{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:07:56Z","timestamp":1788890876999,"version":"build-2803163510"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001646","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T17:29:06Z","timestamp":1788888546000},"page":"e0001646","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Topologically distinct intratumoral heterogeneity scores for predicting high-risk pathological grades in invasive lung adenocarcinoma: A multicenter study across four institutions"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5608-9978","authenticated-orcid":true,"given":"Shanyue","family":"Lin","sequence":"first","affiliation":[{"name":"Xiangtan Central Hospital(The Affiliated Hospital of Hunan University)","place":["Xiangtan, Hunan, China"],"department":["Department of Radiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudian","family":"Mao","sequence":"additional","affiliation":[{"name":"Xiangtan Central Hospital(The Affiliated Hospital of Hunan University)","place":["Xiangtan, Hunan, China"],"department":["Department of Radiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[{"name":"Xiangtan Central Hospital(The Affiliated Hospital of Hunan University)","place":["Xiangtan, Hunan, China"],"department":["Department of Radiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanyin","family":"Qi","sequence":"additional","affiliation":[{"name":"The Affiliated Hospital of Southwest Medical University","place":["Luzhou, Sichuan, China"],"department":["Department of Radiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Liuyang Hospital of Traditional Chinese Medicine","place":["Changsha, Hunan, China"],"department":["Department of Radiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7267-6494","authenticated-orcid":true,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"The Third Xiangya Hospital of Central South University","place":["Changsha, Hunan, China"],"department":["Department of Radiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4824-6138","authenticated-orcid":true,"given":"Zhichao","family":"Zuo","sequence":"additional","affiliation":[{"name":"Xiangtan Central Hospital(The Affiliated Hospital of Hunan University)","place":["Xiangtan, Hunan, China"],"department":["Department of Radiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"issue":"1","key":"pdig.0001646.ref001","first-page":"39","article-title":"The 2015 World Health Organization Classification of lung tumors: new entities since the 2004 Classification","volume":"110","author":"M Mengoli","year":"2018","journal-title":"Pathologica"},{"issue":"9","key":"pdig.0001646.ref002","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1097\/JTO.0000000000000630","article-title":"The 2015 World Health Organization classification of lung tumors: impact of genetic, clinical and radiologic advances since the 2004 classification","volume":"10","author":"WD Travis","year":"2015","journal-title":"J Thorac Oncol"},{"key":"pdig.0001646.ref003","article-title":"The new IASLC\/ATS\/ERS lung adenocarcinoma classification from a clinical perspective: current concepts and future prospects","volume":"6","author":"J Zugazagoitia","year":"2014","journal-title":"J Thorac Dis"},{"key":"pdig.0001646.ref004","doi-asserted-by":"crossref","first-page":"15330338261429796","DOI":"10.1177\/15330338261429796","article-title":"Robustness and accuracy of radiomics models for classifying IASLC grading in lung adenocarcinomas: a comprehensive analysis of a large multicenter CT database","volume":"25","author":"X Fan","year":"2026","journal-title":"Technol Cancer Res Treat"},{"issue":"6","key":"pdig.0001646.ref005","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1007\/s11596-022-2672-7","article-title":"Development and validation of a nomogram for predicting the 1-, 3-, and 5-year survival in patients with acinar-predominant lung adenocarcinoma","volume":"42","author":"Z-C Zuo","year":"2022","journal-title":"Curr Med Sci"},{"issue":"5","key":"pdig.0001646.ref006","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1007\/s00408-022-00561-y","article-title":"Impact of high-grade patterns in early-stage lung adenocarcinoma: a multicentric analysis","volume":"200","author":"P Bertoglio","year":"2022","journal-title":"Lung"},{"issue":"16","key":"pdig.0001646.ref007","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.1093\/jnci\/djt166","article-title":"Impact of micropapillary histologic subtype in selecting limited resection vs lobectomy for lung adenocarcinoma of 2cm or smaller","volume":"105","author":"J Nitadori","year":"2013","journal-title":"J Natl Cancer Inst"},{"issue":"30","key":"pdig.0001646.ref008","doi-asserted-by":"crossref","first-page":"3439","DOI":"10.1200\/JCO.2014.58.8335","article-title":"Subtype classification of lung adenocarcinoma predicts benefit from adjuvant chemotherapy in patients undergoing complete resection","volume":"33","author":"M-S Tsao","year":"2015","journal-title":"J Clin Oncol"},{"issue":"10335","key":"pdig.0001646.ref009","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1016\/S0140-6736(21)02333-3","article-title":"Segmentectomy versus lobectomy in small-sized peripheral non-small-cell lung cancer (JCOG0802\/WJOG4607L): a multicentre, open-label, phase 3, randomised, controlled, non-inferiority trial","volume":"399","author":"H Saji","year":"2022","journal-title":"Lancet"},{"key":"pdig.0001646.ref010","doi-asserted-by":"crossref","first-page":"107990","DOI":"10.1016\/j.lungcan.2024.107990","article-title":"Segmentectomy vs. Lobectomy in stage IA non-small cell lung cancer: a systematic review and meta-analysis of perioperative and survival outcomes","volume":"197","author":"L Bertolaccini","year":"2024","journal-title":"Lung Cancer"},{"issue":"1","key":"pdig.0001646.ref011","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1186\/s12880-025-01700-6","article-title":"Efficacy of CEUS-guided biopsy for thoracic and pulmonary lesions: a systematic review and meta-analysis","volume":"25","author":"Z Sun","year":"2025","journal-title":"BMC Med Imaging"},{"issue":"3","key":"pdig.0001646.ref012","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1148\/radiol.2016142975","article-title":"Lung adenocarcinoma: correlation of quantitative CT findings with pathologic findings","volume":"280","author":"JP Ko","year":"2016","journal-title":"Radiology"},{"issue":"3","key":"pdig.0001646.ref013","doi-asserted-by":"crossref","DOI":"10.1016\/j.crad.2022.11.011","article-title":"Association of CT findings with invasive subtypes and the new grading system of lung adenocarcinoma","volume":"78","author":"K Volmonen","year":"2023","journal-title":"Clin Radiol"},{"issue":"1","key":"pdig.0001646.ref014","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1186\/s12890-023-02690-3","article-title":"A pretreatment prediction model of grade 3 tumors classed by the IASLC grading system in lung adenocarcinoma","volume":"23","author":"K Wang","year":"2023","journal-title":"BMC Pulm Med"},{"issue":"1","key":"pdig.0001646.ref015","first-page":"013504","article-title":"Systematic analysis of bias and variability of morphologic features for lung lesions in computed tomography","volume":"6","author":"J Hoye","year":"2019","journal-title":"J Med Imaging (Bellingham)"},{"key":"pdig.0001646.ref016","doi-asserted-by":"crossref","first-page":"1406166","DOI":"10.3389\/fonc.2024.1406166","article-title":"Predicting pathological grade of stage I pulmonary adenocarcinoma: a CT radiomics approach","volume":"14","author":"X Huang","year":"2024","journal-title":"Front Oncol"},{"key":"pdig.0001646.ref017","doi-asserted-by":"crossref","first-page":"15330338241300734","DOI":"10.1177\/15330338241300734","article-title":"Radiomics nomogram based on optimal volume of interest derived from high-resolution CT for preoperative prediction of IASLC grading in clinical IA lung adenocarcinomas: a multi-center, large-population study","volume":"23","author":"Z Zuo","year":"2024","journal-title":"Technol Cancer Res Treat"},{"issue":"9","key":"pdig.0001646.ref018","doi-asserted-by":"crossref","first-page":"1946","DOI":"10.1016\/j.acra.2022.12.006","article-title":"A CT-based radiomics nomogram combined with clinic-radiological characteristics for preoperative prediction of the novel IASLC grading of invasive pulmonary adenocarcinoma","volume":"30","author":"Z Yang","year":"2023","journal-title":"Acad Radiol"},{"issue":"1","key":"pdig.0001646.ref019","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/s12885-025-13445-0","article-title":"Quantifying intratumoral heterogeneity within sub-regions to predict high-grade patterns in clinical stage I solid lung adenocarcinoma","volume":"25","author":"Z Zuo","year":"2025","journal-title":"BMC Cancer"},{"key":"pdig.0001646.ref020","doi-asserted-by":"crossref","first-page":"109337","DOI":"10.1016\/j.cmpb.2026.109337","article-title":"Dual-branch attention-enhanced network integrating CT images and clinicoradiographic features for preoperative ternary classification of IASLC grading in lung adenocarcinoma: a multicenter study","volume":"280","author":"Z Zuo","year":"2026","journal-title":"Comput Methods Programs Biomed"},{"key":"pdig.0001646.ref021","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.phro.2021.10.007","article-title":"A systematic review and quality of reporting checklist for repeatability and reproducibility of radiomic features","volume":"20","author":"E Pfaehler","year":"2021","journal-title":"Phys Imaging Radiat Oncol"},{"issue":"2","key":"pdig.0001646.ref022","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"A Zwanenburg","year":"2020","journal-title":"Radiology"},{"issue":"10","key":"pdig.0001646.ref023","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1016\/j.diii.2020.09.001","article-title":"Interobserver agreement issues in radiology","volume":"101","author":"M Benchoufi","year":"2020","journal-title":"Diagn Interv Imaging"},{"key":"pdig.0001646.ref024","unstructured":"Neha F, Shukla DK. Radiomics in medical imaging: methods, applications, and challenges. arXiv preprint arXiv:260200102. 2026. https:\/\/arxiv.org\/abs\/2602.00102"},{"issue":"2","key":"pdig.0001646.ref025","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1007\/s00330-022-09055-0","article-title":"ITHscore: comprehensive quantification of intra-tumor heterogeneity in NSCLC by multi-scale radiomic features","volume":"33","author":"J Li","year":"2023","journal-title":"Eur Radiol"},{"issue":"10","key":"pdig.0001646.ref026","doi-asserted-by":"crossref","first-page":"4244","DOI":"10.1016\/j.acra.2024.04.008","article-title":"Quantification of intratumoral heterogeneity: distinguishing histological subtypes in clinical T1 stage lung adenocarcinoma presenting as pure ground-glass nodules on computed tomography","volume":"31","author":"J Zhang","year":"2024","journal-title":"Acad Radiol"},{"key":"pdig.0001646.ref027","doi-asserted-by":"crossref","first-page":"20552076241289181","DOI":"10.1177\/20552076241289181","article-title":"Enhancing the prediction of the invasiveness of pulmonary adenocarcinomas presenting as pure ground-glass nodules: Integrating intratumor heterogeneity score with clinical-radiological features via machine learning in a multicenter study","volume":"10","author":"H Zheng","year":"2024","journal-title":"Digit Health"},{"issue":"1","key":"pdig.0001646.ref028","doi-asserted-by":"crossref","first-page":"272","DOI":"10.21037\/qims-24-734","article-title":"Assessment of intratumor heterogeneity for preoperatively predicting the invasiveness of pulmonary adenocarcinomas manifesting as pure ground-glass nodules","volume":"15","author":"H Qi","year":"2025","journal-title":"Quant Imag Med Surg"},{"issue":"1","key":"pdig.0001646.ref029","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1186\/s13244-025-02097-0","article-title":"Intratumoral heterogeneity score enhances invasiveness prediction in pulmonary ground-glass nodules via stacking ensemble machine learning","volume":"16","author":"Z Zuo","year":"2025","journal-title":"Insights Imaging"},{"key":"pdig.0001646.ref030","doi-asserted-by":"crossref","first-page":"109137","DOI":"10.1016\/j.cmpb.2025.109137","article-title":"Multiperspective tumor heterogeneity metrics for preoperative prediction of IASLC grading in clinical stage IA lung adenocarcinomas: a multicenter study","volume":"274","author":"Z Zuo","year":"2026","journal-title":"Comput Methods Programs Biomed"},{"key":"pdig.0001646.ref031","doi-asserted-by":"crossref","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Y Nohara","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"issue":"2","key":"pdig.0001646.ref032","article-title":"Topologically distinct 2D and 3D intratumoral heterogeneity scores for preoperatively predicting invasiveness in stage I lung adenocarcinoma: a multicenter study","volume":"5","author":"Z Zuo","year":"2026","journal-title":"PLOS Digit Health"},{"issue":"5","key":"pdig.0001646.ref033","doi-asserted-by":"crossref","first-page":"111756","DOI":"10.1016\/j.ejso.2026.111756","article-title":"Preoperative CT-based topologically distinct intratumoral heterogeneity scores for predicting intratumoral tertiary lymphoid structures and outcomes in hepatocellular carcinoma: a multicenter study","volume":"52","author":"J Zhao","year":"2026","journal-title":"Eur J Surg Oncol"},{"key":"pdig.0001646.ref034","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"SM Lundberg","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"pdig.0001646.ref035","doi-asserted-by":"crossref","first-page":"15330338251351365","DOI":"10.1177\/15330338251351365","article-title":"Ensemble machine learning classifiers combining CT radiomics and clinical-radiological features for preoperative prediction of pathological invasiveness in lung adenocarcinoma presenting as part-solid nodules: a multicenter retrospective study","volume":"24","author":"Y Li","year":"2025","journal-title":"Technol Cancer Res Treat"},{"issue":"1","key":"pdig.0001646.ref036","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1186\/s12885-025-14259-w","article-title":"Stacking classifiers based on integrated machine learning model: fusion of CT radiomics and clinical biomarkers to predict lymph node metastasis in locally advanced gastric cancer patients after neoadjuvant chemotherapy","volume":"25","author":"T Ling","year":"2025","journal-title":"BMC Cancer"},{"issue":"7","key":"pdig.0001646.ref037","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6560\/aab4b1","article-title":"Receiver operating characteristic (ROC) curves: review of methods with applications in diagnostic medicine","volume":"63","author":"NA Obuchowski","year":"2018","journal-title":"Phys Med Biol"},{"key":"pdig.0001646.ref038","unstructured":"Zwanenburg A, Leger S, Valli\u00e8res M, L\u00f6ck S. The image biomarker standardisation initiative\u2014IBSI 0.0. 1dev documentation 2019. ProQuest Number: INFORMATION TO ALL USERS. 2021."},{"issue":"9","key":"pdig.0001646.ref039","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1080\/17476348.2024.2324083","article-title":"Advances in lung cancer surgery: the role of segmentectomy in early-stage management","volume":"18","author":"L Bertolaccini","year":"2024","journal-title":"Expert Rev Respir Med"},{"issue":"5","key":"pdig.0001646.ref040","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1055\/a-2649-9277","article-title":"Surgical therapy for stage i lung cancer-lobar versus sublobar resection","volume":"46","author":"S Rudasill","year":"2025","journal-title":"Semin Respir Crit Care Med"},{"issue":"10","key":"pdig.0001646.ref041","doi-asserted-by":"crossref","first-page":"2709","DOI":"10.3390\/cancers15102709","article-title":"Intratumoral heterogeneity in lung cancer","volume":"15","author":"X Lv","year":"2023","journal-title":"Cancers (Basel)"},{"key":"pdig.0001646.ref042","doi-asserted-by":"crossref","unstructured":"Neha F, Bhati D, Shukla DK. Phenotyping of histology imaging data with histomics. Preprints. 2026. https:\/\/doi.org\/10.20944\/preprints202604.1359.v1","DOI":"10.20944\/preprints202604.1359.v1"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T17:29:13Z","timestamp":1788888553000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001646"}},"subtitle":[],"editor":[{"given":"Ashkan","family":"Ebadi","sequence":"first","affiliation":[{"name":"National Research Council Canada","place":["CANADA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":42,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001646","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]}}}