CN113436722A - Technology for molecular feature prediction and prognosis judgment of renal clear cell carcinoma based on pathological picture - Google Patents
Technology for molecular feature prediction and prognosis judgment of renal clear cell carcinoma based on pathological picture Download PDFInfo
- Publication number
- CN113436722A CN113436722A CN202110694103.2A CN202110694103A CN113436722A CN 113436722 A CN113436722 A CN 113436722A CN 202110694103 A CN202110694103 A CN 202110694103A CN 113436722 A CN113436722 A CN 113436722A
- Authority
- CN
- China
- Prior art keywords
- pathological
- patient
- picture
- molecular
- cell carcinoma
- 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
- 230000001575 pathological effect Effects 0.000 title claims abstract description 80
- 238000004393 prognosis Methods 0.000 title claims abstract description 25
- 208000030808 Clear cell renal carcinoma Diseases 0.000 title claims abstract description 21
- 206010073251 clear cell renal cell carcinoma Diseases 0.000 title claims abstract description 21
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 230000004083 survival effect Effects 0.000 claims abstract description 18
- 230000035772 mutation Effects 0.000 claims abstract description 12
- 210000004027 cell Anatomy 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 210000000805 cytoplasm Anatomy 0.000 claims description 6
- 102100032742 Histone-lysine N-methyltransferase SETD2 Human genes 0.000 claims description 3
- 101001095815 Homo sapiens E3 ubiquitin-protein ligase RING2 Proteins 0.000 claims description 3
- 101000654725 Homo sapiens Histone-lysine N-methyltransferase SETD2 Proteins 0.000 claims description 3
- 101001057193 Homo sapiens Membrane-associated guanylate kinase, WW and PDZ domain-containing protein 1 Proteins 0.000 claims description 3
- 101000601770 Homo sapiens Protein polybromo-1 Proteins 0.000 claims description 3
- 101000740048 Homo sapiens Ubiquitin carboxyl-terminal hydrolase BAP1 Proteins 0.000 claims description 3
- 101000740049 Latilactobacillus curvatus Bioactive peptide 1 Proteins 0.000 claims description 3
- 102100027240 Membrane-associated guanylate kinase, WW and PDZ domain-containing protein 1 Human genes 0.000 claims description 3
- 102100037516 Protein polybromo-1 Human genes 0.000 claims description 3
- 230000007170 pathology Effects 0.000 claims 2
- 108090000623 proteins and genes Proteins 0.000 abstract description 2
- 238000013518 transcription Methods 0.000 abstract description 2
- 230000035897 transcription Effects 0.000 abstract description 2
- 206010028980 Neoplasm Diseases 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 201000011510 cancer Diseases 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000005056 cell body Anatomy 0.000 description 1
- 210000003855 cell nucleus Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002103 transcriptional effect Effects 0.000 description 1
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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a technology for predicting the molecular characteristics of renal clear cell carcinoma and judging prognosis based on pathological pictures, which comprises the following parts: a first part: extracting the characteristics of the pathological picture; a second part: the pathological picture predicts the molecular characteristics of the patient; and a third part: predicting the life cycle of the patient by integrating a single pathological picture and a pathological picture into a multiomic; the invention can rapidly and economically quantify pathological pictures of patients, predict important mutation states, molecular subtype attributions and survival of the patients, and rapidly and economically judge the survival time of the patients with existing gene, transcription or proteomics data.
Description
Technical Field
The invention relates to cancer molecular feature prediction, in particular to a renal clear cell carcinoma molecular feature prediction and prognosis judgment technology based on pathological pictures, and belongs to the technical field of cell processing.
Background
With the development of accurate oncology, histopathological images have become the gold standard for diagnostic staging of tumors. Meanwhile, omics maps including genomics, transcriptomics and proteomics are becoming a conventional method for identifying tumor features and being used for life prediction, but quantitative studies on pathological images and great potential application value thereof are not completely developed, and the technology is a blank in renal clear cell carcinoma.
The pathological picture analysis in the prior art can only be intuitively felt by naked eyes, and the intuitive result of the naked eyes cannot be measured while a large amount of information is ignored. Models have been used to predict patients using genetic, transcriptional or proteomic techniques. However, these models require sequencing data of the patient, requiring a large amount of money and relatively long waiting times.
The invention analyzes basic and high-order characteristics (including cell morphology, size, nuclear size, cytoplasm density gray scale, cell proximity relation and the like) of cells of renal clear cell carcinoma by using an automatic method with high efficiency, consistency and cost benefit, predicts mutation, molecular subtype and prognosis of renal clear cell carcinoma by using a machine learning method based on the cell characteristics, and integrates pathological picture characteristics with data of genomics, transcriptomics and proteomics for patients with the data, thereby remarkably improving the prognosis capability.
The technology has the characteristics of economy, high efficiency and the like, can be well integrated with other omics data of patients, and solves the technical problems of quantification and application of pathological pictures. In addition, the basic framework of the technology can be popularized and applied to other cancer types, and has a large application potential.
Disclosure of Invention
The present invention aims to provide a renal clear cell carcinoma molecular feature prediction and prognosis judgment technology based on pathological images to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: a renal clear cell carcinoma molecular feature prediction and prognosis judgment technology based on pathological pictures comprises the following parts:
a first part: extracting the characteristics of the pathological picture;
a second part: the pathological picture predicts the molecular characteristics of the patient;
and a third part: predicting the life cycle of the patient by integrating a single pathological picture and a pathological picture into a multiomic;
as a preferred technical scheme of the invention, the characteristic extraction of the pathological picture comprises the following specific operation steps:
s1: reading a pathological picture by adopting open source programming software Python, and cutting the pathological picture into small slices with 800 pixels by 1000 pixels;
s2: randomly selecting 50 small slices for each patient by adopting Python, outputting and storing the 50 small slices in corresponding folders of each patient, and performing feature extraction on the 50 corresponding small pathological slices of each patient by adopting open source software CellProfiler;
as a preferred embodiment of the present invention, in step S2, 593 features including cell morphology, size, nuclear size, cytoplasm density gray scale and cell proximity relation can be extracted from each of 50 small pathological sections, and the average value of each feature of the 50 pictures represents the feature of the patient, so that a total of 593 features can be extracted from pathological pictures of each patient.
As a preferred technical solution of the present invention, the specific operation steps of the second part are as follows:
the first step is as follows: carrying out mutation and molecular subtype prediction on 593 pathological characteristics of the patient by adopting open source programming software Python;
the second step is as follows: the method comprises the steps of selecting pathological picture characteristics of a patient by using a random forest algorithm, further carrying out mutation and molecular subtype classification modeling on the selected characteristics by using the random forest algorithm, and effectively predicting important mutation (VHL, BAP1, PBRM1 and SETD2) states and molecular subtype (basal type, interstitial type, classical type and atypical) attribution of renal clear cell carcinoma patients through the pathological picture characteristics after the classification modeling.
As a preferred technical scheme of the invention, the specific operation steps for predicting the survival time of the patient are as follows:
a. performing patient prognosis analysis by using open source programming software R;
b. the random survival forest model is realized through open source programming software R, the pathological picture characteristics of the patient are input, the prognosis risk score of the patient can be output at high precision, and the survival probability of the patient in 1 year, 3 years and 5 years can be accurately predicted through the prognosis risk score.
Compared with the prior art, the invention has the beneficial effects that:
the invention relates to a technology for predicting the molecular characteristics and prognosis of renal clear cell carcinoma based on pathological pictures, which can quickly and economically quantify pathological pictures of patients, predict important mutation states, molecular subtype affiliations and survival of the patients, and quickly and economically judge the survival time of the patients with existing gene, transcription or proteomics data more accurately.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic view of a pathological image feature extraction process according to the present invention;
FIG. 3 is a schematic structural diagram of a CellProfiler feature extraction process according to the present invention;
FIG. 4 is a schematic structural diagram of a process for predicting molecular characteristics of a patient according to the pathological image characteristics of the present invention;
FIG. 5 is a schematic structural diagram of a process for predicting the survival time of a patient according to the characteristics of pathological images of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-5, the present invention provides a technical solution of a renal clear cell carcinoma molecular feature prediction and prognosis determination technique based on pathological images: a technology for predicting the molecular characteristics of renal clear cell carcinoma and judging the prognosis of renal clear cell carcinoma based on pathological pictures comprises the following parts:
a first part: extracting the characteristics of the pathological picture;
a second part: the pathological picture predicts the molecular characteristics of the patient;
and a third part: predicting the life cycle of the patient by integrating a single pathological picture and a pathological picture into a multiomic;
the specific operation steps of the first part are as follows:
s1: reading a pathological picture by adopting open source programming software Python, and cutting the pathological picture into small slices with 800 pixels by 1000 pixels;
s2: randomly selecting 50 small slices for each patient by adopting Python, outputting and storing the 50 small slices in corresponding folders of the patients, and extracting the characteristics of the 50 small pathological slices corresponding to each patient by adopting open source software CellProfiler;
in step S2, 593 features including cell morphology, size, nuclear size, cytoplasm density gray scale, and cell proximity relation can be extracted from each of 50 small pathological sections, and the average value of each feature of the 50 pictures is used to represent the feature of the patient, so that a total of 593 features can be extracted from the pathological picture of each patient.
The second part comprises the following specific operation steps:
the first step is as follows: carrying out mutation and molecular subtype prediction on 593 pathological characteristics of the patient by adopting open source programming software Python;
the second step is as follows: and selecting pathological picture features of the patient by using a random forest algorithm, and further mutating the selected features and performing molecular subtype classification modeling by using the random forest algorithm.
In the second step, after classification modeling, the model can effectively predict important mutation (VHL, BAP1, PBRM1, SETD2) states and molecular subtype (basal type, interstitial type, classical type and atypical type) attribution of renal clear cell carcinoma patients through pathological picture characteristics.
The third part comprises the following specific operation steps:
a. performing patient prognosis analysis by using open source programming software R;
b. the random survival forest model is realized through open source programming software R, the pathological picture characteristics of the patient are input, and the prognosis risk score of the patient can be output with high precision.
In the step b, the survival probability of the patient for 1 year, 3 years and 5 years can be accurately predicted through the prognosis risk score, and meanwhile, the accuracy of the score can be further improved by combining other omics of the patient, such as genomics, transcriptomics, proteomics and the like.
According to fig. 1-3, the version of the open source programming software Python is 3.6.3, the version of the open source software CellProfiler is 2.2.0, and the version of the open source programming software R is 3.5.3.
As shown in fig. 1, the technique is mainly divided into three steps: 1) extracting pathological picture features; 2) predicting the molecular characteristics of the patient by the pathological picture characteristics; 3) predicting the life cycle of the patient by the pathological picture characteristics;
as shown in fig. 2, specifically, the pathological image feature extraction process includes the following steps:
1. taking a pathological picture of a patient as input, reading the whole pathological picture by an Openslide library of a programming software Python, cutting the pathological picture into pathological small sections of 800 pixels by 1000 pixels, and randomly selecting 50 pathological small sections for subsequent analysis.
2. 593 features of the 50 small sections were extracted by CellProfiler software and averaged for summary.
As shown in fig. 3, specifically, the CellProfiler feature extraction process is as follows:
1. and image processing, namely taking 50 small slices as input, wherein the image processing comprises the steps of image input, color correction, brightness correction and gray scale correction.
2. The 50 processed small slices are used as input, an object recognition module is written through CellProfiler, and the cell nucleus is recognized firstly, and then the cell body and the cytoplasm are recognized.
3. The identified cells are used as input, and a feature extraction module is written by CellProfiler to extract 593 features of the patient cells, including basic and high-order features (including cell morphology, size, nuclear size, cytoplasm density gray scale, cell proximity relation and the like).
According to fig. 4, specifically, the process of predicting the molecular characteristics of the patient by the pathological image characteristics includes:
1. and taking the extracted pathological picture characteristics of the patient as input, and performing random forest algorithm screening characteristics through a random library of programming software Python.
2. And (3) taking the extracted important features as input, and predicting the important mutation state and the molecular subtype attribution of the patient by adopting a random library of programming software Python to construct a completed random forest algorithm model.
As shown in fig. 5, in detail, the pathological image feature prediction patient survival process:
1. 593 pathological characteristics of the patient are used as input, a random forest survival algorithm model is constructed through a randomForestSRC package of programming software R, and the disease risk score and survival probability of 1, 3 and 5 years are output.
2. By taking 593 pathological characteristics of the patient and other omics data (including genomics, proteomics and transcriptomics) as input, a more accurate disease risk score of the patient and a more accurate survival probability of 1, 3 and 5 years can be output.
The programming software Python and R can be replaced by MATLAB, C + +, Java and other programming languages.
In the description of the present invention, it is to be understood that the indicated orientations or positional relationships are based on the orientations or positional relationships shown in the drawings and are only for convenience in describing the present invention and simplifying the description, but are not intended to indicate or imply that the indicated devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are not to be construed as limiting the present invention.
In the present invention, unless otherwise explicitly specified or limited, for example, it may be fixedly attached, detachably attached, or integrated; can be mechanically or electrically connected; the terms may be directly connected or indirectly connected through an intermediate, and may be communication between two elements or interaction relationship between two elements, unless otherwise specifically limited, and the specific meaning of the terms in the present invention will be understood by those skilled in the art according to specific situations.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. A technology for predicting the molecular characteristics of renal clear cell carcinoma and judging the prognosis based on pathological pictures is characterized by comprising the following parts:
a first part: extracting the characteristics of the pathological picture;
a second part: the pathological picture predicts the molecular characteristics of the patient;
and a third part: single pathology pictures and pathology picture integrated multiomics predict patient survival.
2. The renal clear cell carcinoma molecular feature prediction and prognosis determination technology based on pathological image as claimed in claim 1, wherein: the specific operation steps of the feature extraction of the pathological picture are as follows:
s1: reading a pathological picture by adopting open source programming software Python, and cutting the pathological picture into small slices with 800 pixels by 1000 pixels;
s2: and randomly selecting 50 small slices for each patient by adopting Python, outputting and storing the 50 small slices in corresponding folders of the patients, and extracting the characteristics of the 50 small pathological slices corresponding to each patient by adopting open source software CellProfiler.
3. The renal clear cell carcinoma molecular feature prediction and prognosis determination technology based on pathological image as claimed in claim 2, wherein: in step S2, 593 features including cell morphology, size, nuclear size, cytoplasm density gray scale, and cell proximity relation can be extracted from each of 50 small pathological sections, and the average value of each feature of the 50 pictures is used to represent the feature of the patient, so that a total of 593 features can be extracted from the pathological picture of each patient.
4. The renal clear cell carcinoma molecular feature prediction and prognosis determination technology based on pathological image as claimed in claim 1, wherein: the specific operation steps of the second part are as follows:
the first step is as follows: carrying out mutation and molecular subtype prediction on 593 pathological characteristics of the patient by adopting open source programming software Python;
the second step is as follows: the method comprises the steps of selecting pathological picture characteristics of a patient by using a random forest algorithm, further carrying out mutation and molecular subtype classification modeling on the selected characteristics by using the random forest algorithm, and effectively predicting important mutation (VHL, BAP1, PBRM1 and SETD2) states and molecular subtype (basal type, interstitial type, classical type and atypical) attribution of renal clear cell carcinoma patients through the pathological picture characteristics after the classification modeling.
5. The renal clear cell carcinoma molecular feature prediction and prognosis determination technology based on pathological image as claimed in claim 1, wherein: the specific operation steps for predicting the survival time of the patient are as follows:
a. performing patient prognosis analysis by using open source programming software R;
b. the random survival forest model is realized through open source programming software R, the pathological picture characteristics of the patient are input, the prognosis risk score of the patient can be output at high precision, and the survival probability of the patient in 1 year, 3 years and 5 years can be accurately predicted through the prognosis risk score.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110694103.2A CN113436722A (en) | 2021-06-22 | 2021-06-22 | Technology for molecular feature prediction and prognosis judgment of renal clear cell carcinoma based on pathological picture |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110694103.2A CN113436722A (en) | 2021-06-22 | 2021-06-22 | Technology for molecular feature prediction and prognosis judgment of renal clear cell carcinoma based on pathological picture |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113436722A true CN113436722A (en) | 2021-09-24 |
Family
ID=77757040
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110694103.2A Pending CN113436722A (en) | 2021-06-22 | 2021-06-22 | Technology for molecular feature prediction and prognosis judgment of renal clear cell carcinoma based on pathological picture |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113436722A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114093512A (en) * | 2021-10-21 | 2022-02-25 | 杭州电子科技大学 | Survival prediction method based on multi-mode data and deep learning model |
-
2021
- 2021-06-22 CN CN202110694103.2A patent/CN113436722A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114093512A (en) * | 2021-10-21 | 2022-02-25 | 杭州电子科技大学 | Survival prediction method based on multi-mode data and deep learning model |
CN114093512B (en) * | 2021-10-21 | 2023-04-18 | 杭州电子科技大学 | Survival prediction method based on multi-mode data and deep learning model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dimitriou et al. | Deep learning for whole slide image analysis: an overview | |
US20200272864A1 (en) | Platform, device and process for annotation and classification of tissue specimens using convolutional neural network | |
CN103168314B (en) | For the method and apparatus of the mood based on Facial action unit identification individuality | |
Xie et al. | Deep learning for image analysis: Personalizing medicine closer to the point of care | |
CN108319605A (en) | The structuring processing method and system of medical examination data | |
CN108021788A (en) | The method and apparatus of deep sequencing data extraction biomarker based on cell free DNA | |
CN111598875A (en) | Method, system and device for building thyroid nodule automatic detection model | |
US20120010528A1 (en) | Systems and methods for predicting disease progression in patients treated with radiotherapy | |
Xie et al. | Evaluating cancer-related biomarkers based on pathological images: a systematic review | |
US20230306598A1 (en) | Systems and methods for mesothelioma feature detection and enhanced prognosis or response to treatment | |
Albalawi et al. | Oral squamous cell carcinoma detection using EfficientNet on histopathological images | |
CN113436722A (en) | Technology for molecular feature prediction and prognosis judgment of renal clear cell carcinoma based on pathological picture | |
Qiao et al. | Multi-modality artificial intelligence in digital pathology | |
CN112489813A (en) | Technology for molecular feature prediction and prognosis judgment of renal clear cell carcinoma based on pathological picture | |
Qiu et al. | Automatic prostate gleason grading using pyramid semantic parsing network in digital histopathology | |
Saidi et al. | Technology insight: will systems pathology replace the pathologist? | |
Classe et al. | Perspectives in pathomics in head and neck cancer | |
CN117612711B (en) | Multi-mode prediction model construction method and system for analyzing liver cancer recurrence data | |
Dabass et al. | A hybrid U-Net model with attention and advanced convolutional learning modules for simultaneous gland segmentation and cancer grade prediction in colorectal histopathological images | |
Wu et al. | Development and validation of an artificial intelligence-based image classification method for pathological diagnosis in patients with extramammary Paget’s disease | |
CN112749277B (en) | Medical data processing method, device and storage medium | |
Tenali et al. | Oral Cancer Detection using Deep Learning Techniques | |
CN113435469A (en) | Kidney tumor enhanced CT image automatic identification system based on deep learning and training method thereof | |
Vale-Silva et al. | MultiSurv: Long-term cancer survival prediction using multimodal deep learning | |
CN116933135A (en) | Modeling system and method for cancer stage prediction model based on cross-modal fusion cascade |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210924 |
|
WD01 | Invention patent application deemed withdrawn after publication |