Rectal cancer lymph node metastasis diagnosis method based on deep learning multi-mode CT

Abstract

The invention discloses a rectal cancer lymph node metastasis diagnosis method based on deep learning multi-modal CT, and the method comprises the steps: carrying out the data preprocessing of a rectal cancer multi-modal CT image, and extracting the image features of a cut 3D plain-scan CT image and a cut 3D enhanced CT image through a newly constructed Mlenet (multi-modal Lenet convolutional neural network) convolutional neural network; and splicing the feature maps to form a new feature map, inputting the new feature map into a new Mlenet convolutional neural network, and performing dichotomy prediction to obtain a dichotomy prediction result. According to the method, effective feature extraction can be carried out on the multi-modal CT image, and the accuracy of lymph node metastasis prediction is greatly improved.

Description

technical field [0001] The technical field of image processing involved in the present invention, in particular, relates to a method for diagnosing rectal cancer lymph node metastasis based on deep learning multimodal CT. Background technique [0002] In recent years, lymph node metastasis is an independent risk factor for local recurrence and distant metastasis of rectal cancer, and it is also an important basis for evaluating pathological staging, surgical methods, and postoperative adjuvant therapy. Whether patients with rectal cancer have lymph node metastasis has an important impact on the decision-making of treatment options and the prognosis of patients. Therefore, accurate judgment of whether there is lymph node metastasis is an important step in the treatment of rectal cancer. Therefore, effective identification of lymph node metastasis signatures that can affect the survival and preoperative risk stratification of rectal cancer patients will help to formulate indiv...

AI Technical Summary

Problems solved by technology

The spatial and temporal heterogeneity of solid tumors at the gene, protein, cell, microenvironment, tissue, and organ levels limits the accuracy and representativeness of invasive detection methods such as pathology and molecular studies, and Biopsy is very burdensome to the patient, which limits the molecular detection method based on invasive biopsy; CT is the preferred radiomics examination method for lymph node metastasis of rectal cancer, and it can detect tumor location, lymph node metastasis, and surrounding organ invasion. Both evaluations have obvious advantages; however, the method of CT diagnosis of lymph node metastasis is usually that radiologists scan each image layer by layer to judge the shape, boundary and density of lymph nodes. This traditional method is time-consuming and subjective. Bias, resulting in reduced accuracy and efficiency; AI medical diagnosis has been widely used in medical image recognition, disease diagnosis and other aspects at home and abroad. AI can identify abnormal areas in medical images, and then provide reference for radiologists. Improve lesion detection rate

Images