CN112233811A - NASH liver digital pathological analysis system, working method and application - Google Patents

NASH liver digital pathological analysis system, working method and application Download PDF

Info

Publication number
CN112233811A
CN112233811A CN202011115333.0A CN202011115333A CN112233811A CN 112233811 A CN112233811 A CN 112233811A CN 202011115333 A CN202011115333 A CN 202011115333A CN 112233811 A CN112233811 A CN 112233811A
Authority
CN
China
Prior art keywords
pathological
unit
storage unit
pathological feature
analysis
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
Application number
CN202011115333.0A
Other languages
Chinese (zh)
Inventor
靳策
陈继巧
沈红英
庄永杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Kemaqi Biotechnology Co ltd
Original Assignee
Jiangsu Kemaqi Biotechnology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu Kemaqi Biotechnology Co ltd filed Critical Jiangsu Kemaqi Biotechnology Co ltd
Priority to CN202011115333.0A priority Critical patent/CN112233811A/en
Publication of CN112233811A publication Critical patent/CN112233811A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
    • 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
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • 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
    • G06T2207/30056—Liver; Hepatic

Abstract

The invention discloses a NASH liver digital pathological analysis system, a working method and application; belongs to the field of pathological analysis; the technical key points are as follows: it includes: a NASH liver digital pathology analysis system, comprising: the device comprises an imaging unit, a storage unit, a display unit and a processing unit; the imaging unit is used for carrying out full-slice scanning on the dyed slices to obtain slice images; the storage unit is used for storing the information transmitted by the imaging unit and the processing unit; the processing unit is used for determining an identification region ROI and a positive marker Label from an original image and analyzing and calculating a pathological characteristic part; the display unit is used for displaying results.

Description

NASH liver digital pathological analysis system, working method and application
Technical Field
The invention relates to the technical fields of medical research, pathological analysis and the like, in particular to an NASH liver digital pathological analysis system, a working method and application.
Background
At this stage, research on digital pathology analysis systems is increasing.
For example: CN103393403B discloses a digital human body structure analysis method and a digital human body analysis and pathology analysis method and system, a digitalized tool suitable for medical research, clinical consultation, teaching in colleges and universities, and personal body feeling, mainly comprising a three-dimensional human body model processing module, a pathology data storage module, a pathology data search and analysis module, a multimedia server, an image output device (projection, display or touch screen), and the like, the system adopts windows Chinese operating system or android operating system as a main operating platform, uses virtual digital technology to input data of skin, muscle, tissue, organs, bones, acupuncture points and the like of a human body into the system, and enables a user to analyze, study and learn the detailed structure of the human body in 360 degrees in all directions through a man-machine interaction technology, and also inputs various pathological change data of each part of the human body into the system, so that the user can conveniently and visually compare, finally, the purposes of learning, researching and pathological judgment and analysis are achieved.
However, the digital analysis system for NASH pathology analysis has not been studied yet by search.
Disclosure of Invention
The invention aims to provide an NASH liver digital pathological analysis system, a working method and application aiming at the defects of the prior art.
A NASH liver digital pathology analysis system, comprising: the device comprises an imaging unit, a storage unit, a display unit and a processing unit;
the imaging unit is used for carrying out full-slice scanning on the dyed slices to obtain slice images;
the storage unit is used for storing the information transmitted by the imaging unit and the processing unit;
the processing unit is used for determining an identification region ROI and a positive marker Label from an original image and analyzing and calculating a pathological characteristic part;
the display unit is used for displaying various results.
Further, the imaging unit scans the slice and sends the scanned image to the storage unit, and the output end of the imaging unit is connected with the input end of the storage unit;
the processing unit is bidirectionally connected with the storage unit, namely information can circulate bidirectionally;
and the input end of the display unit is connected with the output end of the storage unit.
Further, the processing unit processes the initial image of the imaging unit, which includes: the system comprises a recognition analysis area module, a pathological characteristic part recognition module and a pathological characteristic analysis module;
the identification analysis region module is used for identifying an analysis region in the original image transmitted by the storage unit, namely determining an identification region ROI;
wherein the pathological feature identification module is used for identifying pathological features in the ROI area;
the pathological feature analysis module is used for analyzing and calculating pathological feature parts.
Further, still include: and the output end of the input unit is connected with the input end of the storage unit.
A working method of an NASH liver digital pathological analysis system comprises the following steps:
s1, imaging: scanning the stained section by using an imaging unit;
s2, determining images of the identification region ROI, images of the positively marked Label and the positive rate;
s3, displaying the result, the display unit displaying: identifying images of the regional ROI, images of the positively labeled Label and the positive rate;
wherein, S2 includes the following substeps:
s2-1, identifying an analysis region in the original image transmitted by the storage unit, namely determining an identification region ROI;
s2-2, identifying corresponding pathological feature parts, namely positive marker Label, in the ROI by calling a pathological feature part analysis module;
s2-3, analyzing and calculating the pathological feature part by using the pathological analysis evaluation module, specifically, calculating the positive rate which is the quantitative value of the pathological feature, namely the area of the pathological feature in the tissue/the analysis area of the tissue;
and S2-4, transferring the images generated in the first step and the second step and the data generated in the third step to a storage unit.
Further, before the step of S1, the method further comprises a step of S0, inputting a fatty degeneration pathological feature marker: inputting the fatty degeneration pathological feature marker, the inflammation pathological feature marker and the necrosis pathological feature marker into a storage unit by using an input unit;
h & E staining: the pathological feature markers of the steatosis are as follows: judging the color threshold value, namely judging the color to be gray and to be steatosis; pathological feature markers of necrosis were used: judging by a color threshold value, namely, when the color is pink brown, the color is necrosis; the inflammation pathological feature markers are as follows: judging by a color threshold value, namely judging as inflammation when the color is blue;
SR staining: the pathological feature marker of the collagen fiber content adopts the following steps: the color threshold value is judged, namely the collagen fiber deposition which is positive in staining is judged by 'the color is pink'.
A NASH liver digital pathological analysis system is applied, and is used for quantitatively analyzing steatosis, inflammation, necrosis and collagen fiber content.
The application has the advantages that:
first, the present application presents a NASH liver digital pathology analysis system, which includes: the device comprises an imaging unit, a storage unit, a display unit and a processing unit; the imaging unit is used for carrying out full-slice scanning on the dyed slices to obtain slice images; the storage unit is used for storing the information transmitted by the imaging unit and the processing unit; the processing unit is used for determining an identification region ROI (region of interest) and a positive marker Label (pathological feature marker) from an original image and analyzing and calculating pathological feature parts; the display unit is used for displaying various results.
That is, the NASH liver digital pathology analysis system of the present application identifies the pathological feature region based on the pathological feature Label (as shown in fig. 6 to 9, it can be calibrated on the image), and can determine the pathological degree of the tissue, for example: steatosis, inflammation, hepatocellular necrosis, collagen fibrils.
Secondly, the application provides a working method of the NASH liver digital pathology analysis system, which specifically comprises the following steps: s1, imaging: scanning the stained section by using an imaging unit; s2, determining images of the identification region ROI, images of the positively marked Label and the positive rate; s3, displaying the result, the display unit displaying: identifying images of the regional ROI, images of the positively labeled Label and the positive rate; wherein S2 is the core concept of the present application and is also an essential technical feature for solving the technical problem.
Third, the present application presents pathological signature markers for NASH liver digital pathological features: h & E staining: the pathological feature markers of the steatosis are as follows: judging the color threshold value, namely judging the color to be gray and to be steatosis; pathological feature markers of necrosis were used: judging by a color threshold value, namely, when the color is pink brown, the color is necrosis; the inflammation pathological feature markers are as follows: judging by a color threshold value, namely judging as inflammation when the color is blue; SR staining: the pathological feature marker of the collagen fiber content adopts the following steps: the color threshold value is judged, namely the collagen fiber deposition which is positive in staining is judged by 'the color is pink'.
Drawings
The invention will be further described in detail with reference to examples of embodiments shown in the drawings to which, however, the invention is not restricted.
FIG. 1(a) is an original scan image stained with H & E; fig. 1(b) is an original scanned image stained with SR.
FIG. 2(a) is an image of an analysis area stained with H & E; fig. 2(b) is an analysis region image stained with SR.
FIG. 3(a) is a positive marker image stained with H & E; FIG. 3(b) is a positive marker image stained with SR.
FIG. 4 is a NASH liver digital pathology analysis system of example 1.
Fig. 5 is a flowchart of the operation of a NASH liver digital pathology analysis system of example 1.
Fig. 6 is a steatosis analysis image of example 2.
Fig. 7 is a necrosis analysis image of example 2.
Fig. 8 is an image of liver fibrosis/collagen deposition analysis of example 2.
Fig. 9 is an analysis image of inflammation of example 2.
Detailed Description
Example 1, a NASH liver digital pathology analysis system, comprising: an imaging unit 1, a storage unit 2, an input unit 3, a display unit 4, a processing unit 5;
the imaging unit 1 is used for carrying out full-slice scanning on the dyed slices to obtain slice images;
the storage unit 2 is used for storing the information transmitted by the imaging unit 1 and the processing unit 5;
the processing unit 5 is used for determining an identification region ROI and a positive marker Label from an original image and analyzing and calculating a pathological characteristic part;
the display unit 4 is used for displaying various results;
the imaging unit 1 scans a slice and sends a scanned image to the storage unit 2, and the output end of the imaging unit 1 is connected with the input end of the storage unit 2;
the processing unit 5 is bidirectionally connected with the storage unit 2, namely information can circulate bidirectionally;
the output end of the input unit 3 is connected with the input end of the storage unit 2, and the input end of the display unit 4 is connected with the output end of the storage unit 2;
the processing unit 5 processes an initial image of the imaging unit 1, and includes: the system comprises a recognition analysis area module 5-1, a pathological characteristic part recognition module 5-2 and a pathological characteristic analysis module 5-3;
the identification and analysis region module 5-1 is configured to identify an analysis region in the original image transmitted from the storage unit 2, that is, determine an identification region ROI;
wherein the pathological feature recognition module 5-2 is configured to recognize a pathological feature in the ROI region;
the pathological feature analysis module 5-3 is used for analyzing and calculating pathological feature parts.
The working method of the processing unit 5 comprises the following steps:
firstly, identifying an analysis region in the original image transmitted by the storage unit 2, namely determining an identification region ROI;
secondly, identifying a corresponding pathological characteristic part, namely a positive marker Label, in the ROI by calling a pathological characteristic part analysis module 5-2;
thirdly, analyzing and calculating the pathological feature part by using the pathological analysis evaluation module 5-3, specifically, calculating the quantification value-positive rate of the pathological feature, namely the area of the pathological feature in the tissue/the analysis area of the tissue;
and fourthly, transmitting the images generated in the first step and the second step and the data generated in the third step to a storage unit 2.
In particular, for the first step, since the stained section has a very significant color difference from the background color (fig. 1), image recognition can be performed by the color difference, i.e. the analysis region ROI is determined, for example, as shown in fig. 2.
For the second step, the pathologic feature region recognition module 5-2 is called, and the pathologic feature region recognition module 5-2 accesses the storage unit 1 (the storage unit 1 retains the judgment criterion of the pathologic features).
For the third step, after the second step is finished, the pathological analysis and evaluation module 5-3 performs pathological feature statistical data on the slice image, that is, the pathological feature statistical data of the measured tissue condition is obtained by using classified positioning positives to obtain a quantitative value-positive rate of the pathological feature.
It should be noted that the pathological feature and pathological feature markers of the liver stored in the storage unit 1 are critical to the accuracy of the system: specifically, the following indexes are selected for joint judgment: tissue area size, form factor, pixel range, color threshold.
The pathological feature markers are input to the storage unit 1 through the input unit 3.
A working method of a NASH liver digital pathology analysis system comprises the following steps:
s1, imaging, namely scanning the dyed slices by adopting an imaging unit;
s2, determining images of the identification region ROI, images of the positively marked Label and the positive rate;
s3, displaying the result, the display unit displaying: determining an image of an identification region ROI, an image of a positively labeled Label and a positive rate;
s2 includes the following substeps:
s2-1, identifying an analysis region in the original image transmitted from the storage unit 2, namely determining an identification region ROI;
s2-2, identifying corresponding pathological feature parts, namely positive marker Label, in the ROI by calling the pathological feature part analysis module 5-2;
s2-3, using the pathological analysis evaluation module 5-3 to analyze and calculate the pathological feature part, specifically, calculating the quantitative value-positive rate of the pathological feature, namely the area of pathological feature in the tissue/the analysis area of the tissue;
and S2-4, transferring the images generated in the first step and the second step and the data generated in the third step to a storage unit 2.
Example 2, a NASH liver digital pathology analysis system for quantitatively analyzing steatosis, measuring inflammation, measuring necrosis, measuring collagen fiber content;
in the step of example 1, before the step of S1, further comprising S0, the method further comprises inputting a fatty degeneration pathology signature: inputting a fatty degeneration pathological feature marker, an inflammation pathological feature marker, a necrosis pathological feature marker (the fatty degeneration pathological feature marker, the inflammation pathological feature marker and the necrosis pathological feature marker are pathological sections stained by H & E) and a collagen fiber content pathological feature marker (the collagen fiber content pathological feature marker is a pathological section stained by SR) into a storage unit by using an input unit 1;
the pathological feature markers of the steatosis are as follows: the color threshold value is determined, i.e., the color is gray, i.e., when the color is "# E3DEDB, # E3DDDD, # E5DDDB, # E5DCDD, # E7DFDD, # E3DEDB, # E6DDDE, # E9E2 DC", etc. Total fat content% = (large lipid droplet area + small lipid droplet area)/analysis area x 100.
As shown in fig. 6, which is a steatosis analysis image, it can be seen that: regular fat vacuoles are visible in hepatocytes, which are of varying sizes, and the hepatocyte nuclei are located at the margins.
Pathological feature markers of necrosis were used: the color threshold value is judged, namely, the color is pink brown. And (3) measuring and calculating the necrotic area: necrotic area ratio% = necrotic area/analysis area plane x 100.
The pathological feature marker of the collagen fiber content adopts the following steps: the color threshold value is judged, namely the collagen fiber deposition which is positive in staining is judged by 'the color is pink'. The collagen fiber content (quantified value of pathological characteristics) was measured, and the collagen fiber area per unit area was found to be a percentage. Collagen fiber content% = collagen fiber area/analysis area x 100.
The above-mentioned embodiments are only for convenience of description, and are not intended to limit the present invention in any way, and those skilled in the art will understand that the technical features of the present invention can be modified or changed by other equivalent embodiments without departing from the scope of the present invention.

Claims (7)

1. A NASH liver digital pathology analysis system, comprising: the device comprises an imaging unit, a storage unit, a display unit and a processing unit;
the imaging unit is used for carrying out full-slice scanning on the dyed slices to obtain slice images;
the storage unit is used for storing the information transmitted by the imaging unit and the processing unit;
the processing unit is used for determining an identification region ROI and a positive marker Label from an original image and analyzing and calculating a pathological characteristic part;
the display unit is used for displaying results.
2. The NASH liver digital pathology analysis system of claim 1, wherein the imaging unit scans the slice, sends the scanned image to the storage unit, and the output of the imaging unit is connected to the input of the storage unit;
the processing unit is bidirectionally connected with the storage unit, namely information can circulate bidirectionally;
and the input end of the display unit is connected with the output end of the storage unit.
3. The NASH liver digital pathology analysis system of claim 1, wherein the processing unit processes the initial image of the imaging unit, which comprises: the system comprises a recognition analysis area module, a pathological characteristic part recognition module and a pathological characteristic analysis module;
the identification analysis region module is used for identifying an analysis region in the original image transmitted by the storage unit, namely determining an identification region ROI;
wherein the pathological feature identification module is used for identifying pathological features in the ROI area;
the pathological feature analysis module is used for analyzing and calculating pathological feature parts.
4. The NASH liver digital pathology analysis system of claim 3, further comprising: and the output end of the input unit is connected with the input end of the storage unit.
5. A method for operating an NASH liver digital pathology analysis system according to any one of claims 1 to 4, comprising the steps of:
s1, imaging: scanning the stained section by using an imaging unit;
s2, determining images of the identification region ROI, images of the positively marked Label and the positive rate;
s3, displaying the result, the display unit displaying: identifying images of the regional ROI, images of the positively labeled Label and the positive rate;
wherein, S2 includes the following substeps:
s2-1, identifying an analysis region in the original image transmitted by the storage unit, namely determining an identification region ROI;
s2-2, identifying corresponding pathological feature parts, namely positive marker Label, in the ROI by calling a pathological feature part analysis module;
s2-3, analyzing and calculating the pathological feature part by using the pathological analysis evaluation module, specifically, calculating the positive rate which is the quantitative value of the pathological feature, namely the area of the pathological feature in the tissue/the analysis area of the tissue;
and S2-4, transferring the images generated in the first step and the second step and the data generated in the third step to a storage unit.
6. The method of claim 5, further comprising, prior to the step of S1, the step of inputting a marker for a pathological characteristic of steatosis at S0: inputting the fatty degeneration pathological feature marker, the inflammation pathological feature marker and the necrosis pathological feature marker into a storage unit by using an input unit;
h & E staining: the pathological feature markers of the steatosis are as follows: judging the color threshold value, namely judging the color to be gray and to be steatosis; pathological feature markers of necrosis were used: judging by a color threshold value, namely, when the color is pink brown, the color is necrosis; the inflammation pathological feature markers are as follows: judging by a color threshold value, namely judging as inflammation when the color is blue;
SR staining: the pathological feature marker of the collagen fiber content adopts the following steps: the color threshold value is judged, namely the collagen fiber deposition which is positive in staining is judged by 'the color is pink'.
7. Use of a NASH liver digital pathology analysis system, characterized in that it is the NASH liver digital pathology analysis system according to any one of claims 1 to 4, for quantitative analysis of steatosis, determination of inflammation, determination of necrosis, determination of collagen fibre content.
CN202011115333.0A 2020-10-19 2020-10-19 NASH liver digital pathological analysis system, working method and application Pending CN112233811A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011115333.0A CN112233811A (en) 2020-10-19 2020-10-19 NASH liver digital pathological analysis system, working method and application

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011115333.0A CN112233811A (en) 2020-10-19 2020-10-19 NASH liver digital pathological analysis system, working method and application

Publications (1)

Publication Number Publication Date
CN112233811A true CN112233811A (en) 2021-01-15

Family

ID=74117923

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011115333.0A Pending CN112233811A (en) 2020-10-19 2020-10-19 NASH liver digital pathological analysis system, working method and application

Country Status (1)

Country Link
CN (1) CN112233811A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105431089A (en) * 2013-07-17 2016-03-23 肝病定量分析有限责任公司 Systems and methods for determining hepatic function from liver scans
CN105550651A (en) * 2015-12-14 2016-05-04 中国科学院深圳先进技术研究院 Method and system for automatically analyzing panoramic image of digital pathological section
CN108573490A (en) * 2018-04-25 2018-09-25 王成彦 A kind of intelligent read tablet system for tumor imaging data
CN109791693A (en) * 2016-10-07 2019-05-21 文塔纳医疗系统公司 For providing the digital pathology system and related work process of visualization full slice image analysis
CN110763677A (en) * 2019-09-12 2020-02-07 杭州迪英加科技有限公司 Thyroid gland frozen section diagnosis method and system
CN110772286A (en) * 2019-11-05 2020-02-11 王宁 System for discernment liver focal lesion based on ultrasonic contrast
CN111247596A (en) * 2017-10-20 2020-06-05 基恩菲特公司 Automatic pattern recognition and scoring method for histological images

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105431089A (en) * 2013-07-17 2016-03-23 肝病定量分析有限责任公司 Systems and methods for determining hepatic function from liver scans
CN105550651A (en) * 2015-12-14 2016-05-04 中国科学院深圳先进技术研究院 Method and system for automatically analyzing panoramic image of digital pathological section
CN109791693A (en) * 2016-10-07 2019-05-21 文塔纳医疗系统公司 For providing the digital pathology system and related work process of visualization full slice image analysis
CN111247596A (en) * 2017-10-20 2020-06-05 基恩菲特公司 Automatic pattern recognition and scoring method for histological images
CN108573490A (en) * 2018-04-25 2018-09-25 王成彦 A kind of intelligent read tablet system for tumor imaging data
CN110763677A (en) * 2019-09-12 2020-02-07 杭州迪英加科技有限公司 Thyroid gland frozen section diagnosis method and system
CN110772286A (en) * 2019-11-05 2020-02-11 王宁 System for discernment liver focal lesion based on ultrasonic contrast

Similar Documents

Publication Publication Date Title
White et al. MeshMonk: Open-source large-scale intensive 3D phenotyping
CN110490851B (en) Mammary gland image segmentation method, device and system based on artificial intelligence
CN109920538B (en) Zero sample learning method based on data enhancement
Mastmeyer et al. Evaluation of direct haptic 4d volume rendering of partially segmented data for liver puncture simulation
Karapetyan et al. Automatic detection and concealment of specular reflections for endoscopic images
CN111583385B (en) Personalized deformation method and system for deformable digital human anatomy model
CN110428417A (en) Property method of discrimination, storage medium and the Vltrasonic device of carotid plaques
CN106023214B (en) Image quality evaluating method and system based on central fovea view gradient-structure similitude
Woo et al. Speech map: A statistical multimodal atlas of 4D tongue motion during speech from tagged and cine MR images
Xia et al. Toward accurate quality estimation of screen content pictures with very sparse reference information
Mussi et al. A novel ear elements segmentation algorithm on depth map images
CN111528907A (en) Ultrasonic image pneumonia auxiliary diagnosis method and system
Mariam et al. On smart gaze based annotation of histopathology images for training of deep convolutional neural networks
CN106204523A (en) A kind of image quality evaluation method and device
Fathabad et al. Content based image retrieval for medical images
Platiša et al. Influence of study design on digital pathology image quality evaluation: the need to define a clinical task
CN112233811A (en) NASH liver digital pathological analysis system, working method and application
CN112132772B (en) Pathological section real-time interpretation method, device and system
CN116993699A (en) Medical image segmentation method and system under eye movement auxiliary training
CN115607153B (en) Psychological scale answer quality assessment system and method based on eye movement tracking
Hewer et al. A multilinear tongue model derived from speech related MRI data of the human vocal tract
Zhang et al. An approach of region of interest detection based on visual attention and gaze tracking
Langlois et al. Uncovering visual priors in spatial memory using serial reproduction.
CN117671774B (en) Face emotion intelligent recognition analysis equipment
Hammal et al. Eyes segmentation applied to gaze direction and vigilance estimation

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