Topologically distinct intratumoral heterogeneity scores for predicting high-risk pathological grades in invasive lung adenocarcinoma: A multicenter study across four institutions
4 affiliations
- 1Department of Radiology, Xiangtan Central Hospital(The Affiliated Hospital of Hunan University), Xiangtan, Hunan, China
- 2Department of Radiology, The Affiliated Hospital of Southwest Medical University, Luzhou, Sichuan, China
- 3Department of Radiology, Liuyang Hospital of Traditional Chinese Medicine, Changsha, Hunan, China
- 4Department of Radiology, The Third Xiangya Hospital of Central South University, Changsha, Hunan, China
Abstract
High-risk subtypes of invasive lung adenocarcinoma (IAC), particularly micropapillary- or solid-predominant patterns, are closely associated with poor prognosis. This multicenter retrospective study developed and validated a predictive model for the preoperative identification of these high-risk subtypes using topologically distinct intratumoral heterogeneity (ITH) scores derived from CT images. The study included 1,051 patients with IAC. Two complementary ITH scores were developed: a two-dimensional ITH score, which integrated local radiomics features with global pixel distribution patterns on the largest cross-sectional CT slice, and a three-dimensional ITH score, which extended this quantification across the entire tumor volume. Clinicoradiological features and ITH scores were incorporated as model inputs to construct six base machine learning classifiers and a final stacking ensemble classifier. Model interpretability and robustness were evaluated using SHapley Additive exPlanations (SHAP)-based ablation analyses. An independent dataset from The Cancer Imaging Archive (TCIA) was used for external validation to investigate associations between ITH scores and pathological characteristics, genomic features, recurrence-free survival, and overall survival. The stacking ensemble classifier achieved the best predictive performance, with an area under the receiver operating characteristic curve of 0.875, outperforming models based solely on radiomics features (0.834) or clinicoradiological features (0.792). SHAP analysis identified the 3D ITH score as the most influential contributor to model output, and TCIA validation showed that higher 3D ITH scores were associated with more aggressive tumor biology and poorer survival outcomes. The topologically distinct 3D ITH score may provide a clinically meaningful imaging biomarker for preoperative risk stratification in IAC. Author summary: We studied whether patterns hidden inside lung tumors on routine CT scans can help identify patients with more aggressive disease before surgery. Pathologists can determine tumor grade after resection, but treatment decisions often need to be made earlier. We developed a way to measure how fragmented and spatially complex the internal structure of a tumor is, using both a single representative image slice and the full tumor volume. We then combined these measurements with standard clinical and imaging features in a machine learning model. In a multicenter patient cohort, the model using the three-dimensional heterogeneity score performed better than models based only on conventional radiomics or routine clinical imaging features. This score also showed meaningful associations with adverse pathological findings and survival outcomes in an external public dataset. Our findings suggest that spatial tumor heterogeneity on CT images may provide useful preoperative information for risk stratification and individualized surgical planning.
Related
- Machine learning models integrating 2D and 3D intratumoral heterogeneity features from multi-sequence MRI: accurate prediction of perineural invasion in pancreatic ductal adenocarcinoma
- Explainable machine learning integrating CT-derived intratumoral heterogeneity for histological subtype prediction in pure ground-glass lung adenocarcinoma: multicenter validation and transcriptomic characterization
- MRI-based intratumoral and peritumoral heterogeneity for predicting intracranial progression in EGFR-mutant lung adenocarcinoma patients with treatment-naive brain metastases receiving first-line third-generation EGFR-TKIs.
- Mechanistic Decoding of Pharmacodynamic Intratumoral Heterogeneity: A Pan-Cancer Regulatory Framework
- Multi-b-value diffusion-weighted imaging-based habitat imaging for preoperative prediction of histological grade and prognosis in soft tissue sarcoma: focusing on intratumoral heterogeneity
BibTeX
@article{lin2026topologically,
title = {{Topologically distinct intratumoral heterogeneity scores for predicting high-risk pathological grades in invasive lung adenocarcinoma: A multicenter study across four institutions}},
author = {Shanyue Lin and Yudian Mao and Qian He and Wanyin Qi and Sanhong Zhang and Wei Li and Zhichao Zuo},
journal = {PLOS Digital Health},
year = {2026},
month = sep,
doi = {10.1371/journal.pdig.0001646},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001646},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Topologically distinct intratumoral heterogeneity scores for predicting high-risk pathological grades in invasive lung adenocarcinoma: A multicenter study across four institutions
AU - Shanyue Lin
AU - Yudian Mao
AU - Qian He
AU - Wanyin Qi
AU - Sanhong Zhang
AU - Wei Li
AU - Zhichao Zuo
PY - 2026
DA - 2026/09/08
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0001646
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001646
AB - High-risk subtypes of invasive lung adenocarcinoma (IAC), particularly micropapillary- or solid-predominant patterns, are closely associated with poor prognosis. This multicenter retrospective study developed and validated a predictive model for the preoperative identification of these high-risk subtypes using topologically distinct intratumoral heterogeneity (ITH) scores derived from CT images. The study included 1,051 patients with IAC. Two complementary ITH scores were developed: a two-dimensional ITH score, which integrated local radiomics features with global pixel distribution patterns on the largest cross-sectional CT slice, and a three-dimensional ITH score, which extended this quantification across the entire tumor volume. Clinicoradiological features and ITH scores were incorporated as model inputs to construct six base machine learning classifiers and a final stacking ensemble classifier. Model interpretability and robustness were evaluated using SHapley Additive exPlanations (SHAP)-based ablation analyses. An independent dataset from The Cancer Imaging Archive (TCIA) was used for external validation to investigate associations between ITH scores and pathological characteristics, genomic features, recurrence-free survival, and overall survival. The stacking ensemble classifier achieved the best predictive performance, with an area under the receiver operating characteristic curve of 0.875, outperforming models based solely on radiomics features (0.834) or clinicoradiological features (0.792). SHAP analysis identified the 3D ITH score as the most influential contributor to model output, and TCIA validation showed that higher 3D ITH scores were associated with more aggressive tumor biology and poorer survival outcomes. The topologically distinct 3D ITH score may provide a clinically meaningful imaging biomarker for preoperative risk stratification in IAC. Author summary: We studied whether patterns hidden inside lung tumors on routine CT scans can help identify patients with more aggressive disease before surgery. Pathologists can determine tumor grade after resection, but treatment decisions often need to be made earlier. We developed a way to measure how fragmented and spatially complex the internal structure of a tumor is, using both a single representative image slice and the full tumor volume. We then combined these measurements with standard clinical and imaging features in a machine learning model. In a multicenter patient cohort, the model using the three-dimensional heterogeneity score performed better than models based only on conventional radiomics or routine clinical imaging features. This score also showed meaningful associations with adverse pathological findings and survival outcomes in an external public dataset. Our findings suggest that spatial tumor heterogeneity on CT images may provide useful preoperative information for risk stratification and individualized surgical planning.
SN - 2767-3170
ER -