Head and neck tumor distal metastasis prediction method based on machine learning

Abstract

The invention relates to a head and neck tumor distal metastasis prediction method based on machine learning, and the method comprises the steps: building an improved convolutional neural network, training a built network model through the head and neck CT image data of a head and neck tumor patient with distal metastasis, and predicting the distal metastasis of the head and neck tumor after the training; and inputting a head and neck CT image of a head and neck tumor patient, which is shot in real time, into the network model, and outputting a result as far-end metastasis prediction of the head and neck CT image of the head and neck tumor patient. A radiomics method is adopted to replace a biopsy method to predict far-end metastasis of head and neck cancers, the pain that a head and neck patient suffers from multiple times of biopsy is avoided, a deep learning method is adopted to supplement a feature extraction algorithm of original radiomics, and the problem that the number of head and neck medical images is small is solved.

Description

technical field [0001] The present invention relates to the technical field of deep learning, and more specifically, relates to a machine learning-based method for predicting distal metastasis of head and neck tumors, computer equipment and storage media. Background technique [0002] Malignant tumors of the head and neck account for about 5% of malignant tumors in the whole body. Due to the complex anatomical structure and other reasons, although surgery is the main method of treatment, the rate of radical resection is low, and the early clinical symptoms are hidden. In the middle and advanced stages, it has always been a difficult point in tumor treatment. The diagnosis of malignant tumors of the head and neck usually requires a combination of medical history, signs, endoscopic biopsy and related imaging examinations. Imaging examinations are helpful for tumor detection, staging, and evaluation of treatment prognosis. Predicting whether the tumor has metastasized has impo...

AI Technical Summary

Problems solved by technology

Deep learning has achieved remarkable results in natural image classification. There are also studies on applying deep learning to medical image processing and diagnosis, but there are few imaging data of head and neck cancer.

Images