Functional-based multi-omics early prediction of radiation pneumonitis in NSCLC using AI-generated perfusion and ventilation from planning CT.

This study aims to develop a functional-based multi-omics model for early prediction of radiation pneumonitis (RP) by extracting radiomic and dosiomic features from functionally defined lung regions, using generated perfusion () and ventilation () from pre-radiotherapy planning computed tomography (CT).We retrospectively analyzed data from 121 patients with locally advanced non-small cell lung cancer treated with curative-intent intensity-modulated radiotherapy between 2015 and 2019, including pre-treatment CT and dose maps. Q and V maps were generated from CT with deep learning-based and supervoxel-based approaches, respectively. Regions of interest (ROIs) combined the planning target volume with each of three functional lung regions-high functional lung (HFL), low functional lung, and whole lung (WL)-defined by thresholds on Q and V maps. Radiomic and dosiomic features were extracted from CT and dose distributions within each ROI. For each ROI, three methods-radiomics (R), dosiomics (D), and dual-omics (RD)-were constructed. 13 machine learning algorithms were trained and evaluated using 10-fold cross-validation, and model performance was assessed by the average area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and1 score. RP was defined as CTCAE grade ⩾2.Of the 35 selected features, 20 were from HFL. In dual-omics models, using HFL features improved predictive performance for RP (AUC 0.879 ± 0.105) compared to WL (AUC 0.778 ± 0.100). In HFL, the RD method outperformed both R (AUC 0.786 ± 0.076) and D (AUC 0.791 ± 0.107) methods. Decision curve analysis showed the dual-omics model based on HFL provided the highest net benefit across threshold probabilities.This study is the first to systematically demonstrate that features extracted from CT-derived HFL capture important functional differences and provide strong predictive value for RP. Compared to conventional methods, integrating radiomics, dosiomics, and CT-based functional information further improves predictive performance.