Prognosis prediction system and method for lung cancer patients

Abstract

The invention discloses a prognosis prediction system and method for lung cancer patients, belonging to the field of neural networks. The system comprises: an annotation module for annotating digitalpathological images to obtain annotated images; an acquisition module for acquiring prognosis data and survival time corresponding to the annotated images; a collection module for respectively addingeach annotated image, the prognosis data and the survival time into a data set to generate training data sets; a classification module for dividing the training data sets into a training set and a test set; a training module for training the training set to obtain a prognosis prediction model for lung cancer patients; a test module for inputting the test set into the prognosis prediction model forthe lung cancer patients to obtain corresponding prediction accuracy; and a prediction module for inputting the digital pathological image of a patient to be detected into the prognosis prediction model for the lung cancer patients to obtain predicted prognosis data and predicted survival time. The prognosis prediction system and method have the following beneficial effect: a doctor can formulatea treatment scheme according to prediction results, so treatment effect is improved, and survival time is prolonged.

Description

technical field [0001] The invention relates to the field of neural networks, in particular to a system and method for predicting the prognosis of lung cancer patients. Background technique [0002] The latest cancer epidemiological statistics in China show that there were 730,000 new lung cancer patients and 600,000 deaths in 2015. Lung cancer has become the cancer with the highest incidence and mortality in China. Lung cancer deaths account for 25% of all cancer deaths. Due to the high recurrence risk and low survival rate of lung cancer, most patients with stage IB-IIIA lung cancer will receive postoperative adjuvant chemotherapy. However, based on parameters such as the degree of residual lesions, lymph node metastasis, and cancer stage, even with the same treatment plan, the overall prognosis of patients will be very different. In recent years, clinicians have been working to find independent prognostic factors related to lung cancer. Tumor size and pathological grad...

AI Technical Summary

Problems solved by technology

In order to find more visual features in pathological slices, there is evidence to support the feasibility of using convolutional neural networks to evaluate the prognosis of various malignant tumors. The product neural network algorithm model has yet to be developed. In order to solve the above problems, the present invention develops a prognosis prediction system that can predict the prognosis of lung cancer patients through digital pathological images of patients.

Images