CT-derived nested habitats score for preoperative IASLC grading in lung adenocarcinoma: cross-center validation and radiogenomic analysis
Abstract
IntroductionThe 2020 International Association for the Study of Lung Cancer (IASLC) grading system integrates the predominant histologic pattern and the proportion of high-grade patterns, but preoperative CT assessment is limited by spatial averaging of heterogeneous tumor components. We aimed to develop a CT-derived nested habitats score (NHS) that recursively identifies grade-associated intratumoral CT subregions, evaluate its cross-center performance for preoperative IASLC grading, and explore its transcriptomic correlates.MethodsThis retrospective two-center study included 650 patients with surgically resected lung adenocarcinoma. Center 1 formed the development cohort (n = 390); Center 2 was stratified 1:1 into validation (n = 130) and locked test (n = 130) cohorts, both from the same external institution. The prespecified primary task was pathologic IASLC Grade 1 versus Grade 2/3. NHS was generated using five-fold out-of-fold estimation in development data. Clinical-radiological, whole-tumor radiomics, NHS, and integrated models were compared, with algorithm selection confined to validation before one-time test evaluation. An independent TCGA-LUAD/TCIA CT-RNA cohort (n = 88) underwent exploratory WGCNA and Hallmark gene-set enrichment analysis.ResultsThe development/validation/test cohorts contained 41/14/14 Grade 1, 293/101/96 Grade 2, and 56/15/20 Grade 3 tumors. The selected random-forest integrated model yielded AUCs of 0.871 (95% CI, 0.784–0.936) in validation and 0.866 (95% CI, 0.784–0.935) in testing. NHS alone yielded AUCs of 0.828 and 0.854, compared with 0.620 and 0.497 for the clinical-radiological model and 0.703 and 0.775 for whole-tumor radiomics. NHS accounted for 76.3% of mean absolute SHAP contribution; removing NHS reduced AUC by 0.251 (95% CI, 0.079–0.439) in validation and 0.369 (95% CI, 0.200–0.553) in testing. Brier scores for NHS and the integrated model (0.074–0.077) were below the non-informative reference (0.096), but calibration slopes exceeded 1, and decision curves showed no net benefit over treating all patients as Grade 2/3 at low-to-intermediate thresholds. Exploratory radiogenomics showed nominal NHS-associated coexpression modules and enrichment of WNT/beta-catenin, E2F, G2M-checkpoint, and immune-related programs.DiscussionNHS discriminated IASLC Grade 1 from Grade 2/3 tumors, retained stable performance in two held-out cohorts from a second institution, and contributed most of the integrated model’s discrimination. The transcriptomic associations are hypothesis-generating, and recalibration and prospective multicenter evaluation are required before clinical application.
Related
- MRI-derived radiogenomic surrogate of a hypoxia–angiogenesis–EMT transcriptional state in nasopharyngeal carcinoma: multicenter external validation
- A new strategy to count and sort neutrophil‐derived extracellular vesicles: Validation in infectious disorders
- Urinary TAGMe methylation enables preoperative risk stratification and reveals enhancer‑mediated regulation in urothelial carcinoma
- Advances in Treatment of Refractory Advanced and Recurrent Cervical Adenocarcinoma: Molecular Heterogeneity and Differences from Squamous Cell Carcinoma
- Sodium butyrate inhibits the proliferation of temozolomide-resistant glioblastoma (A172) and lung adenocarcinoma (A549) cells and biphasically regulates EGFR expression
BibTeX
@article{peng2026ctderived,
title = {{CT-derived nested habitats score for preoperative IASLC grading in lung adenocarcinoma: cross-center validation and radiogenomic analysis}},
author = {Wang Peng and Jiajun Liu and Li Li and Wanyin Qi and Jinhong Zhao and Dinghua Li},
journal = {Frontiers in Molecular Biosciences},
year = {2026},
month = nov,
doi = {10.3389/fmolb.2026.2006861},
url = {https://www.frontiersin.org/articles/10.3389/fmolb.2026.2006861},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - CT-derived nested habitats score for preoperative IASLC grading in lung adenocarcinoma: cross-center validation and radiogenomic analysis
AU - Wang Peng
AU - Jiajun Liu
AU - Li Li
AU - Wanyin Qi
AU - Jinhong Zhao
AU - Dinghua Li
PY - 2026
DA - 2026/11/04
JO - Frontiers in Molecular Biosciences
DO - 10.3389/fmolb.2026.2006861
UR - https://www.frontiersin.org/articles/10.3389/fmolb.2026.2006861
AB - IntroductionThe 2020 International Association for the Study of Lung Cancer (IASLC) grading system integrates the predominant histologic pattern and the proportion of high-grade patterns, but preoperative CT assessment is limited by spatial averaging of heterogeneous tumor components. We aimed to develop a CT-derived nested habitats score (NHS) that recursively identifies grade-associated intratumoral CT subregions, evaluate its cross-center performance for preoperative IASLC grading, and explore its transcriptomic correlates.MethodsThis retrospective two-center study included 650 patients with surgically resected lung adenocarcinoma. Center 1 formed the development cohort (n = 390); Center 2 was stratified 1:1 into validation (n = 130) and locked test (n = 130) cohorts, both from the same external institution. The prespecified primary task was pathologic IASLC Grade 1 versus Grade 2/3. NHS was generated using five-fold out-of-fold estimation in development data. Clinical-radiological, whole-tumor radiomics, NHS, and integrated models were compared, with algorithm selection confined to validation before one-time test evaluation. An independent TCGA-LUAD/TCIA CT-RNA cohort (n = 88) underwent exploratory WGCNA and Hallmark gene-set enrichment analysis.ResultsThe development/validation/test cohorts contained 41/14/14 Grade 1, 293/101/96 Grade 2, and 56/15/20 Grade 3 tumors. The selected random-forest integrated model yielded AUCs of 0.871 (95% CI, 0.784–0.936) in validation and 0.866 (95% CI, 0.784–0.935) in testing. NHS alone yielded AUCs of 0.828 and 0.854, compared with 0.620 and 0.497 for the clinical-radiological model and 0.703 and 0.775 for whole-tumor radiomics. NHS accounted for 76.3% of mean absolute SHAP contribution; removing NHS reduced AUC by 0.251 (95% CI, 0.079–0.439) in validation and 0.369 (95% CI, 0.200–0.553) in testing. Brier scores for NHS and the integrated model (0.074–0.077) were below the non-informative reference (0.096), but calibration slopes exceeded 1, and decision curves showed no net benefit over treating all patients as Grade 2/3 at low-to-intermediate thresholds. Exploratory radiogenomics showed nominal NHS-associated coexpression modules and enrichment of WNT/beta-catenin, E2F, G2M-checkpoint, and immune-related programs.DiscussionNHS discriminated IASLC Grade 1 from Grade 2/3 tumors, retained stable performance in two held-out cohorts from a second institution, and contributed most of the integrated model’s discrimination. The transcriptomic associations are hypothesis-generating, and recalibration and prospective multicenter evaluation are required before clinical application.
SN - 2296-889X
ER -