Imaging omics feature processing method for predicting recurrence of hepatocellular carcinoma after surgery excision based on multi-modal MRI images

Abstract

The invention provides an imaging omics feature processing method for predicting recurrence of hepatocellular carcinoma after surgery excision based on multi-modal MRI images. The method comprises thefollowing steps: collecting MR sample images of multi-modal hepatocellular carcinoma, carrying out region-of-interest delineation on the MR sample images, and extracting image features of the region-of-interest; performing dummy variable processing on the extracted image features to generate a dummy variable feature with a value of 0 or 1; calculating a Spearman correlation coefficient, removinghigh correlation characteristics by taking 0.95 as a threshold value, and performing characteristic selection by adopting a support vector machine recursive characteristic elimination method; and inputting the selected features into a model to construct an L1 regularization Logistic regression model, and performing parameter adjustment through a five-fold cross validation technology to obtain a feature dimension reduction result. Based on an optimization theory of a machine learning method, the five-fold cross validation technology is introduced, an L2 regularization Logistic regression modelis obtained through optimization according to an L2 regularization model construction thought, and the L2 regularization Logistic regression model is evaluated by adopting an ROC method.

Description

technical field [0001] The present invention relates to the technical fields of imaging medicine, nuclear medicine and radiomics, and in particular, to a radiomics feature processing method for predicting the recurrence of surgically resected hepatocellular carcinoma based on multimodal MRI images. Background technique [0002] Hepatocellular carcinoma is the sixth most common cancer and the fourth cause of cancer-related death worldwide, and liver resection is one of the most important treatment strategies for patients with early-stage liver cancer. However, up to 70% of patients with HCC after hepatectomy relapse within 5 years. Time to recurrence is one of the independent prognostic factors. Early recurrence (2 years) of HCC has a worse prognosis than late recurrence (>2 years). Therefore, risk stratification of HCC patients is required. Previous studies have demonstrated that some pathological factors can be used for risk stratification of HCC, such as microvascular ...

AI Technical Summary

Problems solved by technology

However, the acquisition of pathological features relies on tissue samples obtained by invasive surgery or biopsy, and the heterogeneity of tumors limits the validity of this sample, because it is impossible to characterize the entire tumor from small tissue samples

In addition, biopsies are invasive, potentially bleeding, and risk of infection and dissemination prevent their widespread clinical use

Images