CN104657598A - Method for calculating fractal dimension of microvessels of tissue - Google Patents
Method for calculating fractal dimension of microvessels of tissue Download PDFInfo
- Publication number
- CN104657598A CN104657598A CN201510047378.1A CN201510047378A CN104657598A CN 104657598 A CN104657598 A CN 104657598A CN 201510047378 A CN201510047378 A CN 201510047378A CN 104657598 A CN104657598 A CN 104657598A
- Authority
- CN
- China
- Prior art keywords
- image
- tissue
- fractal dimension
- gained
- mvfd
- 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
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention belongs to the field of medical digital image analysis and particularly relates to a method for calculating fractal dimension of microvessels of tissue. The method comprises the following steps: carrying out conventional slicing on the tissue to be tested, so as to obtain a tissue slice; carrying out immunohistochemical staining blood vessel marking on the tissue slice so as to obtain a stained slice, and then, photographing a two-dimensional structured image of the stained slice by adopting image acquisition equipment, so as to obtain a digital slice; extracting a microvessel-rich hot-spot area from the digital slice, and naming the microvessel-rich hot-spot area as an image A; extracting a stained positive target area from the image A based on a threshold method in an HSB (Hue-Saturation-Brightness) color space so as to obtain an image A1, and then, converting the image A1 into a binary system, so as to obtain an image B; carrying out image skeletonizing on the image B, so as to obtain an image C; calculating the fractal dimension mvFD of the image C by adopting a box-counting method. The method is simple in operation, simple and convenient in calculation and relatively small in error, and the obtained fractal dimension can be used for completely and effectively reflecting the form complexity and number of the microvessels of the tissue to be tested.
Description
Technical field
The invention belongs to medical digital images analysis field, be specifically related to a kind of computing method of tissue microvascular fractal dimension.
Background technology
Blood vessel is biological hemophoric pipeline.Human normal tissue or pathological tissues are all containing blood vessel, and especially some pathology (as malignant tumour) tissue is containing enriching blood vessel, and forms blood vessel network system.Histopathologic slide is the main carriers carrying out pathological diagnosis, and wherein, the feature such as form, quantity of tissue blood vessel can as the foundation of some disease (as malignant tumour) auxiliary diagnosis.The method of current assessment tissue blood vessel feature comprises vascular morphology description, vessel density calculating, blood vessel-specific molecular marked compound immunohistochemical staining etc.But, still lack the index of rational judgment vascular morphology complexity at present.
Fractal dimension is an index in fractal geometry, is widely used in fields such as materialogy, architecture, digital image analysises.In biomedicine, fractal dimension is used to the complicacy evaluating morphological feature, comprises karyomorphism, chromatin Structure and tumor tissues edge roughness degree etc.At present, a kind of computing method of tissue microvascular fractal dimension are not yet set up.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of computing method of tissue microvascular fractal dimension, the method is simple to operate, it is easy to calculate, error is less, and gained fractal dimension complete, effective reflection can be detected complicacy and the quantity of tissue microvascular form.
For achieving the above object, technical scheme of the present invention is:
Computing method for tissue microvascular fractal dimension, comprise the step of carrying out as follows:
(1) tissue to be checked is carried out conventional film-making and obtain histotomy;
(2) histotomy of step (1) gained is carried out immunohistochemical staining label vascular and obtain stained, then adopt the two-dimensional structure image of image capture device picked-up stained to obtain digital slices;
(3) intercept from the digital slices of step (2) gained containing abundant " hot zone " of blood capillary, called after image A;
(4) in HSB color space based on the stained positive target area of the image A of threshold method extraction step (3) gained, obtain image A
1, then by image A
1be converted into scale-of-two, obtain image B;
(5) process of image Skeleton is carried out to the image B of step (4) gained, obtain image C;
(6) box-like counting method is adopted to calculate the fractal dimension mvFD of image C in described step (5), be specially: with pixel value 4,8,16,32,64,128,256 for square box length of side ε, calculate all target areas and the minimum non-overlapped square box number N (ε) of binary value required for the region of 1 in overlay image C respectively; With log ε for horizontal ordinate, log N (ε) is ordinate, makes scatter diagram, does linear regression with least square method, obtain regression equation: log N (ε)=alog ε+b, according to this equation, namely the opposite number of a is considered to mvFD.
Further, the computing method of described a kind of tissue microvascular fractal dimension, in described step (2), described immunohistochemical staining is AntiCD3 McAb 4 immunohistochemical staining.
Further, the computing method of described a kind of tissue microvascular fractal dimension, described AntiCD3 McAb 4 immunohistochemical staining adopts DAB colour developing.
Further, the computing method of described a kind of tissue microvascular fractal dimension, in described step (2), described image capture device is section panoramic scanning instrument.
Further, the computing method of described a kind of tissue microvascular fractal dimension, in described step (3), intercept 3-5 and contain blood capillary the abundantest " hot zone ", called after image A from described digital slices;
Further, the computing method of described a kind of tissue microvascular fractal dimension, in described step (3), the pixel of described image A is not less than 1920 × 1080.
Further, the computing method of described a kind of tissue microvascular fractal dimension, in described step (4), the parameter of described threshold method setting is: H:0-90 and 215-255, S:25-255 or S:38-255, B:0-255.
The computing method of a kind of tissue microvascular fractal dimension of the present invention, the method is simple to operate, it is easy to calculate, error is less, and blood vessel fractal dimension complete, effective reflection can be detected the complicacy of tissue microvascular form, quantity and distribution.
Glioma is one of modal tumour of central nervous system.Glioblastoma is the glioma (WHO IV level) that grade malignancy is the highest, accounts for 50% of all gliomas, treatment difficulty, poor prognosis and recurrence rate is high.Clinically mainly based on pathological diagnosis, according to comprising the features such as oncocyte atypia, necrosis and blood vessel hyperplasia, wherein, blood vessel hyperplasia most characteristic, show as blood vessel and there is Various Complex form, namely present " special-shaped blood vessel ", it distributes and has larger heterogeneity in same knurl body, between different knurl body.The complicacy of vascular morphology and the heterogeneity of distribution are diagnosed significant for auxiliary glioblastoma.The index of existing reflection glioma vascular morphology and distribution character comprises qualitative index (special-shaped blood vessel being divided into blood vessel bunch sample, glomerulus sample and garland sample etc.) and quantitative target as microvessel density and blood vessel diameter, point number etc.But qualitative index statistics subjectivity is comparatively large, lacks unified standard; Microvessel density only can reflect blood vessel number, and due to its counting error of complicacy of special-shaped vascular morphology larger; Blood vessel diameter and a point number statistics easily cause Select Error.Therefore, need one can reflect glioblastoma Microvascular architecture complicacy and quantity and calculate easy, that error is less New Set, blood capillary fractal dimension is expected to meet above-mentioned requirements.
In view of this, another object of the present invention is to the computing method that a kind of glioma cells in tissue blood capillary fractal dimension is provided, comprise the step of carrying out as follows:
(1) tissue to be checked is carried out histotomy of cutting into slices to obtain;
(2) histotomy of step (1) gained is carried out AntiCD3 McAb 4 immunohistochemical staining label vascular and obtain stained, then use the scanning of section panoramic scanning instrument to obtain digital slices;
(3) from the digital slices of step (2) gained, intercept 3-5 contain blood capillary the abundantest " hot zone ", image pixel is 1920 × 1080, called after image A;
(4) use image analysis software to extract immunohistochemical staining Positive Objects region based on threshold method in HSB color space to the image A of step (3) gained, obtain image A
1, the parameter set by described threshold method is: H:0-90 and 215-255, S:25-255, B:0-255; Then use described image analysis software by image A
1be converted into scale-of-two, obtain image B;
(5) use the image analysis software described in step (4) to carry out the process of image Skeleton to the image B of step (4) gained, obtain image C;
(6) box-like counting method is adopted to calculate the fractal dimension mvFD of image C in described step (5), be specially: with pixel value 4,8,16,32,64,128,256 for square box length of side ε, calculate all target areas and the minimum non-overlapped square box number N (ε) of binary value required for the region of 1 in overlay image C respectively; With log ε for horizontal ordinate, log N (ε) is ordinate, makes scatter diagram, does linear regression with least square method, obtain regression equation: log N (ε)=alog ε+b, according to this equation, namely the opposite number of a is considered to mvFD.
The computing method of a kind of glioma cells in tissue blood capillary fractal dimension of the present invention, the method is simple to operate, it is easy to calculate, error is less, and samples of human glioma blood capillary fractal dimension can complete, effective reflection glioblastoma blood capillary complexity.
Accompanying drawing explanation
The process flow diagram of the computing method of Fig. 1 a kind of tissue microvascular fractal dimension of the present invention.
Fig. 2 glioma different blood vessel form blood capillary fractal dimension compares (A: capillary sample; B: blood vessel bunch sample; C: glomerulus sample; D: garland sample; E:A-D tetra-kinds of vascular morphology mvFD compare.**,P<0.01)。
Fig. 3 different stage glioma blood capillary fractal dimension compares (I, II: Low grade glioma; III, IV: High Grade Gliomas.*,P<0.05；**,P<0.01)。
Fig. 4 is based on the glioblastoma patient Kaplan-Meier survivorship curve (A: Overall survival of mvFD expression difference; B: Progression free survival phase).
Fig. 5 chemotherapy and non-chemotherapy glioblastoma patient contrast (A: patients undergoing chemotherapy group based on the Kaplan-Meier survivorship curve of mvFD expression difference; B: non-patients undergoing chemotherapy group).
Embodiment
Further describe the present invention below in conjunction with specific embodiment, advantage and disadvantage of the present invention will be more clear along with description.But these embodiments are only exemplary, do not form any restriction to scope of the present invention.It will be understood by those skilled in the art that and can modify to the details of technical solution of the present invention and form or replace down without departing from the spirit and scope of the present invention, but these amendments and replacement all fall within the scope of protection of the present invention.
In following examples, for glioblastoma sample (from Southwest Hospital, Chongqing City and Tiantan Hospital of Beijing), the computing method of concrete elaboration tissue microvascular fractal dimension of the present invention, wherein carry out Treatment Analysis with Image J 1.46s image analysis software.
The computing method of embodiment 1 samples of human glioma blood capillary fractal dimension
1, the calculating of samples of human glioma blood capillary fractal dimension
Carry out the calculating of samples of human glioma blood capillary fractal dimension according to the process flow diagram shown in Fig. 1, concrete steps are as follows:
(1) adopt microtome to carry out conventional film-making in tissue to be checked and obtain histotomy;
(2) histotomy of step (1) gained is carried out AntiCD3 McAb 4 immunohistochemical staining label vascular (adopting DAB development process) and obtain stained, then use the scanning of section panoramic scanning instrument to obtain digital slices;
(3) from the digital slices of step (2) gained, intercept 3-5 contain blood capillary the abundantest " hot zone ", image pixel is 1920 × 1080, called after image A;
(4) image analysis software Image J 1.46s is used to the image A of step (3) gained, in HSB (Hue-Saturation-Brightness) color space, extract immunohistochemical staining Positive Objects region based on threshold method, obtain image A
1, the parameter set by described threshold method is: H:0-90 and 215-255, S:25-255, B:0-255; Then in image analysis software Image J 1.46s, according to the operation of " Process "-" Binary "-" Make Binary ", by image A
1be converted into scale-of-two, obtain image B;
(5) the image Skeleton function in use Image J 1.46s software, to the image B process of step (4) gained, is operating as " Process "-" Binary "-" Skeletonize ", obtains binary picture C;
(6) box-like counting method (box-counting method) is adopted to calculate the fractal dimension mvFD of image C in described step (5), be specially: with pixel value 4,8,16,32,64,128,256 for square box length of side ε, calculate all target areas and the minimum non-overlapped square box number N (ε) of binary value required for the region of 1 in overlay image C respectively; With log ε for horizontal ordinate, log N (ε) is ordinate, makes scatter diagram, does linear regression with least square method, obtain regression equation: logN (ε)=alog ε+b, according to this equation, namely the opposite number of a is considered to mvFD.
2, glioma different blood vessel form blood capillary fractal dimension compares
Different blood vessel form (capillary sample, blood vessel bunch sample, glomerulus sample and garland sample) blood capillary fractal dimension is compared, result as shown in Figure 2, blood capillary fractal dimension (mvFD) reflects pathological section tissue microvascular complexity, for glioma, vascular morphology is more complicated, and mvFD is larger.
3, different stage glioma blood capillary fractal dimension compares
Glioma pathological is I grade (astrocytoma), II grade (astroblastoma), III ~ IV grade (multiform glue blastoma).I ~ II grade of astrocytoma is low potential malignancy, and onset is slow, and tumour mostly is solid or cystic in the performance of CT and MR, obscure boundary, and tumour solid portion or cystic tubercle all can be strengthened.Clinical manifestation is different from lesions position there is corresponding symptom progressively, and finally occurs the symptom of intracranial hypertension.The multiform glue blastoma onset of III ~ IV grade is quick, is the tumour that grade of malignancy is the highest, is grown on cerebral hemisphere more, and because tumor growth is rapid, tumor center can have many places downright bad and hemorrhage, CT and MR all obviously strengthens, and can accompany the oedema of large stretch of brain tissue around.
Different stage glioma blood capillary fractal dimension is carried out statistical study, and result as shown in Figure 3, shows that High Grade Gliomas mvFD value is higher than Low grade glioma mvFD value.
The application of embodiment 2 samples of human glioma blood capillary fractal dimension
(56 examples are from Southwest Hospital, Chongqing City to collect the routine glioblastoma patient of 2006-2012 83,27 examples are from Beijing Tiantan Hospital) histopathologic slide and Clinical Follow-up data, statistical study also calculates mvFD value and carries out survival analysis, as shown in Figure 4 and Figure 5, mvFD>1.06 glioblastoma patients overall survival's phase (Fig. 4 A) and Progression free survival phase (Fig. 4 B) are all significantly greater than mvFD≤1.06 patient to result.In the glioblastoma patient accepting chemotherapy, mvFD>1.06 patient's Progression free survival phase is significantly greater than mvFD≤1.06 patient, and prompting mvFD>1.06 can be used as the standard (Fig. 5 A) that glioblastoma Chemotherapy in Patients reacts good.In the patient not accepting chemotherapy, mvFD height survival of patients phase indifference (Fig. 5 B), further illustrates the correlativity of mvFD and chemotherapy side effect.Generally speaking, for glioblastoma, mvFD≤1.06, patient's prognosis mala, chemotherapy side effect is poor, mvFD>1.06, patient prognosis bona, and chemotherapy side effect is good.
Therefore, glioblastoma blood capillary fractal dimension can reflect glioblastoma Microvascular architecture complicacy, and it has prognosis and the chemotherapy side effect effect of prediction glioblastoma patient.
What finally illustrate is, above embodiment is only in order to illustrate technical scheme of the present invention and unrestricted, although with reference to preferred embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that, can modify to technical scheme of the present invention or equivalent replacement, and not departing from aim and the scope of technical solution of the present invention, it all should be encompassed in the middle of right of the present invention.
Claims (8)
1. computing method for tissue microvascular fractal dimension, is characterized in that, comprise the step of carrying out as follows:
(1) tissue to be checked is carried out conventional film-making and obtain histotomy;
(2) histotomy of step (1) gained is carried out immunohistochemical staining label vascular and obtain stained, then adopt the two-dimensional structure image of image capture device picked-up stained to obtain digital slices;
(3) intercept from the digital slices of step (2) gained containing abundant " hot zone " of blood capillary, called after image A;
(4) in HSB color space based on the stained positive target area of the image A of threshold method extraction step (3) gained, obtain image A
1, then by image A
1be converted into scale-of-two, obtain image B;
(5) process of image Skeleton is carried out to the image B of step (4) gained, obtain image C;
(6) box-like counting method is adopted to calculate the fractal dimension mvFD of image C in described step (5), be specially: with pixel value 4,8,16,32,64,128,256 for square box length of side ε, calculate all target areas and the minimum non-overlapped square box number N (ε) of binary value required for the region of 1 in overlay image C respectively; With log ε for horizontal ordinate, log N (ε) is ordinate, makes scatter diagram, does linear regression with least square method, obtain regression equation: log N (ε)=alog ε+b, according to this equation, namely the opposite number of a is considered to mvFD.
2. the computing method of a kind of tissue microvascular fractal dimension according to claim 1, is characterized in that, in described step (2), described immunohistochemical staining is AntiCD3 McAb 4 immunohistochemical staining.
3. the computing method of a kind of tissue microvascular fractal dimension according to claim 2, is characterized in that, described AntiCD3 McAb 4 immunohistochemical staining adopts DAB colour developing.
4. the computing method of a kind of tissue microvascular fractal dimension according to claim 1, is characterized in that, in described step (2), described image capture device is section panoramic scanning instrument.
5. the computing method of a kind of tissue microvascular fractal dimension according to claim 1, is characterized in that, in described step (3), intercept 3-5 and contain blood capillary the abundantest " hot zone ", called after image A from described digital slices.
6. the computing method of a kind of tissue microvascular fractal dimension according to claim 1 or 5, it is characterized in that, in described step (3), the pixel of described image A is not less than 1920 × 1080.
7. the computing method of a kind of tissue microvascular fractal dimension according to claim 1, it is characterized in that, in described step (4), the parameter of described threshold method setting is: H:0-90 and 215-255, S:25-255 or S:38-255, B:0-255.
8. computing method for glioma cells in tissue blood capillary fractal dimension, is characterized in that, comprise the step of carrying out as follows:
(1) tissue to be checked is carried out conventional film-making and obtain histotomy;
(2) histotomy of step (1) gained is carried out AntiCD3 McAb 4 immunohistochemical staining label vascular and obtain stained, then use the scanning of section panoramic scanning instrument to obtain digital slices;
(3) from the digital slices of step (2) gained, intercept 3-5 contain blood capillary the abundantest " hot zone ", image pixel is 1920 × 1080, called after image A;
(4) use image analysis software to extract immunohistochemical staining Positive Objects region based on threshold method in HSB color space to the image A of step (3) gained, obtain image A
1, the parameter set by described threshold method is: H:0-90 and 215-255, S:25-255, B:0-255; Then use described image analysis software by image A
1be converted into scale-of-two, obtain image B;
(5) use the image analysis software described in step (4) to carry out the process of image Skeleton to the image B of step (4) gained, obtain image C;
(6) box-like counting method is adopted to calculate the fractal dimension mvFD of image C in described step (5), be specially: with pixel value 4,8,16,32,64,128,256 for square box length of side ε, calculate all target areas and the minimum non-overlapped square box number N (ε) of binary value required for the region of 1 in overlay image C respectively; With log ε for horizontal ordinate, log N (ε) is ordinate, makes scatter diagram, does linear regression with least square method, obtain regression equation: log N (ε)=alog ε+b, according to this equation, namely the opposite number of a is considered to mvFD.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510047378.1A CN104657598A (en) | 2015-01-29 | 2015-01-29 | Method for calculating fractal dimension of microvessels of tissue |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510047378.1A CN104657598A (en) | 2015-01-29 | 2015-01-29 | Method for calculating fractal dimension of microvessels of tissue |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104657598A true CN104657598A (en) | 2015-05-27 |
Family
ID=53248712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510047378.1A Pending CN104657598A (en) | 2015-01-29 | 2015-01-29 | Method for calculating fractal dimension of microvessels of tissue |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104657598A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908920A (en) * | 2017-11-01 | 2018-04-13 | 东南大学 | The characterizing method of oxygen carrier reactivity in burning chemistry chains |
| CN108062981A (en) * | 2018-01-15 | 2018-05-22 | 深港产学研基地 | A kind of modeling method in the kind of the asymmetric tree of point of shape blood vessel with inter-species scale |
| CN109493949A (en) * | 2018-10-26 | 2019-03-19 | 浙江大学 | A kind of the determination method, apparatus and computer storage medium of left auricle of heart complexity |
| CN111798432A (en) * | 2020-07-07 | 2020-10-20 | 刘军 | Dynamic video image processing method for angiography |
| CN113393425A (en) * | 2021-05-19 | 2021-09-14 | 武汉大学 | Microvessel distribution symmetry quantification method for gastric mucosa staining amplification imaging |
| CN115019926A (en) * | 2022-08-08 | 2022-09-06 | 中国人民解放军总医院第一医学中心 | Method and device for analyzing pathological morphology of renal blood vessels |
| CN116309551A (en) * | 2023-05-11 | 2023-06-23 | 浙江太美医疗科技股份有限公司 | Method, device, electronic equipment and readable medium for determining focus sampling area |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000011146A (en) * | 1998-06-19 | 2000-01-14 | Fuji Xerox Co Ltd | Image processor and ct scanner and fractal dimension measuring method |
| WO2014082015A1 (en) * | 2012-11-23 | 2014-05-30 | Icad, Inc. | System and method for improving workflow efficiencies in reading tomosynthesis medical image data |
-
2015
- 2015-01-29 CN CN201510047378.1A patent/CN104657598A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000011146A (en) * | 1998-06-19 | 2000-01-14 | Fuji Xerox Co Ltd | Image processor and ct scanner and fractal dimension measuring method |
| WO2014082015A1 (en) * | 2012-11-23 | 2014-05-30 | Icad, Inc. | System and method for improving workflow efficiencies in reading tomosynthesis medical image data |
Non-Patent Citations (3)
| Title |
|---|
| 吴晋蓉: "星形细胞肿瘤微血管参数与 VEGF 阳性单位的关系及 CD34+细胞三维分布", 《中国优秀博硕士学位论文全文数据库（硕士）医药卫生科技辑》 * |
| 王泽: "软体柔性管状器官的生物摩檫学性能研究", 《软体柔性管状器官的生物摩檫学性能研究》 * |
| 陈聪 等: "微血管分形维数在胶质瘤患者预后判断中的作用", 《第十届全国肿瘤转移学术大会论文集》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908920A (en) * | 2017-11-01 | 2018-04-13 | 东南大学 | The characterizing method of oxygen carrier reactivity in burning chemistry chains |
| CN108062981A (en) * | 2018-01-15 | 2018-05-22 | 深港产学研基地 | A kind of modeling method in the kind of the asymmetric tree of point of shape blood vessel with inter-species scale |
| CN108062981B (en) * | 2018-01-15 | 2023-06-27 | 深港产学研基地 | Modeling method for intraspecies and interspecific scales of fractal vascular asymmetric tree |
| CN109493949A (en) * | 2018-10-26 | 2019-03-19 | 浙江大学 | A kind of the determination method, apparatus and computer storage medium of left auricle of heart complexity |
| CN109493949B (en) * | 2018-10-26 | 2021-08-10 | 浙江大学 | Method and device for determining complexity of left atrial appendage and computer storage medium |
| CN111798432A (en) * | 2020-07-07 | 2020-10-20 | 刘军 | Dynamic video image processing method for angiography |
| CN113393425A (en) * | 2021-05-19 | 2021-09-14 | 武汉大学 | Microvessel distribution symmetry quantification method for gastric mucosa staining amplification imaging |
| CN113393425B (en) * | 2021-05-19 | 2022-04-26 | 武汉大学 | Microvessel distribution symmetry quantification method for gastric mucosa staining amplification imaging |
| CN115019926A (en) * | 2022-08-08 | 2022-09-06 | 中国人民解放军总医院第一医学中心 | Method and device for analyzing pathological morphology of renal blood vessels |
| CN115019926B (en) * | 2022-08-08 | 2022-10-25 | 中国人民解放军总医院第一医学中心 | Method and device for analyzing pathological morphology of renal blood vessels |
| CN116309551A (en) * | 2023-05-11 | 2023-06-23 | 浙江太美医疗科技股份有限公司 | Method, device, electronic equipment and readable medium for determining focus sampling area |
| CN116309551B (en) * | 2023-05-11 | 2023-08-15 | 浙江太美医疗科技股份有限公司 | Method, device, electronic equipment and readable medium for determining focus sampling area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104657598A (en) | Method for calculating fractal dimension of microvessels of tissue | |
| Arimura et al. | Radiomics with artificial intelligence for precision medicine in radiation therapy | |
| Hu et al. | GasHisSDB: A new gastric histopathology image dataset for computer aided diagnosis of gastric cancer | |
| Yip et al. | Applications and limitations of radiomics | |
| Zhang et al. | Quantitative CT texture analysis for evaluating histologic grade of urothelial carcinoma | |
| Wu et al. | Prediction of molecular subtypes of breast cancer using BI-RADS features based on a “white box” machine learning approach in a multi-modal imaging setting | |
| Baghdadi et al. | Automated differentiation of benign renal oncocytoma and chromophobe renal cell carcinoma on computed tomography using deep learning | |
| Wang et al. | Development of an AI system for accurately diagnose hepatocellular carcinoma from computed tomography imaging data | |
| Daunoravicius et al. | Quantification of myocardial fibrosis by digital image analysis and interactive stereology | |
| EP3758601A1 (en) | Systems and methods for quantifying multiscale competitive landscapes of clonal diversity in glioblastoma | |
| CN109685810A (en) | A kind of recognition methods of Bile fistula lesion and system based on deep learning | |
| JP2019532789A (en) | Mapping of mammary artery calcification | |
| US20200388032A1 (en) | Three dimensional histopathology imaging method and system thereof | |
| Mei et al. | YOLO-lung: A practical detector based on imporved YOLOv4 for Pulmonary Nodule Detection | |
| Condon et al. | Replication of an open-access deep learning system for screening mammography: Reduced performance mitigated by retraining on local data | |
| Zhang et al. | SAMS-Net: Fusion of attention mechanism and multi-scale features network for tumor infiltrating lymphocytes segmentation | |
| Fu et al. | M3ResU-Net: a deep residual network for multi-center colorectal polyp segmentation based on multi-scale learning and attention mechanism | |
| Hajiarbabi | Skin cancer detection using multi-scale deep learning and transfer learning | |
| US11615881B2 (en) | Liver cancer detection | |
| CN105869169A (en) | Automatic dividing method of tumor issue micro array image | |
| Li et al. | Clinical study of diffusion-weighted imaging in the diagnosis of liver focal lesion | |
| CN116309551B (en) | Method, device, electronic equipment and readable medium for determining focus sampling area | |
| CN103164599A (en) | Liver cirrhosis remote consultation system based on abdominal computed tomography (CT) image transmission | |
| Kong et al. | Evaluation of radiomics models based on computed tomography for distinguishing between benign and malignant thyroid nodules | |
| CN103815926B (en) | Breast cancer detection method and apparatus |
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: 20150527 |
|
| RJ01 | Rejection of invention patent application after publication |