Lung cancer staging prediction method based on deep learning

Abstract

The invention relates to a lung cancer TMN staging prediction method based on deep learning. The method comprises the steps of extracting and analyzing chest CT image features by adopting a current relatively mature deep learning method; finally, adopting an existing image data set for training a model structure to achieve quantitative classification of multiple indexes influencing lung cancer staging judgment. A quantified index classification result is provided for a diagnosis doctor. The workload of an occupational doctor is reduced. The staging diagnosis efficiency of the doctor is improved. The doctor is assisted in making a treatment scheme.

Description

technical field [0001] The present invention relates to the intersection field of deep learning and medical image processing in the field of artificial intelligence, and specifically relates to a method for predicting lung cancer staging based on deep learning. Background technique [0002] Lung cancer is one of the most harmful malignant tumors to human health, and its mortality rate ranks first in the mortality rate of malignant tumors. Before the treatment of lung cancer, a clear diagnosis must be made. Both qualitative and staging diagnosis are important. Before lung cancer patients receive treatment, doctors will formulate a specific treatment plan based on the type of cancer, the location of the cancer, the patient's health status, and the stage of the cancer. [0003] Traditional diagnostic methods face the problems of individual differences in patients and unbalanced medical resources. Generally, professional doctors with rich clinical experience can make accurate ...

AI Technical Summary

Problems solved by technology

[0005] At present, most of the problems in the diagnosis of lung cancer remain in the use of deep learning methods for automatic detection of lesions and classification of pulmonary nodules on lung medical images, lack of follow-up diagnostic solutions, etc.

Images