Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Early prediction method for curative effect of cancer chemotherapy based on two-channel convolutional neural network

A technology of convolutional neural network and prediction method, which is applied in the field of dual-channel neural network algorithm, can solve the problem of low accuracy of prediction algorithm and achieve the effect of fast speed and high precision

Pending Publication Date: 2022-03-15
SHANGHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Purpose of the present invention: To solve the problem of low accuracy of the current prediction algorithm, a dual-channel neural network algorithm for predicting the curative effect of neoadjuvant chemotherapy with high precision is established by introducing the feature sharing strategy and weight analysis strategy in the double-branch network

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Early prediction method for curative effect of cancer chemotherapy based on two-channel convolutional neural network
  • Early prediction method for curative effect of cancer chemotherapy based on two-channel convolutional neural network
  • Early prediction method for curative effect of cancer chemotherapy based on two-channel convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Embodiment 1: The idea of ​​the present invention is: first, perform frame cutting operation on the original ultrasound video data of adjuvant chemotherapy, and select ultrasound images with different shapes and clear boundaries; then perform preprocessing operations on the selected ultrasound images, the process includes Image lesions (Region of Interest, ROI) were cropped, grayscaled, denoised, and data enhanced; finally, based on the processed data set, a deep learning model was constructed using a dual-channel neural network algorithm to predict the efficacy of neoadjuvant chemotherapy. Purpose. The matching image data with known curative effect is used to train and test the neural network, and the trained neural network is used to predict the curative effect of the matching image.

[0040] Specific steps include:

[0041] A. Video frame cutting operation: for neoadjuvant chemotherapy ultrasound video frame cutting processing, select some frame images with differen...

Embodiment 2

[0056] Preferred embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings. In this embodiment, the specific configuration of the server running the experiment is as follows: the CPU is Intel Xeon Silver 4110, the graphics card is two Nvidia GeForce RTX2080Ti GPUs, and the ROM is 64GB. In terms of model building, the dual-channel neural network algorithm and comparison model are implemented based on the open source deep learning tool PyTorch1.7.0, and the software environment of the experimental platform is Python3.7 version. In terms of experimental settings, the experiment chooses Adam as the optimization algorithm, the batch size is set to 8, the initial learning rate is set to 0.005, and the number of iterations is set to 128. In terms of loss function, the cross entropy loss function is used. In terms of performance evaluation, the experiment passed accuracy (Accuracy), sensitivity (Sensitivity), specific...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a cancer chemotherapy curative effect early prediction method based on a two-channel convolutional neural network, and the method comprises the steps: respectively inputting image data before chemotherapy and image data after first-stage chemotherapy into two channels for layer-by-layer convolution operation, and carrying out the feature fusion between the two channels, the features output by the last layer of the two channels are subjected to weighted fusion to obtain an output result, each channel has 9 convolution layers, and four times of feature fusion and three times of pooling are carried out. According to the method, the relation between the data in different chemotherapy stages is considered, the relation characteristics between the data can be effectively utilized, in addition, a channel weight analysis strategy is added, a priori knowledge guiding model is introduced for training, the relation between the data in different chemotherapy stages is fully considered, and the accuracy of the method is improved. The prediction task can be completed only by using the ultrasonic image data of the first-stage neoadjuvant chemotherapy, and the precision and the speed are high.

Description

technical field [0001] The invention relates to the field of computers and proposes a dual-channel neural network algorithm for predicting the curative effect of cancer neoadjuvant chemotherapy. Background technique [0002] Neoadjuvant chemotherapy refers to systemic chemotherapy before the implementation of local treatment methods (such as surgery or radiotherapy), the purpose of which is to shrink the tumor and kill invisible metastatic cells early, so as to facilitate subsequent surgery, radiotherapy and other treatments. [0003] Neoadjuvant chemotherapy for breast cancer is a systemic drug treatment before local surgery or radiotherapy, and it is aimed at patients with locally advanced breast cancer (LABC). Patients are expected to achieve pathological complete response (Pathologic Complete Response, pCR) after neoadjuvant chemotherapy, which has great significance for the next treatment of patients. However, a considerable number of patients do not have a pathologica...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/00G06N3/08
CPCG06T7/0012G06N3/08G06T2207/10132G06T2207/20081G06T2207/20084G06T2207/20104G06T2207/20132G06T2207/20032G06T2207/30096
Inventor 谢江史华婵宋祥帅
Owner SHANGHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com