CN110211104B - Image analysis method and system for computer-aided detection of lung mass - Google Patents
Image analysis method and system for computer-aided detection of lung mass Download PDFInfo
- Publication number
- CN110211104B CN110211104B CN201910436100.1A CN201910436100A CN110211104B CN 110211104 B CN110211104 B CN 110211104B CN 201910436100 A CN201910436100 A CN 201910436100A CN 110211104 B CN110211104 B CN 110211104B
- Authority
- CN
- China
- Prior art keywords
- image
- region
- points
- foreground
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
- G06T2207/30061—Lung
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention belongs to the technical field of pattern recognition, image processing and computer vision, and particularly relates to an image analysis method and system for computer-aided detection of lung masses. According to the method, the area of the suspected lump is found according to the change detection of the adjacent frame image, and the filtering is further carried out according to the area form. The image analysis system of the invention comprises the following links: image acquisition, foreground point marking, adjacent frame change detection, suspected lump form filtering and result visualization. The invention has the advantages that: without image data annotation, lung masses can be automatically found from a sequence of CT slice images in an unsupervised manner. The experimental results show that: the method can realize automatic discovery and marking of the tumor and can be used for assisting the diagnosis of doctors.
Description
Technical Field
The invention belongs to the technical field of pattern recognition, image processing and computer vision, and particularly relates to a lung mass image analysis method and system, which can be used for computer-aided diagnosis.
Background
Computer-aided diagnosis of medical images has been of great interest. At present, the deep neural network [1] [2] [3] becomes the mainstream method, but requires a large amount of training data. However, data annotation is costly and not easily accessible. Furthermore, there is often a problem of inconsistency in the raw image values due to device differences, which can degrade the performance of a model trained on one data set over another. The invention therefore proposes an unsupervised computer-aided diagnosis method, which is knowledge-based and therefore has better scene adaptability.
The method can be used for automatically finding the lung tumor in the CT image. From the observation that if a slice of a CT image is traversed and treated as a video-like sequence of images, tumors always appear in a nearly abrupt manner and the number of frames that persist is short. This motivates us to solve the problem of automatic lung mass finding by means of change detection in video processing.
The deep neural network method [1] [2] [3] is based on image block convolution, needs a large amount of training data, and has large cost for a nearly exhaustive feature map calculation method. The unsupervised method has some applications [4] [5] in image segmentation, but image segmentation is often not robust, and over-segmentation or under-segmentation often occurs; since tumors tend to adhere to normal organ tissue, it is very difficult to identify tumors using image segmentation techniques. Another scheme is that an image registration technology is adopted to carry out change detection [6] [7]; such methods are computationally expensive and not stable enough. Furthermore, the above methods all rely on precise segmentation and positioning of the lungs, which is very difficult [8] [9] [10]. The invention provides an image analysis method and system for the computer-aided detection of lung masses, which has the principle of monitoring sudden changes with short duration in a CT image sequence, so that accurate lung segmentation is not required; and because only the difference of the pixels needs to be calculated, the calculation amount is obviously smaller than that of other methods; in addition, the method is knowledge-based, does not depend on a data set greatly, and has strong universality.
Reference documents:
[1]Hongyang Jiang,He Ma,Wei Qian,Mengdi Gao,and Yan Li,“An Automatic Detection System of Lung Nodule Based on Multigroup Patch-Based Deep Learning Network”,IEEE Journal of Biomedical and Health Informatics,Vol.22,No.4,pp.1227-1237,July 2018.
[2]MariosAnthimopoulos,StergiosChristodoulidis,Lukas Ebner,Andreas Christe,and StavroulaMougiakakou,“Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network”,IEEE Transactions on Medical Imaging,Vol.35,No.5,pp.1207-1216,May 2016.
[3]Shin Hoo-Chang,Holger R.Roth,Mingchen Gao,Le Lu,Ziyue Xu,Isabella Nogues,Jianhua Yao,Daniel Mollura,and Ronald M.Summers,“Deep Convolutional Neural Networks for Computer-Aided Detection:CNN Architectures,Dataset Characteristics and Transfer Learning”,IEEE Transactions on Medical Imaging,Vol.35,No.5,pp.1285–1298,May 2016.
[4]BijjuKranthiVeduruparthi,JayantaMukhopadhyay,ParthaPratim Das,Mandira Sahay,SriramPrasathy,SoumendranathRayy,Raj Kumar Shrimaliy,and Sanjoy Chatterjee,“Segmentation of Lung Tumor in Cone Beam CT Images based on Level-Sets”,ICIP 2018,IEEE,pp.1398-1402.
[5]Zhe Liu,Yuqing Song,Charlie Maere,Qingfeng Liu,Yan Zhu,Hu Lu,and Deqi Yuan,“A Method for PET-CT Lung Cancer Segmentation based on Improved Random Walk”,2018 24th International Conference on Pattern Recognition(ICPR),IEEE,pp.1187-1192,Beijing,China,August 20-24,2018.
[6]Ahmed Soliman,FahmiKhalifa,Ahmed Shaffie,Neal Dunlap,Brain Wang,Adel Elmaghraby,Georgy Gimelfarb,Mohammed Ghazal,and Ayman El-Baz,“A Comprehensive Framework for Early Assessment of Lung Injury”,ICIP 2017,IEEE,pp.3275-3279.
[7]Ahmed Soliman,FahmiKhalifa,Ahmed Shaffie,Ni Liu,Neal Dunlap,Brian Wang,Adel Elmaghraby,Georgy Gimelfarb,and Ayman El-Baz,“Image–based CAD System for Accurate Identification of Lung Injury”,ICIP 2016,IEEE,pp.121-125.
[8]Ahmed Soliman,Ahmed Elnakib,FahmiKhalifa,Mohamed Abou El-Ghar,and Ayman El-Baz,“Segmentation of Pathological Lungs From CT Chest Images”,ICIP 2015,IEEE,pp.3655-3659.
[9]Ehsan Hosseini-Asl,Jacek M.Zurada,and Ayman El-Baz,“Automatic Segmentation of Pathological Lung Using Incremental Nonnegative Matrix Factorization”,ICIP 2015,IEEE,pp.3111-3115.
[10]Tuan Anh Ngo and Gustavo Carneiro,“Lung Segmentation in Chest Radiographs using Distance Regularized Level Set and Deep-Structured Learning and Inference”,ICIP 2015 IEEE,pp.2140-2143.。
disclosure of Invention
The invention aims to provide an image analysis method and an image analysis system for computer-aided detection of lung masses.
The invention provides an image analysis method for the computer-aided detection of lung masses, which automatically discovers and positions masses from images without labels in an unsupervised mode, and comprises the following specific steps:
(a) Scanning a human body through medical imaging equipment to obtain an image sequence (such as a CT image), wherein the sequencing principle is as follows: two slices that are spatially adjacent correspond to images of adjacent frames.
(b) And marking foreground points and background points for the image sub-sequence containing the lungs, wherein the points corresponding to the region where the lungs of each frame of image are located are used as the foreground points, and the rest points are used as the background points.
(c) Calculating the change between adjacent frame images, detecting a mutation area mark, and marking the mutation area as a suspected lump;
specifically, there may be 2 representative calculation methods:
(c1) Order to
Indicating that the image of the t-th frame is located at the coordinate (x) i ,y i ) The point (c) of (a) is,
and
respectively representing whether the point belongs to the foreground or the background, observing K +1 continuous frame images (K is more than or equal to 1), and regarding a point set which meets the following formula as a suspicious point:
clustering the obtained suspicious points into connected areas by an 8-neighbor area growing method, wherein each obtained connected area corresponds to one suspected lump;
(c2) Clustering foreground points of each frame of image into connected regions by an 8-neighbor region growing method, calculating the corresponding relation between the connected regions of the two frames of images, if a certain connected region (point set A) of the previous frame of image and a certain connected region (point set B) of the next frame of image meet | A-B | > infinity, marking A-B as a region where a suspected lump is located, wherein, ' A-B ' represents set subtraction, "| A-B | ' represents the number of elements of the set A-B, and τ is a threshold value (the value range is suggested as [0.05, ]).
(d) Filtering the suspected mass;
specifically, there may be the following 3 representative calculation methods:
(d1) If the number of points contained in a connected region consisting of a foreground point is less than a threshold value (the value range is suggested as [0,0.0005 × M × N ], where M and N represent the height and width of the image), excluding the region from the set of suspected lump regions;
(d2) Performing principal component analysis (principal component analysis) on a connected region formed by a foreground point, dividing a larger value of the two obtained characteristic values by a smaller value, and if a ratio is greater than a threshold value (a value range [3, ∞ ]), excluding the region from a set of suspected lump regions;
(d3) If the ratio of the number of points contained in the connected region consisting of a foreground point and the area of the minimum bounding rectangle of the region is less than a certain threshold (the value range is suggested to be [0,0.35 ]), the region is excluded from the set of suspected lump regions.
(e) And marking the lump at the corresponding coordinate position of the corresponding image frame.
For the above image analysis method, the invention also relates to an image analysis system for computer-aided detection of lung masses, the system comprising five modules: the human body acquisition image sequence acquisition and sorting module, the image lung area foreground point and background point marking module, the image mutation area detection and marking module, the suspected lump filtering module and the lump position marking module are sequentially and correspondingly executed to the operation contents of the steps (a), (b), (c), (d) and (e) in the image analysis method.
The invention has the advantages that: without image data annotation, lung masses can be automatically found from a sequence of CT slice images in an unsupervised manner. The experimental results show that: the method can realize automatic discovery and marking of the tumor and can be used for assisting the diagnosis of doctors.
Drawings
Fig. 1 is a block diagram of an automatic lung mass image detection system.
Fig. 2 shows a correctly detected mass (within a box).
Detailed Description
The image analysis system of the invention comprises the following links: the image analysis system comprises image acquisition, foreground point marking, adjacent frame change detection, suspected lump form filtering and result visualization, and the composition of the whole image analysis system is shown in figure 1.
Example 1:
(a) Scanning a human body through medical imaging equipment to obtain an image sequence (such as a CT image), wherein the sequencing principle is as follows: two slices which are spatially adjacent correspond to images of adjacent frames;
(b) For an image subsequence containing lungs, marking foreground points and background points, wherein points corresponding to the area where the lungs of each frame of image are located are used as the foreground points, and the rest points are used as the background points;
(c) Calculating the change between adjacent frame images, and marking the mutation area as a suspected lump: order to
Indicating that the image of the t-th frame is located at the coordinate (x) i ,y i ) The point (b) of,
And
respectively representing whether the point belongs to the foreground or the background, observing K +1 continuous frame images (K is more than or equal to 1), and regarding a point set which meets the following formula as a suspicious point:
clustering the obtained suspicious points into connected regions by using an 8-neighbor region growing method, wherein each obtained connected region corresponds to one suspected lump;
(d) Filtering the suspected lump:
if the number of points contained in a connected region consisting of foreground points is less than 0.0005 xMxN, where M and N represent the height and width of the image, excluding the region from the set of suspected tumor regions;
performing principal component analysis (principal component analysis) on a connected region formed by a foreground point, dividing the larger value of the two obtained characteristic values by the smaller value, and if the ratio is larger than a threshold value 3, excluding the region from the set of suspected lump regions;
if the ratio of the number of points contained in a connected region formed by a foreground point to the area of the minimum circumscribed rectangle of the region is less than 0.35, excluding the region from the set of suspected lump regions;
(e) And marking the lump at the corresponding coordinate position of the corresponding image frame.
In the step (b), the calculation steps of the method for determining the lung image subsequence and the foreground point are as follows:
(1) Assuming that the resolution of each slice image is M multiplied by N, and the CT value of a pixel (x, y) is I (x, y), marking the pixel points of which the CT value in the image satisfies {74 ≦ I (x, y) ≦ 774 x ∈ 1, M ^ y ∈ [1, N ] } as foreground points;
(2) Clustering the foreground points into connected regions by an 8-neighbor region growing method, wherein the definition of the connectivity is as follows: if some of 8 neighbor points of a foreground point are also foreground points, the neighbor points are communicated with the point and belong to the same communicated area;
(3) Filtering and screening the connected region by adopting a filtering method: if the number of points contained in a connected region formed by a foreground point is less than 0.01 multiplied by M multiplied by N, excluding the region from the set of connected regions;
(4) Sequentially scanning (in the direction from head to foot of the human body) the CT image of each slice until an image is found which contains and only contains 2 connected regions as the starting frame of the image subsequence of lungs, while marking the two connected regions as left and right lungs, respectively, according to position;
(5) Scanning downwards from the left lung and the right lung along the initial frame respectively to find a current lung region which meets the consistency test with the previous frame image, wherein the consistency test method comprises the following steps:
let n be i Representing the number of foreground points contained in a lung region in an image of a current frame (i-th frame), nOld representing the number of foreground points of the lung region of a previous frame, and nMax representing the number of foreground points corresponding to the maximum lung region recorded until the current frame is scanned;
if n is i <1.5 × nOld, the current frame passes consistency check, and nOld and nMax are updated:
let nOld = n i ；
If n is i >nMax, let nMax = n i ；
Otherwise, recording the current frame number T, and turning to the step (7);
(6) Repeating the step (5) until n i <0.5 multiplied by nMax, and recording the current frame number T;
(7) Tracing back from the current frame T until n appears i ≥n i-1 I-1 is marked as the last frame of the sub-sequence of lung images.
In the step (2), the calculation steps of the 8-neighbor region growing method are as follows:
(1) randomly selecting one of foreground points which are not scanned yet as a seed point of a current connected region;
(2) scanning 8 neighbor points of each foreground point contained in the current connected region and adding the foreground points into the current connected region;
(3) repeating the step (2) until no more foreground points communicated with the area can be found;
(4) if all foreground points are scanned, ending; otherwise, turning to the step (1).
The analysis of the CT images of 6 patients according to the method of example 1 detected 29 masses, 8 of which were real masses, including 5 patient masses, the real masses automatically discovered and labeled by the program being shown in FIG. 2.
Claims (8)
1. An image analysis method for computer-aided detection of lung masses, characterized in that masses are automatically found and located in an unsupervised manner from images that are completely unmarked, comprising the following steps:
(a) Scanning a human body through medical imaging equipment to obtain an image sequence, wherein the sequencing principle is as follows: two spatially adjacent slices correspond to images of adjacent frames;
(b) For an image subsequence containing lungs, marking foreground points and background points, wherein points corresponding to the area where the lungs of each frame of image are located are used as the foreground points, and the rest points are used as the background points;
(c) Calculating the change between adjacent frame images, detecting a mutation area, and marking the mutation area as a suspected lump;
(d) Filtering the suspected mass;
(e) Marking the lump at the corresponding coordinate position of the corresponding image frame;
in step (b), the method for determining the lung image subsequence and the foreground point is as follows:
(1) Assuming that the resolution of each slice image is MxN, and the CT value of a pixel (x, y) is I (x, y), marking a pixel point in the image with the CT value of {74 ≦ I (x, y) ≦ 774 x ∈ [1, M ] ^ y ∈ [1, N ] } as a foreground point; m and N represent the height and width of the image;
(2) Clustering the foreground points into connected regions by an 8-neighbor region growing method, wherein the definition of the connectivity is as follows: if some of 8 neighbor points of a foreground point are also foreground points, the neighbor points are communicated with the point and belong to the same communicated area;
(3) Filtering and screening the connected region by adopting a filtering method: if the number of points contained in a connected region formed by a foreground point is less than 0.01 multiplied by M multiplied by N, excluding the region from the set of connected regions;
(4) Sequentially scanning the CT image of each slice until an image is found that contains and only contains 2 connected regions as the starting frame of the lung image sub-sequence, while labeling the two connected regions as left and right lungs, respectively, according to position;
(5) Scanning downwards from the left lung and the right lung along the initial frame respectively to find a current lung region meeting the consistency test with the previous frame of image; the method for checking consistency comprises the following steps:
let n be q Representing the number of foreground points contained in a lung region in a current q frame image, nOld representing the number of foreground points in a lung region of a previous frame, and nMax representing the number of foreground points corresponding to a maximum lung region recorded until the current frame is scanned;
if n is q <1.5 × nOld, the current frame passes consistency check, and nOld and nMax are updated:
let nOld = n q ；
If n is q >nMax, let nMax = n q ；
Otherwise, recording the current frame number T, and turning to the step (7);
(6) Repeating the step (5) until n q <0.5 multiplied by nMax, and recording the current frame number T;
(7) Tracing back from the current frame T until n appears q ≥n q-1 Q-1 is marked as the last frame of the sub-sequence of lung images.
2. The image analysis method according to claim 1, wherein the method of detecting a mutated region in step (c) comprises the steps of:
order to
Indicating that the image of the t-th frame is located at the coordinate (x) i ,y i ) The point (c) of (a) is,
and
respectively representing whether the point belongs to the foreground or the background, observing K +1 continuous frame images, wherein K is more than or equal to 1, and regarding a point set meeting the following formula as a suspicious point:
and clustering the obtained suspicious points into connected regions by using an 8-neighbor region growing method, wherein each obtained connected region corresponds to one suspected lump.
3. The method for analyzing an image according to claim 1, wherein the method for detecting a mutation region in step (c) is:
clustering foreground points of each frame of image into connected regions by an 8-neighbor region growing method, calculating the corresponding relation between the connected regions of the two frames of images, recording a certain connected region of the previous frame of image as a point set A, recording a certain connected region of the next frame of image as a point set B, and marking A-B as a region where a suspected lump is located if | A-B | > tau is satisfied, wherein "A-B" represents set subtraction, "| A-B |" represents the number of elements of the set A-B, and tau is a threshold value.
4. The image analysis method according to any one of claims 1 to 3, wherein the suspected mass is filtered in step (d) by:
if a connected region of foreground points contains fewer points than a threshold δ ∈ [0,0.0005 × mxn ], where M and N represent the height and width of the image, the region is excluded from the set of suspected mass regions.
5. The method for image analysis according to any one of claims 1 to 3, wherein the suspected mass is filtered in step (d) by:
and performing principal component analysis on a connected region formed by a foreground point, dividing the larger value of the two obtained characteristic values by the smaller value, and if the ratio is greater than a threshold value, excluding the region from the set of suspected lump regions.
6. The method for image analysis according to any one of claims 1 to 3, wherein the suspected mass is filtered in step (d) by:
if the ratio of the number of points contained in a connected region formed by a foreground point to the area of the minimum circumscribed rectangle of the region is less than a certain threshold value, the region is excluded from the set of suspected lump regions.
7. The image analysis method according to claim 1, wherein in the step (b), the calculation step of the 8-neighbor region growing method is:
(1) randomly selecting one of foreground points which are not scanned yet as a seed point of a current connected region;
(2) scanning 8 neighbor points of each foreground point contained in the current connected region and adding the foreground points into the current connected region;
(3) repeating the step (2) until no more foreground points communicated with the area can be found;
(4) if all foreground points are scanned, ending; otherwise, turning to the step (1).
8. Image analysis system for computer-aided detection of lung masses based on the image analysis method of claim 1, 2, 3 or 7, characterized in that it comprises five modules: the system comprises a human body image sequence acquisition and sorting module, a foreground point and background point marking module of an image lung region, an image mutation region detection and marking module, a suspected lump filtering module and a lump position marking module, wherein the five modules sequentially and correspondingly execute the operation contents of steps (a), (b), (c), (d) and (e) in the image analysis method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910436100.1A CN110211104B (en) | 2019-05-23 | 2019-05-23 | Image analysis method and system for computer-aided detection of lung mass |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910436100.1A CN110211104B (en) | 2019-05-23 | 2019-05-23 | Image analysis method and system for computer-aided detection of lung mass |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110211104A CN110211104A (en) | 2019-09-06 |
| CN110211104B true CN110211104B (en) | 2023-01-06 |
Family
ID=67788380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910436100.1A Active CN110211104B (en) | 2019-05-23 | 2019-05-23 | Image analysis method and system for computer-aided detection of lung mass |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110211104B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102429679A (en) * | 2011-09-09 | 2012-05-02 | 华南理工大学 | Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image |
| CN103106408A (en) * | 2013-01-25 | 2013-05-15 | 西安电子科技大学 | Stomach computer tomography (CT) image lymph node automatic auxiliary detecting system without supervision segmentation |
| CN106204600A (en) * | 2016-07-07 | 2016-12-07 | 广东技术师范学院 | Cerebral tumor image partition method based on multisequencing MR image related information |
| CN106548476A (en) * | 2016-11-25 | 2017-03-29 | 天津工业大学 | Using medical image statistics pulmonary three-dimensional feature Method On Shape |
| CN106815576A (en) * | 2017-01-20 | 2017-06-09 | 中国海洋大学 | Target tracking method based on consecutive hours sky confidence map and semi-supervised extreme learning machine |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003070102A2 (en) * | 2002-02-15 | 2003-08-28 | The Regents Of The University Of Michigan | Lung nodule detection and classification |
-
2019
- 2019-05-23 CN CN201910436100.1A patent/CN110211104B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102429679A (en) * | 2011-09-09 | 2012-05-02 | 华南理工大学 | Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image |
| CN103106408A (en) * | 2013-01-25 | 2013-05-15 | 西安电子科技大学 | Stomach computer tomography (CT) image lymph node automatic auxiliary detecting system without supervision segmentation |
| CN106204600A (en) * | 2016-07-07 | 2016-12-07 | 广东技术师范学院 | Cerebral tumor image partition method based on multisequencing MR image related information |
| CN106548476A (en) * | 2016-11-25 | 2017-03-29 | 天津工业大学 | Using medical image statistics pulmonary three-dimensional feature Method On Shape |
| CN106815576A (en) * | 2017-01-20 | 2017-06-09 | 中国海洋大学 | Target tracking method based on consecutive hours sky confidence map and semi-supervised extreme learning machine |
Non-Patent Citations (1)
| Title |
|---|
| 颅脑电阻抗成像数据采集中电极干扰的预处理方法研究;张戈;《中国优秀硕士学位论文全文数据库 (基础科学辑)》;20160215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110211104A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111325739B (en) | Method and device for detecting lung focus and training method of image detection model | |
| WO2018120942A1 (en) | System and method for automatically detecting lesions in medical image by means of multi-model fusion | |
| CN111798425B (en) | Intelligent detection method for mitotic image in gastrointestinal stromal tumor based on deep learning | |
| WO2007018755A1 (en) | Abnormality detection in medical images | |
| CN110503626B (en) | CT image modality alignment method based on space-semantic significance constraint | |
| CN104299242B (en) | Fluoroscopic visualization eye fundus image extracting method based on NGC ACM | |
| US20230005140A1 (en) | Automated detection of tumors based on image processing | |
| CN111553892A (en) | Lung nodule segmentation calculation method, device and system based on deep learning | |
| CN111340825A (en) | Method and system for generating mediastinal lymph node segmentation model | |
| Pham et al. | A comparison of texture models for automatic liver segmentation | |
| Wang et al. | Reduction of bubble-like frames using a RSS filter in wireless capsule endoscopy video | |
| CN111311626A (en) | Skull fracture automatic detection method based on CT image and electronic medium | |
| Jaffar et al. | GA and morphology based automated segmentation of lungs from Ct scan images | |
| Ratheesh et al. | Advanced algorithm for polyp detection using depth segmentation in colon endoscopy | |
| CN110211104B (en) | Image analysis method and system for computer-aided detection of lung mass | |
| Yao et al. | Computer aided lytic bone metastasis detection using regular CT images | |
| Arnold et al. | Indistinct frame detection in colonoscopy videos | |
| Dovganich et al. | Automatic quality control in lung X-ray imaging with deep learning | |
| Mansoor et al. | Near-optimal keypoint sampling for fast pathological lung segmentation | |
| CN110176009B (en) | Lung image segmentation and tracking method and system | |
| Mohammed et al. | Esophageal Cancer Detection Using Feed-Forward Neural Network | |
| CN110349662B (en) | Cross-image set outlier sample discovery method and system for filtering lung mass misdetection results | |
| Liu et al. | Recognition of cervical precancerous lesions based on probability distribution feature guidance | |
| Sindhu et al. | A novel method for automatic detection of inflammatory bowel diseases in wireless capsule endoscopy images | |
| Shaziya et al. | Comprehensive review of automatic lung segmentation techniques on pulmonary CT images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |