Liver cancer image classification method and device combining computer visual features and radiomics features

Abstract

The invention belongs to the technical field of image classification, and particularly relates to a liver cancer image classification method combining computer visual features and radiomics features, which comprises the following steps: S1, collecting liver cancer images and case data corresponding to the liver cancer images, sorting feature diseases and treatment schemes and treatment results of the diseases, and associating input tags as a training sample library; s2, utilizing a computer to intercept focus images at corresponding positions on the liver cancer image from the label established in the step S1, classifying, and establishing a case feature library; and S3, carrying out image omics feature extraction on the focus image intercepted in the step S2. And S4, performing staged association on the disease feature process extracted in the step S3, updating the disease feature process to the case feature library, generating a disease tree feature library, and completing classification of the liver cancer images. A disease tree feature library is established, and the device can be conveniently used as a preoperative evaluation tool and is expected to help surgeons customize individualized preoperative treatment schemes and prognosis evaluation in the future.

Description

technical field [0001] The invention relates to the technical field of image classification, in particular to a liver cancer image classification method and device combining computer vision features and radiomics features. Background technique [0002] Liver cancer is a malignant tumor of the liver, which can be divided into two categories: primary and secondary. Primary malignant tumors of the liver originate from the epithelial or mesenchymal tissues of the liver. The former is called primary liver cancer, which is a malignant tumor with a high incidence in my country and is extremely harmful; rare. Secondary or metastatic liver cancer refers to the invasion of the liver by malignant tumors originating from multiple organs throughout the body, and is generally seen in the liver metastases of malignant tumors in the stomach, biliary tract, pancreas, colorectum, ovary, uterus, lung, breast and other organs. Liver cancer is one of the main causes of cancer death in the world...

AI Technical Summary

Problems solved by technology

[0004] In recent years, more and more experts have proposed the method of learning based on a large number of image visual features to realize the evaluation of factors such as tumor diagnosis, curative effect and prognosis, so as to improve clinical decision-making ability. The radiomics features of the radiomics are helpful for the identification of pathological grades of other cancers, but it is still necessary to explore computer vision features and radiomics features for the classification of liver cancer in order to better solve such problems in the future

Images