CN117611543A - Artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system - Google Patents
Artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system Download PDFInfo
- Publication number
- CN117611543A CN117611543A CN202311568162.0A CN202311568162A CN117611543A CN 117611543 A CN117611543 A CN 117611543A CN 202311568162 A CN202311568162 A CN 202311568162A CN 117611543 A CN117611543 A CN 117611543A
- Authority
- CN
- China
- Prior art keywords
- risk prediction
- model
- module
- prognosis
- image
- 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
- 206010009944 Colon cancer Diseases 0.000 title claims abstract description 42
- 208000001333 Colorectal Neoplasms Diseases 0.000 title claims abstract description 42
- 208000007433 Lymphatic Metastasis Diseases 0.000 title claims abstract description 36
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 61
- 238000004393 prognosis Methods 0.000 claims abstract description 54
- 108010077544 Chromatin Proteins 0.000 claims abstract description 25
- 210000003483 chromatin Anatomy 0.000 claims abstract description 25
- 238000013058 risk prediction model Methods 0.000 claims abstract description 25
- 238000012546 transfer Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000012795 verification Methods 0.000 claims abstract description 18
- 108020004414 DNA Proteins 0.000 claims abstract description 16
- 108091093105 Nuclear DNA Proteins 0.000 claims abstract description 6
- 239000002356 single layer Substances 0.000 claims description 36
- 238000005070 sampling Methods 0.000 claims description 34
- 206010028980 Neoplasm Diseases 0.000 claims description 22
- 210000003855 cell nucleus Anatomy 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 16
- 230000009467 reduction Effects 0.000 claims description 15
- 230000001575 pathological effect Effects 0.000 claims description 13
- 238000009877 rendering Methods 0.000 claims description 11
- 210000004940 nucleus Anatomy 0.000 claims description 10
- 238000003745 diagnosis Methods 0.000 claims description 9
- 238000010972 statistical evaluation Methods 0.000 claims description 9
- 208000005016 Intestinal Neoplasms Diseases 0.000 claims description 6
- 238000002679 ablation Methods 0.000 claims description 6
- 201000002313 intestinal cancer Diseases 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 4
- 238000010186 staining Methods 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 238000009792 diffusion process Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 29
- 206010027476 Metastases Diseases 0.000 abstract description 15
- 230000009401 metastasis Effects 0.000 abstract description 15
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000012143 endoscopic resection Methods 0.000 description 4
- 238000011470 radical surgery Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 208000029691 metastatic malignant neoplasm in the lymph nodes Diseases 0.000 description 3
- 238000010837 poor prognosis Methods 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000004698 lymphocyte Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000002154 non-small cell lung carcinoma Diseases 0.000 description 2
- 230000002980 postoperative effect Effects 0.000 description 2
- 238000002271 resection Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 208000029729 tumor suppressor gene on chromosome 11 Diseases 0.000 description 2
- 206010006187 Breast cancer Diseases 0.000 description 1
- 208000026310 Breast neoplasm Diseases 0.000 description 1
- 206010061818 Disease progression Diseases 0.000 description 1
- 239000013255 MILs Substances 0.000 description 1
- 241001028048 Nicola Species 0.000 description 1
- 208000020584 Polyploidy Diseases 0.000 description 1
- 206010060862 Prostate cancer Diseases 0.000 description 1
- 208000000236 Prostatic Neoplasms Diseases 0.000 description 1
- 208000005718 Stomach Neoplasms Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000005750 disease progression Effects 0.000 description 1
- 206010017758 gastric cancer Diseases 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 210000001165 lymph node Anatomy 0.000 description 1
- 238000002406 microsurgery Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 201000011549 stomach cancer Diseases 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
- 230000004614 tumor growth Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V10/7753—Incorporation of unlabelled data, e.g. multiple instance learning [MIL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
-
- 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
- G06T2207/30096—Tumor; Lesion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/04—Recognition of patterns in DNA microarrays
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses an artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system. According to the technical scheme provided by the invention, the method comprises the following steps: the system comprises a model building module, a model verification module and a risk prediction module; the model building module is used for performing model training by using a first sample set based on the artificial intelligent weak supervision learning framework system to build a transfer risk prediction model; the model verification module is used for verifying the effectiveness of the transfer risk prediction model by using the second sample set; and the risk prediction module is used for carrying out nuclear DNA ploidy and chromatin structure typing analysis on the target sample according to the verified transfer risk model to obtain a prognosis analysis result. According to the invention, a TI-stage colorectal cancer lymph node metastasis risk prediction model can be established according to the existing case data, DNA ploidy, interstitial ratio and chromatin value calculation can be carried out on the current case sample by using the model, and the prognosis metastasis risk can be obtained by analysis.
Description
Technical Field
The invention relates to the field of intelligent medical treatment, in particular to an artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system, computing equipment and a computer storage medium.
Background
With the rapid development of artificial intelligence technology and deep learning technology, the application range of the technology in various industries is also expanding. The technology energy is truly applied to the fields of the industries through artificial intelligence and deep learning technology, and the development of the technology energy is greatly influenced. In the medical field, according to different symptoms, the artificial intelligence technology is utilized to analyze according to each pathological detection result of a patient, so that doctors are assisted in completing treatment, the workload of the doctors is greatly reduced, and the overall efficiency and accuracy of the diagnosis and treatment process are improved.
At present, the application of artificial intelligence technology in diagnosis and treatment of cancers is mostly to analyze the acquired pathological images to identify and diagnose the cancers. There are now non-small cell lung cancer, prostate cancer, stomach cancer, breast cancer, etc. For example, nicolas coudraw et al, university of new york medical school, uses deep learning to build a model for non-small cell lung cancer recognition.
Colorectal cancer is one of the most common cancers and the most main tumor death factors at present, and the radical surgery can well control the lymph node metastasis rate of the colorectal cancer, but has great influence on the postoperative life quality of patients; the damage to patients caused by the anal endoscopic microsurgery is small, but the local recurrence rate and the total recurrence rate are obviously higher than those of radical surgery. Therefore, there is a need to make analytical decisions regarding the risk of metastasis of patients. However, for prognosis effect and metastasis risk after excision operation, a doctor is still required to perform manual analysis and judgment based on pathological features of a patient and combined with related experience, and the process has huge workload and extremely low efficiency.
Disclosure of Invention
In order to solve the technical problems, the invention provides an artificial intelligence-based T1 colorectal cancer lymph node metastasis risk prediction system, and corresponding computing equipment and a computer storage medium.
According to one aspect of the present invention, there is provided an artificial intelligence based system for predicting risk of lymph node metastasis of colorectal cancer in T1 stage, comprising: the system comprises a model building module, a model verification module and a risk prediction module; wherein,
the model building module is used for performing model training by using the first sample set based on the artificial intelligence weak supervision learning framework system to build a transfer risk prediction model;
the model verification module is used for verifying the effectiveness of the transfer risk prediction model by using the second sample set;
and the risk prediction module is used for carrying out nuclear DNA ploidy and chromatin structure typing analysis on the target sample according to the verified transfer risk model to obtain a prognosis analysis result.
In the above solution, the model building module is further configured to:
generating a first sample set based on pathological features and follow-up results of cases in a preset time period stored in a pathological database, wherein the first sample set is divided into a first radical excision set and a first endoscopic excision set according to excision modes;
inputting the first radical excision set and the first endoscope excision set into an artificial intelligent weak supervision learning framework system for model training;
and establishing a transfer risk prediction model based on the training result.
In the above solution, the model building module is further configured to:
identifying first sections in the first sample set by utilizing the intestinal cancer diagnosis model, and determining an intestinal cancer area in each first section;
extracting a plurality of image blocks from each first slice, and calculating a plurality of image block scores by using a binary classification network;
a maximum value selected from the plurality of image block scores, defined as a first prognosis probability corresponding to the first slice;
performing data iteration on the first prognosis probability based on the first radical excision set and the first endoscope excision set to obtain a second prognosis probability, so that the second prognosis probability accords with an actual prognosis result; wherein the actual prognosis results are the prognosis results corresponding to the first slice in the first radical ablation set and the first endoscopic ablation set.
In the above solution, the risk prediction module is further configured to:
performing nuclear shadow collection and nuclear shadow classification on a second slice subjected to nuclear single-layer preparation and Fulgen staining in a target sample to obtain a nuclear single-layer image;
analyzing the cell nucleus monolayer image by using a DNA ploidy analysis system to generate an optical density histogram and obtain a DNA ploidy analysis result;
labeling tumor areas and analyzing the interstitial ratios of H & E stained tumor sections in a target sample, and determining the interstitial ratios in the tumor areas;
determining the pixel quantity of a single-layer image of the cell nucleus, carrying out regional grouping, carrying out traversing type pixel sampling according to different sampling window sizes for each cell nucleus, calculating the gray scale and entropy value of a central pixel of each sampling window, determining window values corresponding to sampling windows with different sizes, generating a 4-dimensional gray scale/entropy matrix array, and calculating to obtain a chromatin value of a corresponding sample;
comparing the first threshold value with the interstitial ratio, and determining an interstitial ratio analysis result according to the comparison result; comparing the second threshold value with the chromatin value, and determining a chromatin value analysis result according to the comparison result; and the DNA ploidy analysis result, the interstitial ratio analysis result and the chromatin value analysis result are used as prognosis analysis results of the T1 colorectal cancer lymph node metastasis risk together.
In the above scheme, the determining the pixel quantity of the cell nucleus single-layer image and performing region grouping, performing traversing pixel sampling according to different sampling window sizes for each cell nucleus, calculating the gray scale and entropy value of the central pixel of each sampling window, determining the window values corresponding to the sampling windows with different sizes, and generating a 4-dimensional gray scale/entropy matrix array further includes:
calculating the sum of gray scale/entropy coordinate systems according to the area of each group after the region grouping aiming at the sampling window of each size;
obtaining a window value of a sampling window with a corresponding size by using the cell nucleus number in a corresponding group at the sum of the gray level/entropy coordinate system;
and (3) carrying out aggregation according to window values corresponding to sampling windows of all sizes to generate a 4-dimensional gray scale/entropy matrix array.
In the above-mentioned scheme, the artificial intelligence-based T1 stage colorectal cancer lymph node metastasis risk prediction system further includes: a statistics evaluation module; wherein,
the statistical evaluation module is used for calculating the accuracy rate, the precision rate and the recall rate of the prognosis analysis results aiming at the plurality of target samples based on the plurality of prognosis analysis results obtained for the plurality of target samples; and drawing a receiver operation characteristic curve based on the accuracy rate, the precision rate and the recall rate, and calculating the area of the receiver operation characteristic curve to serve as a statistical evaluation index of the artificial intelligence-based T1 colorectal cancer lymph node metastasis risk prediction system.
In the above scheme, the system further comprises a rendering module; wherein, the rendering module is used for:
acquiring initial resolution, target resolution and texture data in a nuclear single-layer image;
and rendering the nuclear monolayer image based on the relation between the initial resolution and the target resolution of the nuclear monolayer image.
In the above scheme, the system further comprises a noise reduction module; wherein, the noise reduction module is used for:
converting the nuclear single-layer image into a gray image; noise detection is carried out on the gray level image;
generating a noise recognition matrix corresponding to the gray image matrix and a noise concentration matrix corresponding to the noise recognition matrix;
dividing the gray scale image into a plurality of regions; and sequentially performing diffusion traversal on each region, and simultaneously performing noise reduction treatment on noise pixels until the noise reduction treatment of the whole cell nucleus single-layer image is completed.
According to yet another aspect of the present invention, there is provided a computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations implemented by the artificial intelligence-based T1 stage colorectal cancer lymph node metastasis risk prediction system described above.
According to yet another aspect of the present invention, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations implemented by the artificial intelligence based T1 stage colorectal cancer lymph node metastasis risk prediction system as described above.
According to the technical scheme provided by the invention, the artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system comprises: the system comprises a model building module, a model verification module and a risk prediction module; the model building module is used for performing model training by using a first sample set based on the artificial intelligent weak supervision learning framework system to build a transfer risk prediction model; the model verification module is used for verifying the effectiveness of the transfer risk prediction model by using the second sample set; and the risk prediction module is used for carrying out nuclear DNA ploidy and chromatin structure typing analysis on the target sample according to the verified transfer risk model to obtain a prognosis analysis result. Training and verifying a T1 colorectal cancer lymph node metastasis risk prediction system through pathological data of a large number of past cases stored in a database, completing establishment of a metastasis risk prediction model, and then obtaining a nuclear single-layer image of a target sample by using the metastasis risk prediction model, so as to further obtain a DNA ploidy analysis result, a interstitial ratio analysis result and a chromatin value analysis result, and completing prognosis analysis. On the basis that the establishment process of the transfer risk prediction model is based on a large number of past case data, the accuracy of the result of prognosis analysis is guaranteed, so that medical staff can conveniently and rapidly determine whether the prognosis of a target case is good or bad according to the result of the prognosis analysis, and further scientifically select whether to perform radical surgery or endoscopic resection surgery.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 shows a block diagram of an artificial intelligence based system for predicting risk of metastasis to lymph node of colorectal cancer at stage T1 according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for establishing a model for predicting lymph node metastasis risk of colorectal cancer in stage T1 according to an embodiment of the present invention;
FIG. 3 shows a flow chart of a method for predicting risk of metastasis to a colorectal cancer lymph node based on a metastasis risk prediction model according to an embodiment of the present invention;
FIG. 4 shows a block diagram of an artificial intelligence based system for predicting risk of metastasis to lymph node of colorectal cancer at stage T1 according to another embodiment of the present invention;
FIG. 5 illustrates a schematic diagram of a computing device, according to one embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
FIG. 1 shows a block diagram of an artificial intelligence based system for predicting risk of metastasis to lymph node of colorectal cancer at stage T1 according to an embodiment of the present invention, the system comprising: a model creation module 101, a model verification module 102, and a risk prediction module 103; wherein,
the model building module 101 is configured to perform model training by using the first sample set based on the artificial intelligence weak supervision learning framework system, and build a transfer risk prediction model.
Specifically, the model building module 101 is further configured to execute a method for building a model for predicting lymph node metastasis risk of T1 stage colorectal cancer, and fig. 2 is a schematic flow chart of a method for building a model for predicting lymph node metastasis risk of T1 stage colorectal cancer according to an embodiment of the present invention, as shown in fig. 2, and includes the following steps:
step S201, a first sample set is generated based on pathological features of cases in a preset time period and follow-up results stored in a pathological database, wherein the first sample set is divided into a first radical excision set and a first endoscopic excision set according to excision modes.
Preferably, the first sample set uses pathological data of colorectal cancer cases of 1 st 1999 to 12 nd 2017, wherein the first radical resection set uses 500 radical resections among the above cases, and the first endoscopic resection set uses 100 endoscopic resections among the above cases.
Step S202, inputting the first radical excision set and the first endoscope excision set into an artificial intelligent weak supervision learning framework system for model training.
Specifically, based on an artificial intelligence weakly supervised learning framework system, the pathological features and follow-up results in the first sample set are analyzed, and model training is completed by using a Multi-instance learning method (Multi-Instance Learning, MILs).
Specifically, identifying first sections in the first sample set by using a intestinal cancer diagnosis model, and determining an intestinal cancer region in each first section;
extracting a plurality of image blocks from each first slice, and calculating a plurality of image block scores by using a binary classification network;
a maximum value selected from the plurality of image block scores, defined as a first prognosis probability corresponding to the first slice;
performing data iteration on the first prognosis probability based on the first radical excision set and the first endoscope excision set to obtain a second prognosis probability, so that the second prognosis probability accords with an actual prognosis result; wherein the actual prognosis results are the prognosis results corresponding to the first slice in the first radical ablation set and the first endoscopic ablation set.
Preferably, both the first prognosis probability and the second prognosis probability are used to characterize the poor prognosis corresponding to the first cut (usually understood as the poor prognosis of disease progression, whereas in the context of cancer, usually comprising a low likelihood of cure and a high likelihood of metastasis).
Step S203, a transfer risk prediction model is established based on the training result.
The model verification module 102 is configured to perform performance verification on the transfer risk prediction model using the second sample set.
Preferably, the second sample set uses pathology data of colorectal cancer cases of 2018, 1-2021, 10, wherein 150 cases are radical resected and 50 cases are endoscopic resected.
The risk prediction module 103 is configured to perform analysis on nuclear DNA ploidy and chromatin structure typing on the target sample according to the verified transfer risk model, so as to obtain a prognosis analysis result.
According to the technical scheme provided by the embodiment, the artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system comprises: the system comprises a model building module, a model verification module and a risk prediction module; the model building module is used for performing model training by using a first sample set based on the artificial intelligent weak supervision learning framework system to build a transfer risk prediction model; the model verification module is used for verifying the effectiveness of the transfer risk prediction model by using the second sample set; and the risk prediction module is used for carrying out nuclear DNA ploidy and chromatin structure typing analysis on the target sample according to the verified transfer risk model to obtain a prognosis analysis result. The pathological data of the existing cases are used as a training set and a verification set, the image block score is calculated by extracting the image blocks from the slices to obtain the probability of poor prognosis, and data iteration is performed, so that the heterogeneity of tumors is fully considered in the establishment process of the metastasis risk prediction model, and the prediction process of the finally obtained metastasis risk prediction system is more scientific and accurate. After the transfer risk prediction model is established, a nuclear single-layer image of the target sample is obtained by using the transfer risk prediction model, so that a DNA ploidy analysis result, a interstitial ratio analysis result and a chromatin value analysis result are further obtained, and prognosis analysis is completed. Medical staff can conveniently determine that the prognosis of a target case is better or worse according to the result of prognosis analysis, so that radical surgery or endoscopic resection surgery can be selected more scientifically, and in the whole, the cure rate of a patient is guaranteed, the influence on the postoperative life of the patient is considered, the workload of medical staff is effectively reduced, the diagnosis and treatment efficiency and the pertinence of treatment method selection are greatly improved, and the treatment effect on the patient is further improved.
Fig. 3 shows a flow chart of a colorectal cancer lymph node metastasis risk prediction method based on a metastasis risk prediction model according to an embodiment of the present invention, as shown in fig. 3, the method includes the steps of:
step S301, nuclear shadow collection and nuclear shadow classification are carried out on a second slice which is subjected to nuclear single-layer preparation and Fulgen staining in a target sample, and a nuclear single-layer image is obtained.
Preferably, 300 cases of radical excision cases of 1 month to 2016 month and 100 cases of endoscopic excision cases are adopted, the cases are grouped according to lymph node metastasis characteristics, the differences of tumor DNA ploidy, tumor interstitial ratio and tumor cell nucleus configuration in two excision modes are detected, and further training is carried out on a metastasis risk prediction model; and 300 cases of radical excision cases and endoscopic excision cases from 1 month in 2017 to 12 months in 2020 are taken as verification sets for model efficacy verification.
The nuclear monolayer preparation and the Fulgen staining were treated in a conventional manner and will not be further described herein.
Preferably, the nuclear single layer image is acquired in a nuclear shadow-based digital cytopathology platform. The method comprises the steps of performing spiral continuous scanning and image acquisition on a target sample through a nuclear shadow collector (PWS scanner) until a digital image of a single-layer cell nucleus of the whole sample is obtained, and completing nuclear shadow acquisition; the nuclei to be analyzed in the image are automatically identified as five types of epithelial nuclei (epithelial neclei), lymphocytes (lymphocytes), plasmacytes (plasmacytes), stroma cells (stroma cells), and disqualified nuclei (exempt nuclei) by a nuclear shadow classifier (PWS classifier), and further analysis is performed by the nuclear shadow classifier to verify the accuracy of the classified nuclei.
Step S302, analyzing the cell nucleus monolayer image by using a DNA ploidy analysis system to generate an optical density histogram and obtain a DNA ploidy analysis result.
Preferably, the optical density value of the optical density histogram is 10D.
Step S303, labeling tumor areas and analyzing the interstitial ratios of H & E stained tumor sections in the target samples, and determining the interstitial ratios in the tumor areas.
Preferably, in the target sample, a representative H & E stained tumor section is selected, scanned through a 40-fold lens, at a resolution of 0.23 μm per pixel. And marking the tumor area on the scanned image by using the interstitial ratio analysis software, and calculating the interstitial ratio of the tumor area.
Step S304, determining the pixel quantity of the cell nucleus single-layer image, carrying out region grouping, carrying out traversing pixel sampling according to different sampling window sizes for each cell nucleus, calculating the gray scale and entropy value of the central pixel of each sampling window, determining the window values corresponding to the sampling windows with different sizes, generating a 4-dimensional gray scale/entropy matrix array, and calculating to obtain the chromatin value of the corresponding sample.
Specifically, for each size sampling window, calculating the sum of gray scale/entropy coordinate systems according to the area of each group after the region grouping;
obtaining a window value of a sampling window with a corresponding size by using the cell nucleus number in a corresponding group at the sum of the gray level/entropy coordinate system;
and (3) carrying out aggregation according to window values corresponding to sampling windows of all sizes to generate a 4-dimensional gray scale/entropy matrix array.
Preferably, the nuclear single layer images are divided into 11 groups. The texture of each nucleus in each group was analyzed using a gray/entropy system array. Taking each cell nucleus as a unit, adopting a sampling window with the size of 3*3, taking the center of a pixel at the upper left corner of an image as a starting sampling window, extracting the pixel at the center of the window, and calculating the gray value and the entropy value of the pixel. And then carrying out gray value and entropy value calculation on each pixel of the cell nucleus image in turn, and further calculating to obtain the sum of gray/entropy coordinate systems corresponding to each group of cell nuclei. Dividing the sum of the gray/entropy coordinates by the number of nuclei in the set yields the window value of the 3*3 sampling window. The window values for each odd-sized sampling window are then computed in turn (e.g., from 3*3, 5*5, 7*7, 9*9 … … 31 ×31). And (3) collecting sampling window values of all the sizes to obtain a 4-dimensional gray level/entropy matrix array of the target sample, and obtaining a chromatin value of the corresponding sample based on GLEM-4D (Graph and Language Learning by Expectation Maximization, text graph training frame).
Step S305, comparing the first threshold value with the interstitial ratio, and determining an interstitial ratio analysis result according to the comparison result; comparing the second threshold value with the chromatin value, and determining a chromatin value analysis result according to the comparison result; and the DNA ploidy analysis result, the interstitial ratio analysis result and the chromatin value analysis result are used as prognosis analysis results of the T1 colorectal cancer lymph node metastasis risk together.
In particular, since the tumor stroma plays an important role in the tumor growth, proliferation, infiltration and metastasis processes, the high or low of the stroma ratio can characterize the high or low of the risk of prognosis metastasis. When the interstitial ratio is less than or equal to a first threshold, the prognosis is considered to be better; when the interstitial ratio > the first threshold, the prognosis may be considered as poor. When the chromatin value is greater than or equal to a second threshold, the prognosis is considered to be good; when the chromatin value < the second threshold value, the prognosis is considered to be poor. The appearance of polyploids was analyzed based on the value of the DNA index (DI, DNAindex) in the DNA ploidy analysis results. And comprehensively obtaining a prognosis analysis result of the lymph node metastasis risk of the colorectal cancer in the T1 stage according to the results of the three analyses.
Preferably, the first threshold is 50%; the second threshold is 0.044.
According to the method, three indexes of DNA ploidy, interstitial ratio and chromatin value, which are related to tumor prognosis and recurrence and metastasis, can be obtained and analyzed, and according to the results of the three indexes, the comprehensive analysis of the prognosis of the target sample is carried out, so that the working efficiency and the prediction accuracy are greatly improved, and doctors can be more scientifically and effectively guided to carry out next diagnosis and treatment on patients.
Fig. 4 shows a block diagram of a system for predicting lymph node metastasis risk of T1 colorectal cancer based on artificial intelligence according to another embodiment of the present invention, the system comprising: a model building module 401, a model verification module 402, a risk prediction module 403, a statistical evaluation module 404, a rendering module 405, and a noise reduction module 406; wherein,
the functions of the model building module 401, the model verification module 402, and the risk prediction module 403 are described above, and are not described in detail herein.
The statistical evaluation module 404 is configured to calculate an accuracy rate, an precision rate, and a recall rate of the prognostic analysis results for the plurality of target samples based on the plurality of prognostic analysis results obtained for the plurality of target samples; and drawing a receiver operation characteristic curve based on the accuracy rate, the precision rate and the recall rate, and calculating the area of the receiver operation characteristic curve to serve as a statistical evaluation index of the artificial intelligence-based T1 colorectal cancer lymph node metastasis risk prediction system.
Preferably, the accuracy (a) formula is a= (tp+tn)/(tp+fp+fn+tn); the ratio of the number of correctly classified samples to the total number of samples is characterized. Wherein TP is True Positive (True Positive); TN is True Negative (True Negative); FP is False Positive (False Positive); FN is False Negative (False Negative);
further, TP represents the number of correctly retrieved samples, (tp+fp) represents the number of actually retrieved samples, and (tp+fn) represents the number of samples that should be retrieved.
The formula of the precision (P) is p=tp/(tp+fp), which characterizes the proportion of the number of correctly retrieved samples TP "to all the" number of actually retrieved samples (tp+fp) ".
The formula of the recall (R) is r=tp/(tp+fn), which characterizes the proportion of all "correctly retrieved samples TP" to all "samples (tp+fn) that should be retrieved".
Preferably, a receiver operation characteristic Curve (receiver operating characteristic, ROC) is drawn based on the accuracy, precision and recall, and the Area (Area opening Curve, AUC) of the ROC Curve is calculated as a statistical evaluation index of an artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system, which reflects the sensitivity and specificity of the system.
A rendering module 405, configured to obtain initial resolution, target resolution, and texture data in the nuclear single-layer image; and rendering the nuclear monolayer image based on the relation between the initial resolution and the target resolution of the nuclear monolayer image.
The noise reduction module 406 is configured to convert the nuclear single-layer image into a gray image; noise detection is carried out on the gray level image; generating a noise recognition matrix corresponding to the gray image matrix and a noise concentration matrix corresponding to the noise recognition matrix; dividing the gray scale image into a plurality of regions; and sequentially performing diffusion traversal on each region, and simultaneously performing noise reduction treatment on noise pixels until the noise reduction treatment of the whole cell nucleus single-layer image is completed.
According to the system, the statistical analysis can be performed on the completed prediction result through the statistical evaluation module, the sensitivity and the specificity of the system are scientifically reflected based on the calculated AUC, the index is helpful for judging whether the system needs to be updated or optimized, and meanwhile, medical workers are helped to reasonably utilize the prognosis analysis result obtained by the system, and the diagnosis and treatment accuracy is improved. The image resolution in the sample is insufficient by the rendering module, so that the image is rendered to improve the resolution; and carrying out noise identification on the cell nucleus single-layer image through a noise reduction module and completing noise reduction. Based on the rendering module and the noise reduction module, the definition of the image can be improved, the accuracy of the system in training, verifying and predicting can be improved, and the scientificity and rationality of a doctor in diagnosis and treatment can be indirectly improved.
The invention also provides a nonvolatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the executable instruction can execute the operation implemented by the artificial intelligence-based T1 colorectal cancer lymph node metastasis risk prediction system in any method embodiment.
FIG. 5 illustrates a schematic diagram of a computing device, according to an embodiment of the invention, the particular embodiment of the invention not being limited to a particular implementation of the computing device.
As shown in fig. 5, the computing device may include: a processor 502, a communication interface (Communications Interface) 504, a memory 506, and a communication bus 508.
Wherein:
processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508.
A communication interface 504 for communicating with network elements of other devices, such as clients or other servers.
The processor 502 is configured to execute the program 510, and may specifically perform relevant steps implemented in the embodiment of the artificial intelligence-based T1 stage colorectal cancer lymph node metastasis risk prediction system.
In particular, program 510 may include program code including computer-operating instructions.
The processor 502 may be a central processing unit CPU, or a specific integrated circuit ASIC (Applica tion Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
A memory 506 for storing a program 510. Memory 506 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Program 510 may be specifically configured to cause processor 502 to execute the artificial intelligence based T1 stage colorectal cancer lymph node metastasis risk prediction system in any of the embodiments described above. The specific implementation of each step in the procedure 510 may refer to the corresponding descriptions in the corresponding steps and units implemented in the embodiment of the artificial intelligence-based T1 stage colorectal cancer lymph node metastasis risk prediction system, which are not described herein. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and modules described above may refer to corresponding procedure descriptions in the foregoing method embodiments, which are not repeated herein.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in accordance with embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. An artificial intelligence-based T1 stage colorectal cancer lymph node metastasis risk prediction system, comprising: the system comprises a model building module, a model verification module and a risk prediction module; wherein,
the model building module is used for performing model training by using the first sample set based on the artificial intelligence weak supervision learning framework system to build a transfer risk prediction model;
the model verification module is used for verifying the effectiveness of the transfer risk prediction model by using the second sample set;
and the risk prediction module is used for carrying out nuclear DNA ploidy and chromatin structure typing analysis on the target sample according to the verified transfer risk model to obtain a prognosis analysis result.
2. The system of claim 1, wherein the modeling module is further configured to:
generating a first sample set based on pathological features and follow-up results of cases in a preset time period stored in a pathological database, wherein the first sample set is divided into a first radical excision set and a first endoscopic excision set according to excision modes;
inputting the first radical excision set and the first endoscope excision set into an artificial intelligent weak supervision learning framework system for model training;
and establishing a transfer risk prediction model based on the training result.
3. The system of claim 2, wherein the modeling module is further configured to:
identifying first sections in the first sample set by utilizing the intestinal cancer diagnosis model, and determining an intestinal cancer area in each first section;
extracting a plurality of image blocks from each first slice, and calculating a plurality of image block scores by using a binary classification network;
a maximum value selected from the plurality of image block scores, defined as a first prognosis probability corresponding to the first slice;
performing data iteration on the first prognosis probability based on the first radical excision set and the first endoscope excision set to obtain a second prognosis probability, so that the second prognosis probability accords with an actual prognosis result; wherein the actual prognosis results are the prognosis results corresponding to the first slice in the first radical ablation set and the first endoscopic ablation set.
4. The system of claim 1, wherein the risk prediction module is further configured to:
performing nuclear shadow collection and nuclear shadow classification on a second slice subjected to nuclear single-layer preparation and Fulgen staining in a target sample to obtain a nuclear single-layer image;
analyzing the cell nucleus monolayer image by using a DNA ploidy analysis system to generate an optical density histogram and obtain a DNA ploidy analysis result;
labeling tumor areas and analyzing the interstitial ratios of H & E stained tumor sections in a target sample, and determining the interstitial ratios in the tumor areas;
determining the pixel quantity of a single-layer image of the cell nucleus, carrying out regional grouping, carrying out traversing type pixel sampling according to different sampling window sizes for each cell nucleus, calculating the gray scale and entropy value of a central pixel of each sampling window, determining window values corresponding to sampling windows with different sizes, generating a 4-dimensional gray scale/entropy matrix array, and calculating to obtain a chromatin value of a corresponding sample;
comparing the first threshold value with the interstitial ratio, and determining an interstitial ratio analysis result according to the comparison result; comparing the second threshold value with the chromatin value, and determining a chromatin value analysis result according to the comparison result; and the DNA ploidy analysis result, the interstitial ratio analysis result and the chromatin value analysis result are used as prognosis analysis results of the T1 colorectal cancer lymph node metastasis risk together.
5. The system of claim 4, wherein determining the number of pixels of the single-layer image of nuclei and performing region grouping, performing traversing pixel sampling according to different sampling window sizes for each nucleus, calculating gray scale and entropy values of a central pixel of each sampling window, and determining window values corresponding to sampling windows of different sizes, generating a 4-dimensional gray scale/entropy matrix array, further comprises:
calculating the sum of gray scale/entropy coordinate systems according to the area of each group after the region grouping aiming at the sampling window of each size;
obtaining a window value of a sampling window with a corresponding size by using the cell nucleus number in a corresponding group at the sum of the gray level/entropy coordinate system;
and (3) carrying out aggregation according to window values corresponding to sampling windows of all sizes to generate a 4-dimensional gray scale/entropy matrix array.
6. The system of any one of claims 1-4, wherein the artificial intelligence based T1 stage colorectal cancer lymph node metastasis risk prediction system further comprises: a statistics evaluation module; wherein,
the statistical evaluation module is used for calculating the accuracy rate, the precision rate and the recall rate of the prognosis analysis results aiming at the plurality of target samples based on the plurality of prognosis analysis results obtained for the plurality of target samples; and drawing a receiver operation characteristic curve based on the accuracy rate, the precision rate and the recall rate, and calculating the area of the receiver operation characteristic curve to serve as a statistical evaluation index of the artificial intelligence-based T1 colorectal cancer lymph node metastasis risk prediction system.
7. The system of claim 1 or 4, further comprising, a rendering module; wherein, the rendering module is used for:
acquiring initial resolution, target resolution and texture data in a nuclear single-layer image;
and rendering the nuclear monolayer image based on the relation between the initial resolution and the target resolution of the nuclear monolayer image.
8. The system of claim 1 or 4, further comprising a noise reduction module; wherein, the noise reduction module is used for:
converting the nuclear single-layer image into a gray image; noise detection is carried out on the gray level image;
generating a noise recognition matrix corresponding to the gray image matrix and a noise concentration matrix corresponding to the noise recognition matrix;
dividing the gray scale image into a plurality of regions; and sequentially performing diffusion traversal on each region, and simultaneously performing noise reduction treatment on noise pixels until the noise reduction treatment of the whole cell nucleus single-layer image is completed.
9. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the functions corresponding to the artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system according to any one of claims 1 to 7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform the functionality corresponding to the artificial intelligence based T1 stage colorectal cancer lymph node metastasis risk prediction system of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311568162.0A CN117611543A (en) | 2023-11-22 | 2023-11-22 | Artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311568162.0A CN117611543A (en) | 2023-11-22 | 2023-11-22 | Artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117611543A true CN117611543A (en) | 2024-02-27 |
Family
ID=89949055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311568162.0A Pending CN117611543A (en) | 2023-11-22 | 2023-11-22 | Artificial intelligence-based T1-stage colorectal cancer lymph node metastasis risk prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117611543A (en) |
-
2023
- 2023-11-22 CN CN202311568162.0A patent/CN117611543A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111127466B (en) | Medical image detection method, device, equipment and storage medium | |
| CN108564026B (en) | Network construction method and system for thyroid tumor cytology smear image classification | |
| CN108464840B (en) | Automatic detection method and system for breast lumps | |
| CN108564123B (en) | Thyroid tumor cytology smear image classification method and device | |
| CN111524137B (en) | Cell identification counting method and device based on image identification and computer equipment | |
| CN111488921B (en) | Intelligent analysis system and method for panoramic digital pathological image | |
| CN110807764A (en) | Lung cancer screening method based on neural network | |
| CN109903282B (en) | Cell counting method, system, device and storage medium | |
| CN105809175B (en) | Cerebral edema segmentation method and system based on support vector machine algorithm | |
| Nateghi et al. | A deep learning approach for mitosis detection: application in tumor proliferation prediction from whole slide images | |
| Ström et al. | Pathologist-level grading of prostate biopsies with artificial intelligence | |
| CN112990214A (en) | Medical image feature recognition prediction model | |
| JP2023543044A (en) | Method of processing images of tissue and system for processing images of tissue | |
| CN114445356A (en) | Multi-resolution-based full-field pathological section image tumor rapid positioning method | |
| CN111047559B (en) | Method for rapidly detecting abnormal area of digital pathological section | |
| CN116167964A (en) | Tumor classification method and system based on tumor hyperspectral image | |
| WO2023014789A1 (en) | System and method for pathology image analysis using a trained neural network and active learning framework | |
| Nguyen et al. | An effective deep learning architecture combination for tissue microarray spots classification of h&e stained colorectal images | |
| CN111814893A (en) | Lung full-scan image EGFR mutation prediction method and system based on deep learning | |
| CN112703531A (en) | Generating annotation data for tissue images | |
| CN113435469A (en) | Kidney tumor enhanced CT image automatic identification system based on deep learning and training method thereof | |
| Chauhan et al. | Exploring genetic-histologic relationships in breast cancer | |
| CN112801940A (en) | Model evaluation method, device, equipment and medium | |
| CN115631387B (en) | Method and device for predicting lung cancer pathology high-risk factor based on graph convolution neural network | |
| CN116229176A (en) | Medical image classification method and device combining image histology characteristics and clinical characteristics |
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 |