Rerecurrent nasopharynx cancer radiomics data processing method, system and device and storage medium

Abstract

The invention discloses a recurrent nasopharynx cancer radiomics data processing method, system and device and a storage medium. The radiomics data processing method comprises the following steps: acquiring MRI image data of a patient with recurrent nasopharyngeal carcinoma; extracting image data for analysis, segmenting a focus, extracting image features, and screening image omics key features; and inputting the radiomics key features into a random forest model obtained through training to predict the risk of nasopharyngeal necrosis. According to the invention, accurate guidance is provided for prediction of nasopharyngeal necrosis risk and formulation of a treatment scheme for patients with recurrent nasopharyngeal carcinoma, so that a part of high-risk patients with nasopharyngeal necrosis are prevented from bad outcomes after receiving reradiotherapy, and individualized accurate diagnosis and treatment of recurrent nasopharyngeal carcinoma are promoted.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a radiomics data processing method, system, device and storage medium for recurrent nasopharyngeal carcinoma. Background technique [0002] Nasopharyngeal carcinoma is a malignant tumor of the head and neck, and radiotherapy is the main treatment method for nasopharyngeal carcinoma. In recent years, due to the development of intensity-modulated conformal radiotherapy, the local control rate of nasopharyngeal carcinoma has been significantly improved, but there are still 10% to 15% of patients with recurrence. Re-radiotherapy is currently the most important and effective treatment for recurrent nasopharyngeal carcinoma. Studies have shown that patients with recurrent nasopharyngeal carcinoma may still obtain better local control (3-year local control rate of 66.1%-71.0%) and long-term survival (3-year overall survival: 44.3%-51.8%) after re-radiotherapy. [0...

AI Technical Summary

Problems solved by technology

[0004] A few previous studies have constructed nasopharyngeal necrosis prediction models based on purely clinical factors, but the effect is not ideal

In 2016, Yu et al. found in 228 patients with recurrent nasopharyngeal carcinoma who received reradiation therapy that women, necrosis before reradiation, higher cumulative dose of two radiation treatments (≥141.5Gy) and greater recurrence Tumor volume (≥25.38cm3) is a high-risk factor for fatal nasopharyngeal necrosis, but a reliable individualized prediction model has not been established

In 2019, Li et al. included a cohort of 7,144 large-sample nasopharyngeal carcinoma patients, based on age, pathological type, diabetes history, T stage, radiotherapy technique, whether to undergo radiotherapy again, and blood indicators (C-reactive protein, hemoglobin, albumin levels). ) built a multivariate regression model, although the prediction accuracy of the model reached 0.78, but most of the included patients received initial radiotherapy (only 3.4% of patients received re-radiation therapy), and the clinical application was insufficient

Images