CN103324852A - Four-modal medical imaging diagnosis system based on feature matching - Google Patents
Four-modal medical imaging diagnosis system based on feature matching Download PDFInfo
- Publication number
- CN103324852A CN103324852A CN201310254378XA CN201310254378A CN103324852A CN 103324852 A CN103324852 A CN 103324852A CN 201310254378X A CN201310254378X A CN 201310254378XA CN 201310254378 A CN201310254378 A CN 201310254378A CN 103324852 A CN103324852 A CN 103324852A
- Authority
- CN
- China
- Prior art keywords
- vector
- module
- feature database
- pet
- feature
- 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.)
- Pending
Links
Images
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides a four-modal medical imaging diagnosis system based on feature matching. The four-modal medical imaging diagnosis system comprises CT (computerized tomography) imaging equipment, PET (positron emission tomography) imaging equipment, SPET (single photon emission tomography) imaging equipment, FMI imaging equipment, an image collecting module, a network communicating module and a terminal processor. The image collecting module is connected with the CT imaging equipment, the PET imaging equipment, the SPET imaging equipment and the FMI imaging equipment respectively, and the output end of the image collecting module is connected to the network communicating module. The image collecting module collects four-modal medical images of CT, PET, SPET and FMI, and packs four image signals into a video stream and sends to the network communicating module. The network communicating module is connected with the image collecting module and the terminal processor respectively, and is used for sending the received video stream to the terminal processor. The terminal processor diagnoses diseases through similarity detection between the medical images and a feature library. The four-modal medical imaging diagnosis system has the advantages of high accuracy and low rate of misdiagnosing and missed diagnosis, and has promising application prospect.
Description
Technical field
The present invention relates to the medical image diagnosis technical field, particularly, relate to a kind of four mode medical image diagnostic systems based on characteristic matching.
Background technology
CT, PET image are the important evidence that patient's disease is diagnosed, and owing to CT, PET inspection normally checks patient's whole body, the image data amount that therefore obtains is very large.At present, CT, the PET image finished for shooting, all be directly to carry out medical diagnosis on disease by visual inspection by the doctor, the doctor is when diagnosing, because image data amount is large, add that human eye is limited to the recognition capability of image, the various situations such as mistaken diagnosis inevitably can occur, fail to pinpoint a disease in diagnosis have stayed very large hidden danger to the accuracy of patient treatment.
Summary of the invention
For defective of the prior art, the purpose of this invention is to provide a kind of four mode medical image diagnostic systems based on characteristic matching.
According to an aspect of the present invention, a kind of four mode medical image diagnostic systems based on characteristic matching are provided, comprise: the CT vision facilities, the PET vision facilities, the SPET vision facilities, the FMI vision facilities, image capture module, network communication module and terminal handler, the image capture module input end respectively with the CT vision facilities, the PET vision facilities, the SPET vision facilities, the FMI vision facilities connects, output terminal interconnection network communication module, image capture module gathers CT, PET, SPET, FMI four mode medical images, and four tunnel picture signals are packaged into a video flowing are sent to network communication module, network communication module is connected with terminal handler with image capture module respectively, be sent to terminal handler in order to the video flowing that will receive, terminal handler further comprises:
Decoder module: in order to processing that the video streaming image signal is decoded, unpack and isolate CT, PET, SPET, FMI four mode medical image signals are sent to image display;
Image display: be connected CT, the PET, SPET, the FMI four mode medical image signals that receive in order to demonstration with decoder module;
Feature database module: the ill situation that storage is carried out manual mark and indicated the obvious case of correlated characteristic by the medical expert, and automatically extract the pathological image feature of this affected areas, set up proper vector tabulation to be matched and calculate the dependent thresholds condition and storage according to this feature;
Characteristic extracting module: be connected with decoder module, in order to CT, PET, SPET, the FMI four mode medical image signals that collect are carried out feature extraction, medical image information by PET, SPET, three mode of FMI is determined lesion region, and find out the number of plies of this lesion region CT image, this zone is carried out the extraction of feature, consistent in the tabulation of the proper vector of extraction and the feature database module;
Characteristic matching module: be connected with the feature database module with characteristic extracting module respectively, in order to choose five stack features storehouses vector foundation coupling operator the proper vector of the lesion region of extraction and the proper vector of feature database module stores mated calculating;
The similarity discrimination module: the five stack features storehouses vector according to characteristic matching module is selected finds out relevant ratio, and calculates the similarity operator;
Pathological diagnosis module: provide the case situation of similarity maximum according to threshold condition, and provide ill degree according to the eigenwert of vector.
Preferably, should also comprise based on four mode medical image diagnostic systems of characteristic matching: the feature database update module, the feature database update module is connected with the feature database module, in order to import New Characteristics pathology, upgrade the feature database vector of original feature database module stores and calculate the threshold condition that makes new advances.
Preferably, first vector is carried out the normalization operation before the characteristic matching module coupling, and the SSD(difference of two squares of compute vector and) coefficient, find out the minimum feature database vector of SSD value, and select the case of five stack features storehouses vector correspondence according to ascending order.
Preferably, the computing formula of similarity operator is: 1-SSD/N, and wherein, N is the dimension of vector, SSD is the difference of two squares and the coefficient of vector, demonstrates successively relevant case according to the similarity size.
Preferably, the normalization operation comprises: to the N dimensional feature vector of feature database module stores, calculate minimum value and the maximal value of each dimensional characteristics value, maximal value is Vector_Max (i), minimum value is Vector_Min (i), wherein i represents the i dimensional feature vector, suppose that i dimensional feature vector value is Vector (i), then the value after the normalization is Normalization (i)=(Vector (i)-Vector_Min (i))/(Vector_Max (i)-Vector_Min (i)); Then the vector value scope after the normalization is 0～1.
Preferably, the feature database vector comprises: area, length, length breadth ratio, circle rate, gray average, texture co-occurrence matrix and texture second moment.
Preferably, five stack features storehouse vectors are according to select 5 vectors in the descending feature database vector of storing from feature database.
Compared with prior art, the present invention has following beneficial effect: the present invention is according to CT image, PET image, SPET image and the foundation of the FMI image diagnostic system based on four mode medical image automatic diagnosis diseases, by being arranged in the medical image of the network system collection patient on the image acquisition equipment, detect to diagnose the illness by the similarity to medical image and feature database, take full advantage of many defectives that computer system has remedied Artificial Diagnosis.Possess accuracy high, mistaken diagnosis, the advantage that rate of missed diagnosis is little have broad application prospects.
Description of drawings
By reading the detailed description of non-limiting example being done with reference to the following drawings, it is more obvious that other features, objects and advantages of the present invention will become:
Fig. 1 is the structure principle chart that the present invention is based on four mode medical image diagnostic systems of characteristic matching.
Embodiment
The present invention is described in detail below in conjunction with specific embodiment.Following examples will help those skilled in the art further to understand the present invention, but not limit in any form the present invention.Should be pointed out that to those skilled in the art, without departing from the inventive concept of the premise, can also make some distortion and improvement.These all belong to protection scope of the present invention.
See also Fig. 1, a kind of four mode medical image diagnostic systems based on characteristic matching, comprise: the CT vision facilities, the PET vision facilities, the SPET vision facilities, the FMI vision facilities, image capture module, network communication module and terminal handler, the image capture module input end respectively with the CT vision facilities, the PET vision facilities, the SPET vision facilities, the FMI vision facilities connects, output terminal interconnection network communication module, image capture module gathers CT, PET, SPET, FMI four mode medical images, and four tunnel picture signals are packaged into a video flowing are sent to network communication module, network communication module is connected with terminal handler with image capture module respectively, be sent to terminal handler in order to the video flowing that will receive, terminal handler further comprises:
Decoder module: in order to processing that the video streaming image signal is decoded, unpack and isolate CT, PET, SPET, FMI four mode medical image signals are sent to image display;
Image display: be connected CT, the PET, SPET, the FMI four mode medical image signals that receive in order to demonstration with decoder module;
Feature database module: the ill situation that storage is carried out manual mark and indicated the obvious case of correlated characteristic by the medical expert, and automatically extract the pathological image feature of this affected areas, set up proper vector tabulation to be matched and calculate the dependent thresholds condition and storage according to this feature;
Characteristic extracting module: be connected with decoder module, in order to CT, PET, SPET, the FMI four mode medical image signals that collect are carried out feature extraction, image information by PET, SPET, three mode of FMI is determined lesion region, and find out the number of plies of this lesion region CT image, this zone is carried out the extraction of feature, consistent in the tabulation of the proper vector of extraction and the feature database module;
Characteristic matching module: be connected with the feature database module with characteristic extracting module respectively, in order to choose five stack features storehouses vector foundation coupling operator the proper vector of the lesion region of extraction and the proper vector of feature database module stores mated calculating;
The similarity discrimination module: the five stack features storehouses vector according to characteristic matching module is selected finds out relevant ratio, and calculates the similarity operator;
Pathological diagnosis module: provide the case situation of similarity maximum according to threshold condition, and provide ill degree according to the eigenwert of vector.
Further, should also comprise based on four mode medical image diagnostic systems of characteristic matching: the feature database update module, the feature database update module is connected with the feature database module, in order to import New Characteristics pathology, upgrade the feature database vector of original feature database module stores and calculate the threshold condition that makes new advances.
Further, first vector is carried out the normalization operation before the characteristic matching module coupling, and the SSD(difference of two squares of compute vector and) coefficient, find out the minimum feature database vector of SSD value, and select the case of five stack features storehouses vector correspondence according to ascending order.
Further, the computing formula of similarity operator is: 1-SSD/N, and wherein, N is the dimension of vector, SSD is the difference of two squares and the coefficient of vector, demonstrates successively relevant case according to the similarity size.
Further, the normalization operation comprises: to the N dimensional feature vector of feature database module stores, calculate minimum value and the maximal value of each dimensional characteristics value, maximal value is Vector_Max (i), minimum value is Vector_Min (i), wherein i represents the i dimensional feature vector, suppose that i dimensional feature vector value is Vector (i), then the value after the normalization is Normalization (i)=(Vector (i)-Vector_Min (i))/(Vector_Max (i)-Vector_Min (i)); Then the vector value scope after the normalization is 0～1.
Further, the feature database vector comprises: area, length, length breadth ratio, circle rate, gray average, texture co-occurrence matrix and texture second moment.
Further, five stack features storehouse vectors are according to select 5 vectors in the descending feature database vector of storing from feature database.
Particularly, the course of work of the present invention is: gather CT, PET, SPET, FMI four mode medical images by image capture module first, image acquisition integrated circuit board by image capture module is packaged into a video flowing to four tunnel picture signals, is transferred on the terminal handler by network communication module.Operation four mode pathological diagnosis programs unpack the picture signal of video flowing on the terminal handler, and the signal of isolating four mode shows.The feature database module is to set up the matching vector that initial characteristics is analyzed, by the medical expert the obvious case of correlated characteristic is carried out the craft mark and indicated ill situation, the operation characteristic library module then extracts the pathological image feature of this affected areas automatically, set up proper vector tabulation to be matched and calculate the dependent thresholds condition according to this feature, put into feature database.The feature database update module is user when importing New Characteristics pathology, can upgrade original feature database vector and calculate the threshold condition that makes new advances, and guarantees that like this feature database can be constantly perfect.Characteristic extracting module is that the four mode picture signals that the user collects are carried out the extraction of feature, image information by PET, SPET, three mode of FMI is determined lesion region, and find out the number of plies of this lesion region CT image, this zone is carried out the extraction of feature, consistent in the tabulation of the proper vector of extraction and the feature database.Characteristic matching module is by the coupling operator of setting up the proper vector of the lesion region of extraction and the vector of feature database to be mated calculating, vector need to carry out normalized operation before the coupling, and the SSD coefficient of compute vector (difference of two squares and), find out the minimum feature database vector of SSD value, and carry out selecting case corresponding to five stack features storehouses vector according to ascending order.The similarity discrimination module finds out relevant ratio, and calculates the similarity operator according to the five stack features storehouses vector of selecting previously, and computing formula is 1-SSD/N (N is the dimension of vector), demonstrates successively relevant case according to the similarity size.The pathological diagnosis module provides the case situation of similarity maximum according to threshold condition, and according to the eigenwert of vector, provides ill degree, is judged to be normal if similarity is too small.
The present invention is according to CT image, PET image, SPET image and the foundation of the FMI image diagnostic system based on four mode medical image automatic diagnosis diseases, by being arranged in the medical image of the network system collection patient on the image acquisition equipment, detect to diagnose the illness by the similarity to medical image and feature database, take full advantage of many defectives that computing machine has remedied Artificial Diagnosis.Possess accuracy high, the advantage such as mistaken diagnosis, rate of missed diagnosis are little has broad application prospects.
Above specific embodiments of the invention are described.It will be appreciated that, the present invention is not limited to above-mentioned specific implementations, and those skilled in the art can make various distortion or modification within the scope of the claims, and this does not affect flesh and blood of the present invention.
Claims (7)
1. four mode medical image diagnostic systems based on characteristic matching, it is characterized in that, comprise: the CT vision facilities, the PET vision facilities, the SPET vision facilities, the FMI vision facilities, image capture module, network communication module and terminal handler, described image capture module input end respectively with described CT vision facilities, the PET vision facilities, the SPET vision facilities, the FMI vision facilities connects, output terminal connects described network communication module, described image capture module gathers CT, PET, SPET, FMI four mode medical images, and with CT, PET, SPET, four tunnel picture signals that FMI four mode medical images are corresponding are packaged into a video flowing and are sent to described network communication module, described network communication module is connected with terminal handler with described image capture module respectively, be sent to described terminal handler in order to the video flowing that will receive, described terminal handler further comprises:
Decoder module: in order to processing that the video streaming image signal is decoded, unpack and isolate CT, PET, SPET, FMI four mode medical image signals are sent to image display;
Image display: be connected CT, the PET, SPET, the FMI four mode medical image signals that receive in order to demonstration with described decoder module;
Feature database module: the ill situation that storage is carried out manual mark and indicated the obvious case of correlated characteristic by the medical expert, and automatically extract the pathological image feature of this affected areas, set up proper vector tabulation to be matched and calculate the dependent thresholds condition and storage according to this feature;
Characteristic extracting module: be connected with described decoder module, in order to CT, PET, SPET, the FMI four mode medical image signals that collect are carried out feature extraction, image information by PET, SPET, three mode of FMI is determined lesion region, and find out the number of plies of this lesion region CT image, this zone is carried out the extraction of feature, consistent in the tabulation of the proper vector of extraction and the feature database module;
Characteristic matching module: be connected with the feature database module with described characteristic extracting module respectively, in order to choose five stack features storehouses vector foundation coupling operator the proper vector of the lesion region of extraction and the proper vector of feature database module stores mated calculating;
The similarity discrimination module: the five stack features storehouses vector according to characteristic matching module is selected finds out relevant ratio, and calculates the similarity operator;
Pathological diagnosis module: provide the case situation of similarity maximum according to threshold condition, and provide ill degree according to the eigenwert of vector.
2. four mode medical image diagnostic systems based on characteristic matching according to claim 1, it is characterized in that, also comprise: the feature database update module, described feature database update module is connected with described feature database module, in order to import New Characteristics pathology, upgrade the feature database vector of original feature database module stores and calculate the threshold condition that makes new advances.
3. four mode medical image diagnostic systems based on characteristic matching according to claim 1, it is characterized in that, first vector is carried out the normalization operation before the described characteristic matching module coupling, and the SSD coefficient of compute vector, find out the minimum feature database vector of SSD value, and select case corresponding to five stack features storehouses vector according to ascending order.
4. four mode medical image diagnostic systems based on characteristic matching according to claim 1, it is characterized in that, the computing formula of described similarity operator is: 1-SSD/N, wherein, N is the dimension of vector, SSD is the difference of two squares and the coefficient of vector, demonstrates successively relevant case according to the similarity size.
5. four mode medical image diagnostic systems based on characteristic matching according to claim 3, it is characterized in that, described normalization operation comprises: to the N dimensional feature vector of feature database module stores, calculate minimum value and the maximal value of each dimensional characteristics value, maximal value is Vector_Max (i), minimum value is Vector_Min (i), wherein i represents the i dimensional feature vector, suppose that i dimensional feature vector value is Vector (i), then the value after the normalization is Normalization (i)=(Vector (i)-Vector_Min (i))/(Vector_Max (i)-Vector_Min (i)); Then the vector value scope after the normalization is 0～1.
6. four mode medical image diagnostic systems based on characteristic matching according to claim 1 is characterized in that, described feature database vector comprises: area, length, length breadth ratio, circle rate, gray average, texture co-occurrence matrix and texture second moment.
7. four mode medical image diagnostic systems based on characteristic matching according to claim 6 is characterized in that, described five stack features storehouse vectors are according to select 5 vectors in the descending feature database vector of storing from feature database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310254378XA CN103324852A (en) | 2013-06-25 | 2013-06-25 | Four-modal medical imaging diagnosis system based on feature matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310254378XA CN103324852A (en) | 2013-06-25 | 2013-06-25 | Four-modal medical imaging diagnosis system based on feature matching |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103324852A true CN103324852A (en) | 2013-09-25 |
Family
ID=49193591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310254378XA Pending CN103324852A (en) | 2013-06-25 | 2013-06-25 | Four-modal medical imaging diagnosis system based on feature matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103324852A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318500A (en) * | 2014-10-29 | 2015-01-28 | 无锡中盛医疗设备有限公司 | Medical image workstation |
| TWI511072B (en) * | 2014-02-10 | 2015-12-01 | Ind Tech Res Inst | Pathology data processing apparatus and methods |
| CN105118068A (en) * | 2015-09-29 | 2015-12-02 | 常熟理工学院 | Medical image automatic annotation method under small sample condition |
| CN108288499A (en) * | 2018-01-22 | 2018-07-17 | 沈阳东软医疗***有限公司 | A kind of automatic point is examined method and device |
| CN110348477A (en) * | 2019-06-04 | 2019-10-18 | 上海联影智能医疗科技有限公司 | Medical image processing method, storage medium and computer equipment |
| CN111640480A (en) * | 2020-05-21 | 2020-09-08 | 上海联影智能医疗科技有限公司 | Medical report generation method, computer device, and storage medium |
| CN111930992A (en) * | 2020-08-14 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Neural network training method and device and electronic equipment |
| CN113314202A (en) * | 2020-02-26 | 2021-08-27 | 张瑞明 | System for processing medical images based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201200423Y (en) * | 2008-04-30 | 2009-03-04 | 深圳市蓝韵实业有限公司 | Output equipment of medical ultrasonic digital video image |
| CN101669815A (en) * | 2009-09-22 | 2010-03-17 | 广东威创视讯科技股份有限公司 | Remote diagnosis system of medical section and network transmission method thereof |
| US20100272338A1 (en) * | 2007-12-21 | 2010-10-28 | Koninklijke Philips Electronics N.V. | Method and system for cross-modality case-based computer-aided diagnosis |
| CN102164273A (en) * | 2011-04-20 | 2011-08-24 | 上海交通大学 | Operating room medical information reconstruction and interaction system |
-
2013
- 2013-06-25 CN CN201310254378XA patent/CN103324852A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100272338A1 (en) * | 2007-12-21 | 2010-10-28 | Koninklijke Philips Electronics N.V. | Method and system for cross-modality case-based computer-aided diagnosis |
| CN201200423Y (en) * | 2008-04-30 | 2009-03-04 | 深圳市蓝韵实业有限公司 | Output equipment of medical ultrasonic digital video image |
| CN101669815A (en) * | 2009-09-22 | 2010-03-17 | 广东威创视讯科技股份有限公司 | Remote diagnosis system of medical section and network transmission method thereof |
| CN102164273A (en) * | 2011-04-20 | 2011-08-24 | 上海交通大学 | Operating room medical information reconstruction and interaction system |
Non-Patent Citations (2)
| Title |
|---|
| 卢小泉等: "《化学计量学研究方法》", 30 April 2013, 科学出版社 * |
| 黎维娟: ""多模态影像脑部疾病检索研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI511072B (en) * | 2014-02-10 | 2015-12-01 | Ind Tech Res Inst | Pathology data processing apparatus and methods |
| CN104318500A (en) * | 2014-10-29 | 2015-01-28 | 无锡中盛医疗设备有限公司 | Medical image workstation |
| CN105118068A (en) * | 2015-09-29 | 2015-12-02 | 常熟理工学院 | Medical image automatic annotation method under small sample condition |
| CN105118068B (en) * | 2015-09-29 | 2017-12-05 | 常熟理工学院 | Medical image automatic marking method under a kind of condition of small sample |
| CN108288499B (en) * | 2018-01-22 | 2021-08-06 | 东软医疗***股份有限公司 | Automatic triage method and device |
| CN108288499A (en) * | 2018-01-22 | 2018-07-17 | 沈阳东软医疗***有限公司 | A kind of automatic point is examined method and device |
| CN110348477A (en) * | 2019-06-04 | 2019-10-18 | 上海联影智能医疗科技有限公司 | Medical image processing method, storage medium and computer equipment |
| CN110348477B (en) * | 2019-06-04 | 2021-10-22 | 上海联影智能医疗科技有限公司 | Medical image processing method, storage medium, and computer device |
| CN113314202A (en) * | 2020-02-26 | 2021-08-27 | 张瑞明 | System for processing medical images based on big data |
| CN111640480A (en) * | 2020-05-21 | 2020-09-08 | 上海联影智能医疗科技有限公司 | Medical report generation method, computer device, and storage medium |
| CN111640480B (en) * | 2020-05-21 | 2023-09-26 | 上海联影智能医疗科技有限公司 | Medical report generation method, computer device, and storage medium |
| CN111930992A (en) * | 2020-08-14 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Neural network training method and device and electronic equipment |
| CN111930992B (en) * | 2020-08-14 | 2022-10-28 | 腾讯科技（深圳）有限公司 | Neural network training method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103324852A (en) | Four-modal medical imaging diagnosis system based on feature matching | |
| WO2020207377A1 (en) | Method, device, and system for image recognition model training and image recognition | |
| KR102237441B1 (en) | Method and apparatus for reading lesion from capsule endoscopic image using neural network | |
| US20220051405A1 (en) | Image processing method and apparatus, server, medical image processing device and storage medium | |
| EP3021753B1 (en) | Systems and methods for determining hepatic function from liver scans | |
| US20210174505A1 (en) | Method and system for imaging and analysis of anatomical features | |
| CN103324853A (en) | Similarity calculation system and method based on medical image features | |
| US20220058821A1 (en) | Medical image processing method, apparatus, and device, medium, and endoscope | |
| CN109460717B (en) | Digestive tract confocal laser microscopy endoscope lesion image identification method and device | |
| WO2019098415A1 (en) | Method for determining whether subject has developed cervical cancer, and device using same | |
| CN110287862A (en) | Anti- detection method of taking on the sly based on deep learning | |
| Girgis et al. | An intelligent system to detect Crohn's disease inflammation in Wireless Capsule Endoscopy videos | |
| Chakraborty et al. | Chronic wound characterization using bayesian classifier under telemedicine framework | |
| US9483705B2 (en) | Image processing device, image processing method, and image processing program | |
| Jebarani et al. | Assessment of Crohn's disease lesions in Wireless Capsule Endoscopy images using SVM based classification | |
| Lucassen et al. | Deep learning for detection and localization of B-lines in lung ultrasound | |
| Amiri et al. | A computer-aided method to detect bleeding frames in capsule endoscopy images | |
| Vasconcelos et al. | A new risk assessment methodology for dermoscopic skin lesion images | |
| CN115050456A (en) | Artificial intelligence medical image automatic diagnosis system and method | |
| Wang et al. | Computer aided endoscope diagnosis via weakly labeled data mining | |
| WO2022041710A1 (en) | Image-based motion detection method | |
| Jia | Polyps auto-detection in wireless capsule endoscopy images using improved method based on image segmentation | |
| Figueiredo et al. | An automatic blood detection algorithm for wireless capsule endoscopy images | |
| Zhang et al. | Detection and retrieval of cysts in joint ultrasound b-mode and elasticity breast images | |
| CN103345576B (en) | Case storehouses based on four mode medical images diagnostic system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130925 |
|
| RJ01 | Rejection of invention patent application after publication |