CN115188477A - Method, system and device for prognosis prediction after liver cancer liver transplantation - Google Patents
Method, system and device for prognosis prediction after liver cancer liver transplantation Download PDFInfo
- Publication number
- CN115188477A CN115188477A CN202210917359.XA CN202210917359A CN115188477A CN 115188477 A CN115188477 A CN 115188477A CN 202210917359 A CN202210917359 A CN 202210917359A CN 115188477 A CN115188477 A CN 115188477A
- Authority
- CN
- China
- Prior art keywords
- liver
- image
- inputting
- information
- prognosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G16H50/30—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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T7/0004—Industrial 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
- G06V10/70—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
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the specification provides a method, a system and a device for predicting prognosis of liver cancer after liver transplantation based on deep learning, wherein the method comprises the following steps: acquiring anterior abdominal enhanced CT, identity information, clinical hematology indexes, abdominal operation history, HBV-DNA, complications, postoperative pathological results and postoperative survival information of a hepatic malignant tumor patient and a hepatic benign occupying patient to obtain a data set; dividing a data set into a training set and a testing set, acquiring a front abdominal part enhanced CT (computed tomography) containing a liver fault, segmenting the screened front abdominal part enhanced CT through a U-net network image to obtain a liver image, removing environmental noise interference, and inputting the liver image into a ResNet34 network to obtain a vector containing liver CT information; and substituting the clinical hematological indexes into an XGboost machine learning model to perform first-step prediction to obtain a prediction value of prognosis judgment based on the clinical hematological indexes, substituting the prediction value and the prediction value into an MLP (Multi-level Likefulness) model, and marking the relevant information of the patient prognosis condition again to obtain a final prediction value.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, a system, and an apparatus for predicting prognosis after liver cancer liver transplantation based on deep learning.
Background
Primary liver cancer is the 4 th common malignant tumor in China at present, and seriously threatens the life and health of people in China. The liver transplantation is the only effective treatment means for the end-stage liver diseases, along with the continuous progress of the operation technology, the application and management concept and method of the postoperative immunosuppressant are continuously improved, the early survival rate of the patients is obviously improved, and the side effects of the postoperative rejection and the immunosuppressant, such as opportunistic infection, malignant tumor, metabolic diseases and the like, become the main threats facing the long-term survival of the transplanted patients and the transplanted objects. The postoperative recurrence risk and survival prediction of the liver cancer are related to the postoperative life health and the later life health of patients, a lot of guidance is provided for the treatment of clinical patients through the related research of machine deep learning, and the constructed prediction model is primarily applied in clinic.
In the prior art, an ANN and an LR are used for establishing a patient postoperative survival prediction model of early HCC radical resection, the ANNS is found to be higher than the AUC of other models, in addition, 7919 cases of liver cancer patients are analyzed and reported, and the accuracy of BooXSt is the highest when a recurrence prediction model of liver cancer radical resection is established by using algorithms such as Cox regression, deep learning, random survival forest, extreme gradient and the like. Currently, in the research aiming at the prediction after liver cancer liver transplantation, there is no relevant research for predicting the prognosis condition of patients based on deep learning CNN combined with clinical hematological indexes. In addition, the existing prediction system for liver cancer liver transplantation prognosis comprises prediction based on assay indexes and a convolutional neural network prediction model based on imaging examination, but the independent application of the two methods cannot always give consideration to index change in peripheral blood of patients and difference of liver tumors.
Disclosure of Invention
The invention aims to provide a method, a system and a device for predicting prognosis of liver cancer after liver transplantation based on deep learning, and aims to solve the problems in the prior art.
The invention provides a prognosis prediction method after liver cancer liver transplantation based on deep learning, which comprises the following steps:
acquiring the foreabdomen enhanced CT, the identity information, the clinical hematology index, the abdominal operation history, the HBV-DNA, the complications, the postoperative pathological result and the postoperative survival condition information of a liver malignant tumor patient and a liver benign space occupying patient to obtain a data set;
dividing the data set into a training set and a testing set, acquiring a forebelly enhanced CT (computed tomography) containing a liver fault, which is pre-screened by a doctor in the training set, segmenting the screened forebelly enhanced CT through a U-net network image to obtain a liver image, removing the interference of environmental noise, and inputting the obtained liver image into a ResNet34 network to obtain a vector containing liver CT information;
and substituting the clinical hematology indexes into an XGboost machine learning model to carry out first-step prediction to obtain a prediction value of prognosis judgment based on the clinical hematology indexes, substituting the clinical hematology indexes and the prediction value into an MLP (Multi-level medical processing) model, and marking the relevant information of the patient prognosis condition again to obtain a final prediction value.
The invention provides a prognosis prediction system after liver cancer liver transplantation based on deep learning, which comprises the following steps:
the acquisition module is used for acquiring the foreabdomen enhanced CT, the identity information, the clinical hematology index, the abdominal operation history, the HBV-DNA, the complications, the postoperative pathological result and the postoperative survival condition information of a hepatic malignant tumor patient and a hepatic benign occupying patient to obtain a data set;
the processing module is used for dividing the data set into a training set and a testing set, acquiring the forebelly enhanced CT which is pre-screened by a doctor in the training set and contains a liver fault, segmenting the screened forebelly enhanced CT through a U-net network image to obtain a liver image, removing the interference of environmental noise, and inputting the obtained liver image into a ResNet34 network to obtain a vector containing liver CT information;
and the prediction module is used for substituting the clinical hematological index into the XGboost machine learning model to perform first-step prediction to obtain a prediction value for prognosis judgment based on the clinical hematological index, substituting the clinical hematological index and the prediction value into the MLP model, and marking the relevant information of the patient prognosis condition again to obtain a final prediction value.
The embodiment of the invention also provides a prognosis prediction device after liver cancer liver transplantation based on deep learning, which comprises: the device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the computer program realizes the steps of the liver cancer liver transplantation postoperative prognosis prediction method based on deep learning when being executed by the processor.
The embodiment of the invention also provides a computer readable storage medium, wherein an implementation program for information transmission is stored on the computer readable storage medium, and when the implementation program is executed by a processor, the steps of the prognosis prediction method after liver cancer liver transplantation based on deep learning are implemented.
By adopting the embodiment of the invention, the MLP multilayer perception network is used for jointly analyzing the MLP multilayer perception network and the MLP multilayer perception network, so that the comprehensive analysis of the liver transplantation patients is further enhanced.
Drawings
In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and that other drawings can be obtained by those skilled in the art without inventive exercise.
FIG. 1 is a flowchart illustrating a method for predicting prognosis of liver cancer after liver transplantation based on deep learning according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a method for predicting prognosis of liver cancer after liver transplantation based on deep learning according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a prognosis prediction system for liver cancer after liver transplantation based on deep learning according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a prognosis prediction apparatus for liver cancer after liver transplantation based on deep learning according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments described herein without making any inventive step shall fall within the scope of protection of this document.
Method embodiment
According to an embodiment of the present invention, a method for predicting prognosis after liver cancer liver transplantation based on deep learning is provided, fig. 1 is a flowchart of the method for predicting prognosis after liver cancer liver transplantation based on deep learning according to the embodiment of the present invention, and as shown in fig. 1, the method for predicting prognosis after liver cancer transplantation based on deep learning according to the embodiment of the present invention specifically includes:
step 101, acquiring anterior abdominal enhanced CT, identity information, clinical hematology indexes, abdominal operation history, HBV-DNA, complications, postoperative pathological results and postoperative survival information of a hepatic malignant tumor patient and a hepatic benign occupying patient to obtain a data set; the identity information specifically includes: gender, age, and MBI. The clinical hematological indexes specifically comprise: PNI, NLR, hemoglobin, platelets, albumin, TBIL, ALP, γ GT, AST, ALT, and blood glucose.
102, dividing the data set into a training set and a test set, acquiring a front abdominal enhanced CT (computed tomography) which is pre-screened by a doctor in the training set and contains a liver fault, segmenting the screened front abdominal enhanced CT through a U-net network image to obtain a liver image, removing the interference of environmental noise, and inputting the obtained liver image into a ResNet34 network to obtain a vector containing liver CT information;
and 103, substituting the clinical hematological indexes into an XGboost machine learning model to perform first-step prediction to obtain a predicted value of prognosis judgment based on the clinical hematological indexes, substituting the clinical hematological indexes and the predicted value into an MLP model, and marking relevant information of patient prognosis conditions again to obtain a final predicted value.
Step 103 specifically comprises:
inputting the obtained liver image into a ResNet34 network, firstly carrying out 64 convolution kernels of 7 × 7, and then pooling through a convolution kernel of 3 × 3;
using 64 convolution kernels of 7 × 7 in a conv1 layer, reducing the dimension of a color image with the size of 224 × 224 to 112 × 112 with the step size of 2, and then performing maximum pooling of 3 × 3 with the step size of 2 to further reduce the dimension to 56 × 56;
inputting a conv2 layer consisting of 3 residual learning modules, wherein each residual learning module consists of two convolution layers, the convolution kernel size is 3 multiplied by 3, and 64 channels are formed;
inputting a conv3 layer consisting of 4 residual learning modules, and adjusting the step size to be 2 at a certain convolution layer of the conv3_1 so as to reduce the output dimension of the conv3_4 to 28 multiplied by 28;
inputting a conv4 layer consisting of 6 residual learning modules, adjusting the step size to be 2 at a certain convolution layer in the conv4, and reducing the output dimension of the conv4 to 14 multiplied by 14;
inputting a conv5 layer consisting of 3 residual learning modules, adjusting the step length to 2 in conv5, and finally outputting a liver CT image with 7 multiplied by 7 dimensions; finally, through a full connection layer, the data is output to 1000 classes to obtain the vector containing the patient liver enhanced CT information.
Compared with the MLP, the CNN takes the matrix as input, avoids the loss of two-dimensional information (focus space information or position information), uses more sparse interconnected hierarchies, reduces information overfitting, and shows more obvious advantages in image recognition. The machine learning model can perform feature importance measurement, but has a large gap with a neural network when processing image information. Therefore, the XGboost-MLP-based prediction model constructed by combining the advantages of the machine learning model and the advantages of the neural network models (ANN and CNN) has a better prediction effect.
The above-described technical solutions of the embodiments of the present invention are exemplified below.
Data acquisition: 200 patients with liver malignant tumor and 100 patients with liver benign space occupation in 2011-2020 are selected from a certain hospital, and preoperative abdominal enhancement CT, sex, age, BMI, PNI, NLR, hemoglobin, platelets, albumin, TBIL, ALP, gamma GT, AST, ALT, blood sugar, abdominal operation history, HBV-DNA, complications, postoperative pathological results and postoperative survival conditions of 1 year and 3 years are obtained.
Data processing: 300 patients were treated as per 5: dividing the image into a training set and a testing set, screening out a liver fault from an abdomen enhanced CT image by a doctor, obtaining a liver image by segmenting the liver image through a U-net network image, and inputting the obtained liver image into a ResNet34 network after removing the environmental noise interference to obtain a vector containing CT information: substituting clinical hematology indexes into machine learning models such as XGboost and the like to carry out first-step prediction to obtain a prediction value of prognosis judgment based on the hematology indexes; and substituting the two parts into an MLP model, and marking the relevant information of the patient prognosis condition again to obtain the final predicted value.
The following detailed description of the specific operation scheme is made with reference to the flowchart, as shown in fig. 2:
1. data acquisition: 200 patients with liver malignant tumor and 100 patients with liver benign space occupation in 2011-2020 of a certain hospital are selected to obtain preoperative abdominal enhancement CT, sex, age, BMI, PNI, NLR, hemoglobin, platelet, albumin, TBIL, ALP, gamma GT, AST, ALT, blood sugar, abdominal operation history, HBV-DNA, complications, postoperative pathological results and postoperative survival conditions for 1 year and 3 years.
2. Data processing: 300 patients were treated as per 5:1, dividing the image into a training set and a test set, screening out a liver fault from an abdomen enhanced CT image by a doctor, segmenting the liver image through a U-net network image to obtain a liver image, and inputting the obtained liver image into a ResNet34 network after environmental noise interference is removed to obtain a vector containing CT information: and (3) CT image deep learning, namely inputting the obtained liver image into a ResNet34 network, firstly performing 64 convolution kernels of 7 × 7, and then performing pooling through a convolution kernel of 3 × 3. Using 64 convolution kernels of 7 × 7 at the conv1 level, with a step size of 2, the color image of size 224 × 224 is reduced to 112 × 112. Then 3 × 3 maximum pooling is performed with step size of 2, further reducing the dimensionality to 56 × 56, and then 3 residual learning modules, each consisting of two convolution layers with convolution kernel size of 3 × 3, 64 channels. The conv3 layer is composed of 4 residual learning modules, and in a certain convolution layer of the conv3_1, the step size needs to be adjusted to 2, so that the output dimension of the conv3_4 is reduced to 28 × 28. And then, passing through conv4 composed of 6 residual learning modules, and similarly, adjusting the step size to 2 at a certain convolution layer in conv4, thereby reducing the output dimension of conv4 to 14 × 14. The method consists of 3 residual learning modules, the step size is adjusted to 2 in conv5, and finally a 7 x 7 dimensional liver CT image is output. Finally, through a full connection layer, the data is output to 1000 classes to obtain the vector containing the patient liver enhanced CT information.
3. ANN model integration: substituting the clinical hematology index into a machine learning model such as XGboost and the like to carry out first-step prediction to obtain a prediction value of prognosis judgment based on the hematology index; and substituting the two parts into an MLP model, and marking the relevant information of the patient prognosis condition again to obtain the final predicted value.
In summary, by adopting the technical scheme of the embodiment of the invention, the existing organ allocation policy is optimized, and currently, in most regions of the world, the gold standard for prioritizing the patients to be transplanted is still the end-stage liver disease model, but the allocation policy based on the principle of 'priority of patients with severe disease' has certain defects, and the invention has reference value for reducing the risk of graft loss to a greater extent and improving the possibility of graft survival. The early attention is paid to possible complications in the clinical diagnosis and treatment process, early intervention is performed, the postoperative life quality of a patient is improved to the maximum extent, the system can be carried on a computer or a smart phone terminal, the use of a clinician is facilitated, the condition of the patient is judged in the early stage, and a more targeted treatment scheme is provided.
System embodiment
According to an embodiment of the present invention, a prognosis prediction system after liver cancer liver transplantation based on deep learning is provided, fig. 3 is a schematic diagram of the prognosis prediction system after liver cancer liver transplantation based on deep learning according to an embodiment of the present invention, and as shown in fig. 3, the prognosis prediction system after liver cancer transplantation based on deep learning according to an embodiment of the present invention specifically includes:
an obtaining module 30, configured to obtain foreabdomen enhanced CT, identity information, clinical hematological index, history of abdominal operation, HBV-DNA, complications, postoperative pathological result, and postoperative survival information of a liver malignant tumor patient and a liver benign space occupying patient, so as to obtain a data set; the identity information specifically includes: gender, age, and MBI. The clinical hematological indexes specifically comprise: PNI, NLR, hemoglobin, platelets, albumin, TBIL, ALP, γ GT, AST, ALT, and blood glucose.
The processing module 32 is configured to divide the data set into a training set and a test set, acquire a forebelly enhanced CT including a liver slice, which is pre-screened by a doctor in the training set, divide the screened forebelly enhanced CT by a U-net network image to obtain a liver image, remove environmental noise interference, and input the obtained liver image into a ResNet34 network to obtain a vector including liver CT information;
the processing module 32 is specifically configured to: inputting the obtained liver image into a ResNet34 network, firstly carrying out 64 convolution kernels of 7 × 7, and then pooling through a convolution kernel of 3 × 3;
using 64 convolution kernels of 7 × 7 in a conv1 layer, reducing the dimension of a color image with the size of 224 × 224 to 112 × 112 with the step size of 2, and then performing maximum pooling of 3 × 3 with the step size of 2 to further reduce the dimension to 56 × 56;
inputting a conv2 layer consisting of 3 residual learning modules, wherein each residual learning module consists of two convolution layers, the convolution kernel size is 3 multiplied by 3, and 64 channels are formed;
inputting a conv3 layer consisting of 4 residual learning modules, and adjusting the step size to be 2 at a certain convolution layer of the conv3_1 so as to reduce the output dimension of the conv3_4 to 28 multiplied by 28;
inputting a conv4 layer consisting of 6 residual learning modules, adjusting the step size to be 2 at a certain convolution layer in the conv4, and reducing the output dimension of the conv4 to 14 multiplied by 14;
inputting a conv5 layer consisting of 3 residual learning modules, adjusting the step length to 2 in conv5, and finally outputting a liver CT image with 7 multiplied by 7 dimensions; finally, through a full connection layer, the data is output to 1000 classes to obtain the vector containing the patient liver enhanced CT information.
The prediction module 34 is configured to bring the clinical hematological indicator into the XGboost machine learning model to perform the first prediction, obtain a predicted value for prognosis judgment based on the clinical hematological indicator, bring the clinical hematological indicator and the predicted value into the MLP model, and mark information related to the patient prognosis again to obtain a final predicted value.
The embodiment of the present invention is a system embodiment corresponding to the above method embodiment, and specific operations of each module may be understood with reference to the description of the method embodiment, which is not described herein again.
Apparatus embodiment one
The embodiment of the present invention provides a prognosis prediction device after liver cancer liver transplantation based on deep learning, as shown in fig. 4, including: a memory 40, a processor 42 and a computer program stored on the memory 40 and executable on the processor 42, which computer program when executed by the processor 42 performs the steps as described in the method embodiments.
Device embodiment II
An embodiment of the present invention provides a computer-readable storage medium, on which an implementation program for information transmission is stored, and when executed by the processor 42, the program implements the steps as described in the method embodiment.
The computer-readable storage medium of this embodiment includes, but is not limited to: ROM, RAM, magnetic or optical disks, and the like.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A prognosis prediction method after liver cancer liver transplantation based on deep learning is characterized by comprising the following steps:
acquiring anterior abdominal enhanced CT, identity information, clinical hematology indexes, abdominal operation history, HBV-DNA, complications, postoperative pathological results and postoperative survival information of a hepatic malignant tumor patient and a hepatic benign occupying patient to obtain a data set;
dividing the data set into a training set and a testing set, acquiring a forebelly enhanced CT (computed tomography) containing a liver fault, which is pre-screened by a doctor in the training set, segmenting the screened forebelly enhanced CT through a U-net network image to obtain a liver image, removing the interference of environmental noise, and inputting the obtained liver image into a ResNet34 network to obtain a vector containing liver CT information;
and substituting the clinical hematology indexes into an XGboost machine learning model to carry out first-step prediction to obtain a prediction value of prognosis judgment based on the clinical hematology indexes, substituting the clinical hematology indexes and the prediction value into an MLP (Multi-level medical processing) model, and marking the relevant information of the patient prognosis condition again to obtain a final prediction value.
2. The method according to claim 1, wherein the identity information specifically includes: gender, age, and MBI.
3. The method according to claim 1, wherein the clinical haematological indicators in particular comprise: PNI, NLR, hemoglobin, platelets, albumin, TBIL, ALP, γ GT, AST, ALT, and blood glucose.
4. The method of claim 1, wherein inputting the obtained liver image into a ResNet34 network to obtain a vector containing liver CT information specifically comprises:
inputting the obtained liver image into a ResNet34 network, firstly carrying out 64 convolution kernels of 7 × 7, and then pooling through a convolution kernel of 3 × 3;
using 64 convolution kernels of 7 × 7 in a conv1 layer, reducing the dimension of a color image with the size of 224 × 224 to 112 × 112 with the step size of 2, and then performing maximum pooling of 3 × 3 with the step size of 2 to further reduce the dimension to 56 × 56;
inputting a conv2 layer consisting of 3 residual learning modules, wherein each residual learning module consists of two convolution layers, the convolution kernel size is 3 multiplied by 3, and 64 channels are formed;
inputting a conv3 layer consisting of 4 residual learning modules, and adjusting the step size to be 2 at a certain convolution layer of the conv3_1 so as to reduce the output dimension of the conv3_4 to 28 multiplied by 28;
inputting a conv4 layer consisting of 6 residual learning modules, adjusting the step size to be 2 at a certain convolution layer in the conv4, and reducing the output dimension of the conv4 to 14 multiplied by 14;
inputting a conv5 layer consisting of 3 residual learning modules, adjusting the step length to 2 in conv5, and finally outputting a liver CT image with 7 multiplied by 7 dimensions; finally, through a full connection layer, the data is output to 1000 classes to obtain the vector containing the patient liver enhanced CT information.
5. A prognosis prediction system after liver cancer liver transplantation based on deep learning is characterized by comprising:
the acquisition module is used for acquiring the foreabdomen enhanced CT, the identity information, the clinical hematology index, the abdominal operation history, the HBV-DNA, the complications, the postoperative pathological result and the postoperative survival condition information of a hepatic malignant tumor patient and a hepatic benign occupying patient to obtain a data set;
the processing module is used for dividing the data set into a training set and a testing set, acquiring the forebelly enhanced CT which is pre-screened by a doctor in the training set and contains a liver fault, segmenting the screened forebelly enhanced CT through a U-net network image to obtain a liver image, removing the interference of environmental noise, and inputting the obtained liver image into a ResNet34 network to obtain a vector containing liver CT information;
and the prediction module is used for substituting the clinical hematological index into the XGboost machine learning model to perform first-step prediction to obtain a prediction value for prognosis judgment based on the clinical hematological index, substituting the clinical hematological index and the prediction value into the MLP model, and marking the relevant information of the patient prognosis condition again to obtain a final prediction value.
6. The system according to claim 5, wherein the identity information specifically comprises: gender, age, and MBI.
7. The system according to claim 5, wherein the clinical haematology indicators include in particular: PNI, NLR, hemoglobin, platelets, albumin, TBIL, ALP, γ GT, AST, ALT, and blood glucose.
8. The system of claim 5, wherein the processing module is specifically configured to:
inputting the obtained liver image into a ResNet34 network, firstly carrying out 64 convolution kernels of 7 × 7, and then pooling through convolution kernels of 3 × 3;
using 64 convolution kernels of 7 × 7 in a conv1 layer, reducing the dimension of a color image with the size of 224 × 224 to 112 × 112 with the step size of 2, and then performing maximum pooling of 3 × 3 with the step size of 2 to further reduce the dimension to 56 × 56;
inputting a conv2 layer consisting of 3 residual learning modules, wherein each residual learning module consists of two convolution layers, the convolution kernel size is 3 multiplied by 3, and 64 channels are formed;
inputting a conv3 layer consisting of 4 residual learning modules, and adjusting the step size to be 2 at a certain convolution layer of the conv3_1 so as to reduce the output dimension of the conv3_4 to 28 multiplied by 28;
inputting a conv4 layer consisting of 6 residual learning modules, adjusting the step size to be 2 at a certain convolution layer in the conv4, and reducing the output dimension of the conv4 to 14 multiplied by 14;
inputting a conv5 layer consisting of 3 residual learning modules, adjusting the step length to 2 in the conv5 layer, and finally outputting a liver CT image with 7 multiplied by 7 dimensions; finally, through a full connection layer, the data is output to 1000 classes to obtain the vector containing the patient liver enhanced CT information.
9. A prognosis prediction device after liver cancer liver transplantation based on deep learning is characterized by comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the method for prognosis prediction after deep learning-based liver cancer liver transplantation according to any one of claims 1 to 4.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores thereon an information transfer implementation program, which when executed by a processor implements the steps of the method for predicting prognosis after liver cancer transplantation based on deep learning according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210917359.XA CN115188477A (en) | 2022-08-01 | 2022-08-01 | Method, system and device for prognosis prediction after liver cancer liver transplantation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210917359.XA CN115188477A (en) | 2022-08-01 | 2022-08-01 | Method, system and device for prognosis prediction after liver cancer liver transplantation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115188477A true CN115188477A (en) | 2022-10-14 |
Family
ID=83521852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210917359.XA Pending CN115188477A (en) | 2022-08-01 | 2022-08-01 | Method, system and device for prognosis prediction after liver cancer liver transplantation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115188477A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116486922A (en) * | 2023-04-18 | 2023-07-25 | 中日友好医院(中日友好临床医学研究所) | Gene polymorphism and plasma cytokine-based lung transplantation rejection prediction model and application thereof |
| CN118039070A (en) * | 2024-04-11 | 2024-05-14 | 四川省肿瘤医院 | Clinical care system for interventional operation |
| CN118039070B (en) * | 2024-04-11 | 2024-06-28 | 四川省肿瘤医院 | Clinical care system for interventional operation |
-
2022
- 2022-08-01 CN CN202210917359.XA patent/CN115188477A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116486922A (en) * | 2023-04-18 | 2023-07-25 | 中日友好医院(中日友好临床医学研究所) | Gene polymorphism and plasma cytokine-based lung transplantation rejection prediction model and application thereof |
| CN116486922B (en) * | 2023-04-18 | 2024-01-23 | 中日友好医院(中日友好临床医学研究所) | Method for predicting lung transplant rejection based on gene polymorphism and plasma cytokines and application thereof |
| CN118039070A (en) * | 2024-04-11 | 2024-05-14 | 四川省肿瘤医院 | Clinical care system for interventional operation |
| CN118039070B (en) * | 2024-04-11 | 2024-06-28 | 四川省肿瘤医院 | Clinical care system for interventional operation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101857624B1 (en) | Medical diagnosis method applied clinical information and apparatus using the same | |
| CN111095261A (en) | Automatic analysis system and method for fundus images | |
| Danilov et al. | Classification of intracranial hemorrhage subtypes using deep learning on CT scans | |
| Li et al. | Lung nodule detection with deep learning in 3D thoracic MR images | |
| Maruyama et al. | Simultaneous brain structure segmentation in magnetic resonance images using deep convolutional neural networks | |
| CN115188477A (en) | Method, system and device for prognosis prediction after liver cancer liver transplantation | |
| Zhou et al. | Deep learning-based breast region extraction of mammographic images combining pre-processing methods and semantic segmentation supported by Deeplab v3+ | |
| Hakim et al. | Microcalcification detection in mammography image using computer-aided detection based on convolutional neural network | |
| Banumathy et al. | CAD of BCD from Thermal Mammogram Images Using Machine Learning. | |
| Bugday et al. | Automatic diagnosis of ureteral stone and degree of hydronephrosis with proposed convolutional neural network, RelieF, and gradient‐weighted class activation mapping based deep hybrid model | |
| Wang et al. | RFPNet: Reorganizing feature pyramid networks for medical image segmentation | |
| Lee et al. | Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery | |
| CN115274094A (en) | Liver cancer imaging combined AFP diagnosis model construction method, system and device | |
| Sharma et al. | Generous approach for diagnosis and detection of gastrointestinal tract disease with application of deep neural network | |
| CN115274119A (en) | Construction method of immunotherapy prediction model fusing multi-image mathematical characteristics | |
| CN115440386A (en) | Prediction of immunotherapy effect of advanced cancer patients based on weighted multi-lesion imagemics features | |
| Şengül et al. | Performance Evaluation of Basic Capsule Network Architecture in Classification of Biomedical Images | |
| Saumiya et al. | Unified automated deep learning framework for segmentation and classification of liver tumors | |
| Thaseen et al. | Breast Cancer Detection Using Deep Learning Model | |
| Deepa et al. | Lung cancer prediction and stage classification in CT scans using convolution neural networks-a deep learning model | |
| Kashif et al. | Breast cancer detection and diagnostic with convolutional neural networks | |
| Bhattacharyya et al. | Liver Cancer Classification With Using Gray‐Level Co‐Occurrence Matrix Using Deep Learning Techniques | |
| Hafeez et al. | Brain tumor classification using MRI images and convolutional neural networks | |
| Ramkumar | Identification and Classification of Breast Cancer using Multilayer Perceptron Techniques for Histopathological Image | |
| Zegair et al. | Application of Machine Learning in Melanoma Detection and the Identification of'Ugly Duckling'and Suspicious Naevi: A Review |
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 |