AI-enhanced cancer radiotherapy quality assessment: utilizing daily linac performance, radiomics, dosimetrics, and planning complexity.

ABSTRACT:

Objective

This study aimed to develop and validate an Informer- Convolutional Neural Network (CNN) model to predict the gamma passing rate (GPR) for patient-specific quality assurance in volumetric modulated arc therapy (VMAT), enhancing treatment safety and efficacy by integrating multiple data sources.

Methods

Analyzing 465 VMAT treatment plans covering head & neck, chest, and abdomen, the study extracted data from 31 complexity indicators, 123 radiomics features, and 123 dosimetrics indices, along with daily linac performance data including 141 key performance indicators. A hybrid Informer-CNN architecture was used to handle both temporal and non-temporal data for predicting GPR.

Results

The Informer-CNN model demonstrated superior predictive performance over tradi

SUBMITTER: Deng J 

PROVIDER: S-EPMC11966416 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature