) | 2016-01-13 |
BR112013021657B1 (en) | 2021-03-16 |
JP2014507231A (en) | 2014-03-27 |
KR101967357B1 (en) | 2019-04-09 |
KR20140009407A (en) | 2014-01-22 |
BR112013021657A2 (en) | 2017-07-04 |
CA2827742C (en) | 2018-07-17 |
AU2012220301B2 (en) | 2017-04-13 |
JP6031454B2 (en) | 2016-11-24 |
EP2678827A1 (en) | 2014-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2012220301B2 (en) | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery | |
US7876947B2 (en) | System and method for detecting tagged material using alpha matting | |
JP6877868B2 (en) | Image processing equipment, image processing method and image processing program | |
US20030099385A1 (en) | Segmentation in medical images | |
Dhara et al. | Computer-aided detection and analysis of pulmonary nodule from CT images: a survey | |
Bhadoria et al. | Comparison of segmentation tools for multiple modalities in medical imaging | |
CA2727736C (en) | Method and system for determining an estimation of a topological support of a tubular structure and use thereof in virtual endoscopy | |
US7480401B2 (en) | Method for local surface smoothing with application to chest wall nodule segmentation in lung CT data | |
WO2005112769A1 (en) | Nodule detection | |
EP1831817A2 (en) | System, software arrangement and method for segmenting an image | |
Kaftan et al. | Fuzzy pulmonary vessel segmentation in contrast enhanced CT data | |
Sun et al. | Juxta-vascular nodule segmentation based on flow entropy and geodesic distance | |
US20050002548A1 (en) | Automatic detection of growing nodules | |
Freiman et al. | A variational method for vessels segmentation: algorithm and application to liver vessels visualization | |
JP2012504003A (en) | Fault detection method and apparatus executed using computer | |
Tankyevych | Filtering of thin objects: applications to vascular image analysis | |
KR101494975B1 (en) | Nipple automatic detection system and the method in 3D automated breast ultrasound images | |
Devi et al. | Computer aided diagnosis scheme for polyp detection in CT colonography using K-means clustering and SVM | |
Suzuki | Pixel-based artificial neural networks in computer-aided diagnosis | |
Shaukat | AN EFFICIENT ALGORITHMIC SOLUTION FOR AUTOMATIC SEGMENTATION OF LUNGS FROM CT IMAGES | |
Wu et al. | Multi-scale Medical Image Segmentation Based on Salient Region Detection | |
Promkumtan et al. | Hybrid framework for 3D colon model reconstruction from computed tomographic colonography. | |
Schoonenberg et al. | Effects of filtering on colorectal polyp detection in ultra low dose CT | |
Wang et al. | Data Processing and Analysis | |
Swanly et al. | Research Article Smart Spotting of Pulmonary TB Cavities Using CT Images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12748944 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2827742 Country of ref document: CA |
|
ENP | Entry into the national phase |
Ref document number: 2013554763 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012748944 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2012220301 Country of ref document: AU Date of ref document: 20120224 Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14001628 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 20137025156 Country of ref document: KR Kind code of ref document: A |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112013021657 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112013021657 Country of ref document: BR Kind code of ref document: A2 Effective date: 20130823 |