WO2010019121A1 - Procédés permettant d'améliorer des motifs vasculaires dans le domaine de l'imagerie cervicale - Google Patents
Procédés permettant d'améliorer des motifs vasculaires dans le domaine de l'imagerie cervicale Download PDFInfo
- Publication number
- WO2010019121A1 WO2010019121A1 PCT/US2008/009777 US2008009777W WO2010019121A1 WO 2010019121 A1 WO2010019121 A1 WO 2010019121A1 US 2008009777 W US2008009777 W US 2008009777W WO 2010019121 A1 WO2010019121 A1 WO 2010019121A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- areas
- enhancement
- contrast
- intensity
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000002792 vascular Effects 0.000 title description 4
- 230000002708 enhancing effect Effects 0.000 title description 3
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 26
- 238000012800 visualization Methods 0.000 claims abstract description 24
- 230000001965 increasing effect Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 abstract description 10
- 201000010099 disease Diseases 0.000 abstract description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 4
- 210000003679 cervix uteri Anatomy 0.000 description 17
- 238000003384 imaging method Methods 0.000 description 14
- 210000001519 tissue Anatomy 0.000 description 12
- 210000003484 anatomy Anatomy 0.000 description 11
- 238000012545 processing Methods 0.000 description 9
- 208000004434 Calcinosis Diseases 0.000 description 8
- 238000001514 detection method Methods 0.000 description 8
- 210000004072 lung Anatomy 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 5
- 230000003902 lesion Effects 0.000 description 5
- 230000000877 morphologic effect Effects 0.000 description 5
- 208000006105 Uterine Cervical Neoplasms Diseases 0.000 description 4
- 239000008280 blood Substances 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 238000002573 colposcopy Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000002608 intravascular ultrasound Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000001629 suppression Effects 0.000 description 4
- 230000002123 temporal effect Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 206010008342 Cervix carcinoma Diseases 0.000 description 3
- 201000010881 cervical cancer Diseases 0.000 description 3
- 239000002872 contrast media Substances 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 206010059313 Anogenital warts Diseases 0.000 description 2
- 208000000907 Condylomata Acuminata Diseases 0.000 description 2
- 206010027476 Metastases Diseases 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 208000025009 anogenital human papillomavirus infection Diseases 0.000 description 2
- 201000004201 anogenital venereal wart Diseases 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000001054 cortical effect Effects 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
- 230000005670 electromagnetic radiation Effects 0.000 description 2
- 210000000981 epithelium Anatomy 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 230000009401 metastasis Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 206010008263 Cervical dysplasia Diseases 0.000 description 1
- 206010054949 Metaplasia Diseases 0.000 description 1
- 206010033724 Papilloma viral infections Diseases 0.000 description 1
- 108091081062 Repeated sequence (DNA) Proteins 0.000 description 1
- 208000005475 Vascular calcification Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000001574 biopsy Methods 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 208000007951 cervical intraepithelial neoplasia Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 210000000038 chest Anatomy 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 210000005045 desmin Anatomy 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 229910003460 diamond Inorganic materials 0.000 description 1
- 239000010432 diamond Substances 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001744 histochemical effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000002075 inversion recovery Methods 0.000 description 1
- 230000005415 magnetization Effects 0.000 description 1
- 238000009607 mammography Methods 0.000 description 1
- 230000015689 metaplastic ossification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000001208 nuclear magnetic resonance pulse sequence Methods 0.000 description 1
- 238000009595 pap smear Methods 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 210000005000 reproductive tract Anatomy 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 238000013185 thoracic computed tomography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 210000001215 vagina Anatomy 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 210000003905 vulva Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- 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 generally relates to medical imaging and image enhancement. This invention relates more specifically to computer aided detection and/ or diagnosis of uterine cervical cancer and pre-cancerous lesions.
- a colposcopic examination involves a systematic visual evaluation of the lower genital tract (cervix, vulva, and vagina) with the purpose of identifying and ranking the severity of lesions, so that biopsies representing the highest-grade abnormality can be taken, if necessary.
- visualization enhancement techniques are employed in medical imaging to improve the identification of diagnostically significant tissue structures.
- different colored filters are used to accentuate blood vessel patterns that cannot be easily seen by using regular white light.
- a green filter is commonly used and blocks all light except green light and allows for the increased visualization of cervical blood vessel patterns.
- the implementation of the green filter visual enhancement is commonly accomplished by filtering the standard white light by placing a green-colored optical filter at the output end of the light source, i.e. illuminating the cervix with green light, or by placing a green-colored filter between the cervix and the colposcope detection optics, i.e. filtering the reflected white light before being detected, either visually by the operator or electronically with an imaging sensor.
- a green-colored optical filter at the output end of the light source, i.e. illuminating the cervix with green light
- a green-colored filter between the cervix and the colposcope detection optics i.e. filtering the reflected white light before being detected, either visually by the operator or electronically with an imaging sensor.
- Mathematical morphology is a technique for the analysis and processing of geometrical structures and has been used, as related to the current invention, in the automated analysis of vessels from angiograms (K. Sun and N. Sang, Enhancement of vascular angiogram by multiscale morphology, in Bioinformatics and Biomedical Engineering, 1311-1313 (2007), incorporated herein by reference), micro-calcification analysis from mammograms (Wirth, M., Fraschini, M., and Lyon, J., Contrast enhancement of microcalcifications in mammograms using morphological enhancement and non-flat structuring elements, Proc. 17* IEEE Symposium on Computer-Based Medical Systems, (2008), incorporated herein by reference) and brain magnetic resonance imaging (J.D.
- the algorithm approach can be applied to the standard white light image, providing an image display that is more pleasingly to the human eye.
- image pre-processing steps can be performed to further improve the visualization enhancement.
- One such step would be to segment the images into different regions and apply the visualization enhancement to some of these regions only; for example, only those regions with a high likelihood of finding pre-cancerous or cancerous lesions.
- Applying a visual enhancement algorithm as described in the current invention to uterine cervical images can provide the physician with increased visualization of blood vessel patterns that are sometimes difficult to detect by the naked eye. Such an algorithm could assist the physician in the identification of diagnostically important structures and provide important information in the diagnostic process.
- US Patent Number 6,147,705 to Rrauter et al discloses a video colposcope which includes a system microcomputer having algorithms for color balance levels stored into memory.
- a video camera obtains a subject electronic image of a subject object, and using algorithm-driven digital signal processing circuitry (DSP), color saturation, hue, and intensity levels of the subject electronic image are modified according to previously stored DSP reference filter algorithms and reference color balance levels, thus producing a modified electronic image corresponding to the subject electronic image.
- DSP digital signal processing circuitry
- the modified electronic image is outputted to a display in continuous real time as the corresponding subject image is obtained by the video camera.
- This modified electronic image emulates that obtained through an optical green filter and incorporates a simulated white balance.
- US Patent Number 6,277,067 to Blair discloses a method and portable apparatus for the visual examination and grading of cervical epithelium by means of a hand-held colposcope assembly capable of producing a digital image of the cervix.
- This invention enables realtime imaging and archiving of the entire cervix for the purpose of detecting cancerous and pre-cancerous tissue and by virtue of computerized image processing to suggest an objective diagnosis of the cervical epithelium by means of a low cost, portable, hand-held digital colposcope.
- US Patent Number 6,032,070 to Flock et al. discloses a system and method to view an anatomical structure such as blood vessels in high contrast with its surrounding tissue.
- the system and method is used to produce an image of an anatomical structure using reflected electromagnetic radiation singularly scattered from target tissue.
- the system and method also provide same-side illumination and detection of reflected electromagnetic radiation in a convenient integral imaging device.
- the system and method also provides helmet mounted imaging technology in a single integral helmet which allows the wearer to view an anatomical structure located within a patient such that the image is continuously orientated according to the orientation to the helmet wearer's head.
- the system and method is also used in the performance of venipuncture.
- the system and method provide improved contrast between any anatomical structure and its surrounding tissue for use in any imaging system.
- US Patent Number 7,305,111 to Arimura et al. discloses a method, system, and computer program product for detecting at least one nodule in a medical image of a subject, including identifying, in the medical image, an anatomical region corresponding to at least a portion of an organ of interest; filtering the medical image to obtain a difference image; detecting, in the differenced image, a first plurality of nodule candidates within the anatomical region, calculating respective nodule feature values of the first plurality of nodule candidates from the first plurality based on pixel values of at least one of the medical images and the differenced image; removing false positive nodule candidates from the first plurality of nodule candidates based on the respective nodule feature values to obtain a second plurality of nodule candidates; and determining the at least one nodule by classifying each of the second plurality of nodule candidates as a nodule or a non-nodule based on at least one of the pixel values
- the method includes: acquiring, using a first imaging modality, a first medical image that includes the anatomical structure; applying the first medical image to a trained image processing device to obtain a second medical image, corresponding to the first medical image in which the appearance of the anatomical structure is modified; and outputting the second medical image.
- the image processing device is trained using plural teacher images obtained from a second imaging modality that is different from the first imaging modality.
- the method also includes processing the first medical image to obtain plural processed images, wherein each of the plural processed images has a corresponding image resolution; applying the plural processed images to respective multi-training artificial neural networks (MTANNs) to obtain plural output images, wherein each MTANN is trained to detect the anatomical structure at one of the corresponding image resolutions; and combining the plural output images to obtain a second medical image in which the appearance of the anatomical structure is enhanced.
- MTANNs multi-training artificial neural networks
- US Patent Application Number 2006/0018548 to Chen et al. discloses a method, system, and computer software product for analyzing medical images, including obtaining image data representative of a plurality of medical images of the abnormality, each medical image corresponding to an image of the abnormality acquired at a different time relative to a time of administration of a contrast medium, each medical image including a predetermined number of voxels; partitioning each medical image into at least two groups based on the obtained image data, wherein each group corresponds to a subset of the predetermined number of voxels, and each group is associated with a temporal image pattern in the plurality of medical images; selecting, from among the temporal patterns, an enhancement temporal pattern as representative of the abnormality; and determining, based on the selected temporal pattern, a medical state of the abnormality.
- US Patent Application Number 2006/0147101 to Zhang et al. discloses a method for computer-aided detection of microcalcification clusters that obtains digital mammography data for a single view image and normalizes and filters the image data to reduce noise.
- a first mask is generated and applied to the image data for defining the breast structure, forming a first cropped image.
- a second mask is generated and applied to the image data for defining muscle structure, forming a second cropped image.
- An artifact mask corresponding to vascular calcifications and known imaging artifacts is generated and applied to the first and second cropped images, defining first and second artifact-masked cropped images.
- inversion pulses are successively applied to the imaged slice and the slab orthogonal to the imaging plane, with the thickness equal to the FOV size in the phase-encoding direction.
- Each double-inversion results in a reinversion of the magnetization in a central part of the FOV, while outer areas of the FOV and inflowing blood remain inverted.
- the SFQIR module was implemented for single-slice and multislice acquisition with a fast spin-echo readout sequence. Timing parameters of the sequence corresponding to the maximal suppression efficiency can be found by minimizing variation of the normalized signal over the entire range of T. sub.1 occurring in tissues.
- US Patent Application Number 2007/0165921 to Agam et al. discloses a method for improving a thoracic diagnostic image for the detection of nodules.
- Non-lung regions are removed from the diagnostic image to provide a lung image.
- Vessels and vessel junctions of the lung(s) in the lung image are enhanced according to a first-order partial derivative of each of a plurality of voxels of the lung image.
- a vessel tree representation is constructed from the enhanced vessels and vessel junctions. The vessel tree representation can be subtracted from the lung image to enhance the visibility of nodules in the lung(s).
- IVUS intravascular ultrasound
- New catheter designs including contrast agent introduction subsystems and/ or Doppler subsystems are disclosed.
- Methods for acquiring and analyzing Doppler data from intravascular ultrasound (IVUS) catheters are disclosed.
- RF-based detection of blood and/ or contrast agents such as micro-bubbles are disclosed.
- Methods for frame-grating image data analysis permitting frame registration before, during and after a contrasting effect is imposed on a system being imaged are disclosed.
- Methods for difference imaging for contrast detection are disclosed.
- Methods for quantification and visualization of IVUS data are disclosed. And methods for IVUS imaging are disclosed.
- US Patent Application Number to Shen et al. discloses a method and system for automatically detecting rib metastasis in a thoracic CT volume.
- the ribs are segmented in said CT volume by recursive tracing.
- a series of cross-sectional images are then generated along a centerline of each rib.
- Cortical and trabecular bone structures are segmented in each of the cross-sectional images for each rib.
- Features are calculated for each cross-sectional image based on characteristics of the cortical and trabecular bone structures, and alterations are detected in the cross-sectional images based on the features.
- Rib metastasis is detected in a rib when an alteration is detected in a number of consecutive cross-sectional images along the centerline of the rib.
- the presently preferred embodiment of the present invention comprises identifying a texture region in an image having blood vessel structures; detecting high intensity areas and low intensity areas in the texture region; and controllably variably increasing contrast between the high intensity areas and the low intensity areas without introducing unacceptable unwanted noise, by using a tuning parameter to controllably variably add the high intensity areas to the texture region and subtract the low intensity areas from the texture region, so that visualization of the blood vessel patterns is controllably variably enhanced.
- the invention comprises a method of image contrast enhancement for increased visualization of blood vessel structures by identifying a texture region with high likelihood of presence of disease, applying mathematical morphology operations to detect high and low intensity (brightness) areas within the texture region, and calculating a contrast enhanced image by combining the result of the texture region identification, morphological operations and a tuning parameter.
- the texture region is identified in the original image by determining areas within the image with high variations in intensity.
- areas of high and low intensity within the texture region are identified using mathematical mo ⁇ hology operations.
- variable amounts, determined by a selectable tuning parameter, of the high intensity areas are added, and the low intensity areas are subtracted, from the texture region of the original image, producing images with controllably variable visualization enhancement of blood vessel structures.
- FIG 1 shows a flowchart of the visualization enhancement method
- FIG 2 (a) shows an image of the cervix and FIG 2 (b) shows the identified texture region of the cervix;
- FIG 3 (a) shows the original cervical image
- FIG 3 (b) displays a magnified region (indicated by a square in FIG 3 (a)) of the original image without contrast enhancement
- FIGS 3 (c), 3 (d) and 3 (e) show the result of the blood vessel structure enhancement with the tuning parameter, ⁇ , set to 0, 0.5, and 1.0, respectively.
- the presently preferred embodiment of the invention provides a method which increases and controllably varies the contrast between small blood vessel patterns and the surrounding tissue, without introducing artifacts (noise) in images of the uterine cervix, and as such provides a means to enhance the visualization of said blood vessel patterns.
- a flowchart of the presently preferred embodiment of the invention is shown in FIG 1. The steps of the presently preferred method are described in more detail below. 1. Texture Region Identification
- the visualization (contrast) enhancement method starts with an image of an organ or tissue (such as the cervix) (designated I).
- a segmentation step is applied to the image in which the texture region of the cervix is identified.
- Texture analysis refers to the characterization of regions in an image by their texture. Texture analysis attempts to quantify rough, smooth, silky, or bumpy as a function of the spatial intensity variations in the image (the spatial extent of variations in brightness (or intensity) of the image, preferably measured by using variations in brightness in a black and white version of the image, or "grayscale").
- roughness or bumpiness can be understood as the spatial extent of variations in intensity values, or gray levels, in a black and white version of the image.
- the texture region is referred to as the region which is rich in texture content or, in other words, has high variations in intensity (instead of being smooth in intensity).
- the cervical texture region is associated with both diseased findings, such as abnormal blood vessel structures, and normal findings, such as immature metaplasia. If cervical blood vessel patterns are not located within these fields of rich texture, pre-cancerous lesions are less likely. Thus, by detecting the texture regions, and only applying the enhancement algorithm to these areas, only blood vessel patterns associated with precancerous or cancerous lesions will be visually enhanced.
- This invention provides the means for controllable contrast enhancement and, with segmentation, controllable local contrast enhancement.
- the preferred texture region identification used in the present invention is based on the work presented by Li et al (W. Li, J. Gu, D. Ferris, and A. Poirson, Automated image analysis of uterine cervical images, Proc. OfSPIE 6414, 65142P1-65142P9 (2007), incorporated herein by reference) which utilizes parts of a technique presented by Forstner (Forstner, W., A framework for low level feature extraction, in Proc. of European Conference on Computer Vision, 383-394 (1994), incorporated herein by reference), Grading et al (Grading, J.
- the texture region analysis method determines the texture contrast (i.e. intensity variations) in the image, and separates the image into areas of high and low texture.
- the high texture areas are clustered in one region, which defines the texture region in the cervical image.
- the texture region which is a sub-part of the entire cervical image, I, is designated /, practice, convention, «..
- FIG 2 (a) shows an image of the cervix
- FIG 2 (b) shows the texture region identified using the method described above.
- detecting the texture region is the preferred method of the current invention, it is not a pre-requisite for the following steps.
- the entire image of the cervix can just as well be used in the following steps.
- the step following optional detection of the texture region preferably uses operations based on mathematical morphology (J. Serra, Image Analysis and Mathematical Morphology, Academic Press, New York, 1982, incorporated herein by reference).
- Mathematical morphology is a technique for the analysis and processing of geometrical structures, such as blood vessel patterns, using a few simple mathematical concepts from set theory (which is a branch of mathematics that studies the collections of objects).
- the basic idea in mathematical morphology is to compare the structures in an image against a so- called structuring element having a simple pre-defined shape, and drawing conclusions on how this shape fits or misses the structures in the image.
- Commonly used structuring elements in mathematical morphology include, but are not limited to, disk shape, box shape, and diamond shape.
- Mathematical morphology is commonly applied to digital images, and includes edge detection, noise removal, image enhancement and image segmentation.
- the preferred morphology methods used in the present invention are the top-hat and bottom-hat filters (P. Soille, A note on morphological contrast enhancement, Technical Report concluded ijk des Mines d'Ales-EERIE (1997), incorporated herein by reference; F. Meyer, Iterative image transformations for an automatic screening of cervical smears, The Journal of Histochemistry and Cytochemistry, The Histochemical Society, 128-135 (1979), incorporated herein by reference).
- the top-hat filter captures high intensity (bright) areas in an image.
- the top-hat filter is based on neighborhood ranking and uses the ranked value from two different sized areas.
- the brightest value in an area defined by a sliding window is compared to the brightest value in a surrounding annular (ring-shaped) area. If the brightness difFerence exceeds a threshold value (typically defined as the average brightness of the surrounding area), the area is defined as a bright area.
- a threshold value typically defined as the average brightness of the surrounding area
- the output of the top-hat filter defines the high brightness areas in the image and is designated
- a bottom-hat filter can be used to capture low intensity (dark) areas, such as the blood vessel structures.
- the size of the sliding window preferably a disk shaped structuring element
- the output of the bottom-hat filter defines the low intensity (darker) areas in the image and is designated BH(I textur J.
- the final step in the preferred embodiment of the current invention combines the information from the previous steps in order to improve the local contrast of the image by enhancing the contrast between blood vessel structures and the surrounding tissue.
- One preferred method is low intensity based contrast enhancement which involves subtracting the low intensity areas from the original image and by doing so, increasing the contrast between the low intensity areas and their surroundings (K. Sun and N. Sang, Enhancement of vascular angiogram by multiscale morphology, in Bioinformatics and Biomedical Engineering, 1311-1313 (2007), incorporated herein by reference).
- Another preferred method is high intensity contrast enhancement which involves adding the output from the top-hat operation (the high intensity areas) and subtracting the bottom-hat output (the low intensity areas) from the original image.
- I enHancC U ,, ⁇ e + ⁇ TH ⁇ I ⁇ J]- BH ⁇ I ⁇ ) (1) to create an enhanced image;
- I mhanC ede •
- the controllably variable tuning parameter, a has values controllably selectable between 0 and 1, and provides a means for variable visualization (contrast) enhancement similar to different filter characteristics. From Equation (1), we can see that the tuning parameter preferably only controls the output of the top hat filter and therefore only controls contrast enhancement of the high intensity (brightness) areas, and does not control the output of the bottom hat filter (the contrast enhancement of the low intensity (brightness) areas).
- a value of a 0 means that no high intensity based contrast enhancement is applied which, as described above, has the effect of only subtracting the low intensity areas from the original image and by doing so only increases the contrast of the low intensity areas from their surroundings.
- a value of a 1 adds the full output from the top-hat filter and subtracts the bottom-hat output from the original image which, as described above, stretches both the high intensity areas toward increased intensity and low intensity areas towards decreased intensity, thereby applying maximum contrast enhancement.
- a value of the 0 ⁇ a ⁇ 1 provides (in addition to variable contrast enhancement) a means of controlling the amount of unwanted noise generated in the enhanced image.
- the reason for this behavior is a consequence of the properties (statistical variations) of light. For example, noise in detected signals increases with the intensity of the light.
- a controllably variable visualization enhancement will also provide the user the opportunity to fine tune the amount of contrast enhancement to his or her personal preference.
- FIG 3 shows the original cervical image and FIG 3 (b) displays a magnified region of the original image without contrast enhancement.
- FIG 3 (c), Fig 3(d), and Fig. 3(e) show the results of the contrast enhancement with the tuning parameter, a, set to 0, 0.5, and 1.0, respectively, clearly demonstrating the increased visualization of the blood vessel structure.
- This invention provides visualization enhancement and is not limited to blood vessels or the cervix.
- the contrast enhancement method may also be suitable for other tissue diagnosis instruments and for any other methods that require variable adjustment of contrast.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Endoscopes (AREA)
Abstract
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/US2008/009777 WO2010019121A1 (fr) | 2008-08-15 | 2008-08-15 | Procédés permettant d'améliorer des motifs vasculaires dans le domaine de l'imagerie cervicale |
JP2011522944A JP2012500040A (ja) | 2008-08-15 | 2008-08-15 | 子宮頸部画像における血管パターンを強調するための方法 |
EP08795361A EP2313848A4 (fr) | 2008-08-15 | 2008-08-15 | Procédés permettant d'améliorer des motifs vasculaires dans le domaine de l'imagerie cervicale |
CN200880130729.3A CN102124471A (zh) | 2008-08-15 | 2008-08-15 | 用于增强宫颈成像中的血管图案的方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/US2008/009777 WO2010019121A1 (fr) | 2008-08-15 | 2008-08-15 | Procédés permettant d'améliorer des motifs vasculaires dans le domaine de l'imagerie cervicale |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2010019121A1 true WO2010019121A1 (fr) | 2010-02-18 |
Family
ID=41669099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2008/009777 WO2010019121A1 (fr) | 2008-08-15 | 2008-08-15 | Procédés permettant d'améliorer des motifs vasculaires dans le domaine de l'imagerie cervicale |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP2313848A4 (fr) |
JP (1) | JP2012500040A (fr) |
CN (1) | CN102124471A (fr) |
WO (1) | WO2010019121A1 (fr) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102682305B (zh) * | 2012-04-25 | 2014-07-02 | 深圳市迈科龙医疗设备有限公司 | 宫颈液基细胞学自动筛查方法和*** |
KR101578770B1 (ko) * | 2013-11-21 | 2015-12-18 | 삼성전자주식회사 | 의료 영상 처리 장치 및 그에 따른 의료 영상 처리 방법 |
CN103593829A (zh) * | 2013-11-26 | 2014-02-19 | 北京科技大学 | 基于数学形态学运算的手背静脉显像方法 |
JP6523642B2 (ja) * | 2014-09-26 | 2019-06-05 | テルモ株式会社 | 画像診断装置 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040013292A1 (en) * | 2002-05-17 | 2004-01-22 | Pfizer, Inc. | Apparatus and method for statistical image analysis |
US20070002275A1 (en) * | 2005-07-01 | 2007-01-04 | Siemens Corporate Research Inc. | Method and System For Local Adaptive Detection Of Microaneurysms In Digital Fundus Images |
US20080081998A1 (en) * | 2006-10-03 | 2008-04-03 | General Electric Company | System and method for three-dimensional and four-dimensional contrast imaging |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0816815A (ja) * | 1994-06-28 | 1996-01-19 | Ge Yokogawa Medical Syst Ltd | 画像処理方法及び画像処理装置 |
JP3568279B2 (ja) * | 1995-06-30 | 2004-09-22 | 富士写真フイルム株式会社 | 画像再生方法および装置 |
US5793883A (en) * | 1995-09-29 | 1998-08-11 | Siemens Medical Systems, Inc. | Method for enhancing ultrasound image |
JP4274590B2 (ja) * | 1997-01-20 | 2009-06-10 | オリンパス株式会社 | 画像処理装置 |
FR2829268A1 (fr) * | 2001-09-04 | 2003-03-07 | Koninkl Philips Electronics Nv | Procede de traitement d'images pour angiographie soustractiv e numerisee |
JP4159291B2 (ja) * | 2002-01-30 | 2008-10-01 | フジノン株式会社 | 電子内視鏡装置 |
JP3572304B2 (ja) * | 2002-05-23 | 2004-09-29 | 稔 冨田 | 医療分野におけるフォトレタッチソフトウェアを用いた画像解析方法 |
JP2004032137A (ja) * | 2002-06-24 | 2004-01-29 | Pentax Corp | 画像輪郭強調装置 |
CN1910590A (zh) * | 2004-01-15 | 2007-02-07 | 皇家飞利浦电子股份有限公司 | 图像中的自动造影剂控制 |
JP2006261861A (ja) * | 2005-03-15 | 2006-09-28 | Fuji Photo Film Co Ltd | 撮像装置 |
DE102005035430A1 (de) * | 2005-07-28 | 2007-02-01 | Siemens Ag | Verfahren zur verbesserten Darstellung co-registrierter 2D-3D-Bilder in der medizinischen Bildgebung |
DE602007007340D1 (de) * | 2006-08-21 | 2010-08-05 | Sti Medical Systems Llc | Computergestützte analyse mit hilfe von videodaten aus endoskopen |
-
2008
- 2008-08-15 CN CN200880130729.3A patent/CN102124471A/zh active Pending
- 2008-08-15 WO PCT/US2008/009777 patent/WO2010019121A1/fr active Application Filing
- 2008-08-15 EP EP08795361A patent/EP2313848A4/fr not_active Withdrawn
- 2008-08-15 JP JP2011522944A patent/JP2012500040A/ja active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040013292A1 (en) * | 2002-05-17 | 2004-01-22 | Pfizer, Inc. | Apparatus and method for statistical image analysis |
US20070002275A1 (en) * | 2005-07-01 | 2007-01-04 | Siemens Corporate Research Inc. | Method and System For Local Adaptive Detection Of Microaneurysms In Digital Fundus Images |
US20080081998A1 (en) * | 2006-10-03 | 2008-04-03 | General Electric Company | System and method for three-dimensional and four-dimensional contrast imaging |
Non-Patent Citations (1)
Title |
---|
See also references of EP2313848A4 * |
Also Published As
Publication number | Publication date |
---|---|
CN102124471A (zh) | 2011-07-13 |
EP2313848A4 (fr) | 2012-08-29 |
EP2313848A1 (fr) | 2011-04-27 |
JP2012500040A (ja) | 2012-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8351667B2 (en) | Methods of contrast enhancement for images having blood vessel structures | |
JP5113841B2 (ja) | 内視鏡からの映像を用いるコンピュータ支援解析 | |
Azhari et al. | Brain tumor detection and localization in magnetic resonance imaging | |
Abd Halim et al. | Nucleus segmentation technique for acute leukemia | |
JP4311598B2 (ja) | 異常陰影検出方法および装置 | |
JP2007007440A (ja) | 医療画像において腫瘤や実質組織変形をコンピュータを用いて検出する自動化した方法と装置 | |
CN110610498A (zh) | 乳腺钼靶图像处理方法、***、存储介质及设备 | |
CN110288698B (zh) | 基于mri的半月板三维重建*** | |
Dabass et al. | Biomedical image enhancement using different techniques-a comparative study | |
Ganvir et al. | Filtering method for pre-processing mammogram images for breast cancer detection | |
WO2010019121A1 (fr) | Procédés permettant d'améliorer des motifs vasculaires dans le domaine de l'imagerie cervicale | |
Wang et al. | Improving segmentation of breast arterial calcifications from digital mammography: good annotation is all you need | |
Wu et al. | Hybrid enhancement algorithm for nailfold images with large fields of view | |
Ye et al. | Segmentation and feature extraction of endoscopic images for making diagnosis of acute appendicitis | |
JPH08287230A (ja) | 計算機支援画像診断装置 | |
Zainudin et al. | Feature extraction on medical image using 2D Gabor filter | |
Sobhi et al. | Extraction of Laryngeal Cancer Informative Frames from Narrow Band Endoscopic Videos | |
JP7478245B2 (ja) | 医療画像装置及びその作動方法 | |
Prakash | Medical image processing methodology for liver tumour diagnosis | |
Bashir et al. | Enhancement of fundus images for diagnosing diabetic retinopathy using B-spline | |
Sowmiya et al. | Survey or Review on the Deep Learning Techniques for Retinal Image Segmentation in Predicting/Diagnosing Diabetic Retinopathy | |
Lavanya et al. | Retinal vessel feature extraction from fundus image using image processing techniques | |
Azhari et al. | Glioblastoma multiforme identification from medical imaging using computer vision | |
Kannan et al. | Brain cancer analysis using deep learning architecture on MRI brain image | |
Kothapalli et al. | Spectral Phase Based Medical Image Processing1 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200880130729.3 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 08795361 Country of ref document: EP Kind code of ref document: A1 |
|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2008795361 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2011522944 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |