Functional-based multi-omics early prediction of radiation pneumonitis in NSCLC using AI-generated perfusion and ventilation from planning CT.
Authors
Affiliations (10)
Affiliations (10)
- Health Technology and Informatics, The Hong Kong Polytechnic University, Y934, 11 Yuk Choi Rd, Hung Hom, HONGKONG, 999077, Hong Kong.
- School of Future Science and Engineering, Soochow University, No.333 Ganjiang Road, Suzhou, Jiangsu, 215006, China, Suzhou, Jiangsu, 215006, China.
- department of health technology and informatics, The Hong Kong Polytechnic University, Room Y934, 9/F, Lee Shau Kee Building, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, Hong Kong, 999077, Hong Kong.
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Y934, 11 Yuk Choi Rd, Hung Hom, Hong Kong, Hong Kong, 999077, Hong Kong.
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University Faculty of Health and Social Sciences, Hung Hom, Kowloon, 999077, Hong Kong.
- Department of Radiation Oncology, Henan Cancer Hospital Affiliated Cancer Hospital of Zhengzhou University, No. 127 Dongming Road, Zhengzhou, China, Zhengzhou, Henan, 450003, China.
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University Faculty of Health and Social Sciences, Y934, 11 Yuk Choi Rd, Hung Hom, Kowloon, 999077, Hong Kong.
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, 11 Yuk Choi Rd Hung Hom, Hong Kong., Hong Kong, 999077, Hong Kong.
- The Hong Kong Polytechnic University, Y934, 11 Yuk Choi Rd, Hung Hom, HONG KONG, 999077, Hong Kong.
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Y934, 11 Yuk Choi Rd, Hung Hom, Hong Kong, 999077, Hong Kong.
Abstract
<b>Objective</b>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 (Q) and ventilation (V) from pre-radiotherapy planning computed tomography (CT).
<b>Approach</b>We retrospectively analyzed data from 121 patients with locally advanced non-small cell lung cancer (NSCLC) treated with curative-intent IMRT 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 (PTV) with each of three functional lung regions-high functional lung (HFL), low functional lung (LFL), 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, 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, and F1 score. RP was defined as CTCAE grade ≥ 2.
<b>Main results</b>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.
<b>Significance</b>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.
.