Evaluation system and method for efficacy of synchro-neoadjuvant chemoradiotherapy before rectal cancer surgery

Abstract

The invention relates to an evaluation system and method for the efficacy of synchro-neoadjuvant chemoradiotherapy before the rectal cancer surgery. The evaluation system comprises an image acquisition unit used for acquiring pathological biopsy slice scan images and neoadjuvant chemoradiotherapy treatment pre-MRI images of newly diagnosed locally advanced rectal cancer patients, and classifying the rectal cancer patients into a training set, a check set and a test set, to serve as input image data, an image labeling unit used for respectively labeling the pathological biopsy slice scan imagesand the MRI images of the training set, the check set and the test set, a convolutional neural network constructing unit used for constructing a first convolutional neural network model, and a convolutional neural network model training unit used for obtaining a second convolutional neural network model for evaluating the efficacy of synchro-neoadjuvant chemoradiotherapy before the rectal cancersurgery. The evaluation system for the efficacy of synchro-neoadjuvant chemoradiotherapy before the rectal cancer surgery has multiple advantages such as being high in accuracy, short in time consumption, long in working duration, objective and three-dimensional.

Description

technical field [0001] The present invention relates to a system and method for evaluating curative effect of preoperative neoadjuvant chemoradiotherapy for rectal cancer, in particular to a system and method for evaluating curative effect of preoperative neoadjuvant chemoradiotherapy for rectal cancer based on big data analysis of biopsy pathology and pre-treatment MRI images. Background technique [0002] Deep learning is currently the most suitable and widely used algorithm for image recognition and speech analysis in the field of artificial intelligence. Its inspiration comes from the working mechanism of the human brain. It is to automatically extract features from externally input data by establishing a convolutional neural network. , so that the machine can understand the learning data, obtain information and output. At present, artificial intelligence based on deep learning has been applied in various industries, including speech recognition, face recognition, car lo...

AI Technical Summary

Problems solved by technology

In terms of post-treatment, the analysis of more than 1,500 samples has shown that the T staging of MRI after CRT is not consistent with the pathology, and its specificity can reach 91%, but the sensitivity is only 50%, and the accuracy is not high enough.

At present, doctors are trained through clinical practice and professional knowledge. Qualified doctors manually read and analyze pathological tissue slices and MRI images, and combine their long-term accumulated clinical diagnosis experience to make analysis and diagnosis. The accuracy rate is not high, it takes a long time, and the work continues time is limited

This method of reading images with the naked eye is closely related to subjective factors such as the doctor's own experience and working status, and is prone to missed diagnosis, misdiagnosis, and controversy.

In addition, it takes a long time to train a qualified doctor, and the accumulation of clinical experience is indispensable, and it is inevitable to be affected by subjective emotions and working conditions during the long-term work process. Many factors may affect Patient treatment plan development

[0006] In addition, the occurrence and development of tumors involves all levels from microscopic genes to abnormal macroscopic changes in tissues and organs, and involves the joint action of molecules, cells and tissues. Therefore, a single method cannot accurately predict the malignant biological behavior of tumors. However, the current international Most of the analysis and modeling of medical big data in the world is based on a single level, and its predictive value is limited

Images