{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:52:24Z","timestamp":1791827544188,"version":"4.3.4"},"reference-count":21,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Lung cancer is one of the leading causes of cancer-related mortality worldwide, emphasizing the need for accurate, automated, and clinically interpretable diagnostic systems. Although existing deep learning (DL) models have achieved promising performance in classifying lung nodules as benign or malignant, most approaches are limited to binary classification and provide insufficient support for detailed tumor characterization and TNM staging. Furthermore, conventional convolutional neural networks (CNNs) are effective in extracting local morphological features but often fail to capture long-range spatial dependencies. In contrast, transformer-based models can learn global contextual information but may compromise fine-grained local feature representation. To address these limitations, this study proposes a hybrid ResNet-50\u2013Vision Transformer with Radiomic Feature Fusion (ReViT-RF) framework for lung tumor classification and component-wise TNM stage prediction using thoracic computed tomography (CT) images from the publicly available Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset. The primary clinical objectives of the proposed framework are to: (i) classify pulmonary nodules as benign or malignant, and (ii) predict individual TNM components, including primary tumor extent (T), lymph node involvement (N), and metastatic status (M) for malignant cases. To improve tumor visibility and image quality, CT images are initially preprocessed using Contrast-Limited Adaptive Histogram Equalization (CLAHE) and intensity normalization. The proposed ReViT-RF architecture integrates the complementary advantages of ResNet-50 and Vision Transformer (ViT) for comprehensive feature learning. The CNN branch extracts local morphological, textural, and structural characteristics, whereas the transformer branch captures long-range spatial relationships and global contextual dependencies. In addition, handcrafted radiomic features, including shape, size, texture, and spatial descriptors, are fused with deep features to provide clinically meaningful information for accurate TNM component prediction. The dataset is divided into training, validation, and testing subsets using an 80:10:10 ratio, with data augmentation applied only to the training set to prevent information leakage. Experimental results demonstrate that the proposed framework achieves an accuracy of 97.62% for benign\u2013malignant classification, along with high precision, recall, and F1-score values. Moreover, independent prediction of TNM components provides detailed stage-related information rather than relying on a single aggregated stage label, enabling more precise tumor assessment and clinical decision support. Furthermore, explainability analysis using Gradient-weighted Class Activation Mapping (Grad-CAM) identifies the critical tumor regions contributing to model predictions, improving interpretability and enhancing clinician confidence. Overall, by combining hybrid deep feature extraction, radiomic feature fusion, component-wise TNM stage prediction, and explainable AI analysis, the proposed ReViT-RF framework provides a reliable, comprehensive, and clinically interpretable solution for automated lung tumor analysis.<\/jats:p>","DOI":"10.1371\/journal.pone.0359211","type":"journal-article","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:33:56Z","timestamp":1791826436000},"page":"e0359211","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["ReViT-RF: A hybrid ResNet-50\u2013Vision Transformer with a Radiomic Feature Fusion framework for lung tumor classification and TNM-based stage prediction using CT images"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5984-5162","authenticated-orcid":true,"given":"Shobharani","family":"DA","sequence":"first","affiliation":[{"name":"GITAM School of Computer Science and Engineering","place":["Bangalore, Karnataka, India"],"department":["Department of Computer Science and Systems Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramesh Naik","family":"B","sequence":"additional","affiliation":[{"name":"GITAM School of Computer Science and Engineering","place":["Bangalore, Karnataka, India"],"department":["Department of Computer Science and Systems Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,12]]},"reference":[{"key":"pone.0359211.ref001","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"F Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"issue":"3","key":"pone.0359211.ref002","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/j.annonc.2023.12.003","article-title":"European cancer mortality predictions for the year 2024 with focus on colorectal cancer","volume":"35","author":"C Santucci","year":"2024","journal-title":"Ann Oncol"},{"issue":"4","key":"pone.0359211.ref003","doi-asserted-by":"crossref","first-page":"220147","DOI":"10.1183\/20734735.0147-2022","article-title":"Idiopathic pulmonary fibrosis and lung cancer: Future directions and challenges","volume":"18","author":"A Abu Qubo","year":"2022","journal-title":"Breathe (Sheff)"},{"issue":"1","key":"pone.0359211.ref004","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.jtho.2023.07.019","article-title":"Current and future perspectives on computed tomography screening for lung cancer: A roadmap from 2023 to 2027 from the International Association for the Study of Lung Cancer","volume":"19","author":"S Lam","year":"2024","journal-title":"J Thorac Oncol"},{"issue":"1","key":"pone.0359211.ref005","first-page":"50","article-title":"Screening for lung cancer: 2023 Guideline update from the American Cancer Society","volume":"74","author":"AMD Wolf","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"pone.0359211.ref006","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1002\/cncr.35128","article-title":"Lung cancer statistics 2023","volume":"130","author":"TB Kratzer","year":"2024","journal-title":"Cancer"},{"key":"pone.0359211.ref007","doi-asserted-by":"crossref","first-page":"107412","DOI":"10.1016\/j.lungcan.2023.107412","article-title":"The effect of the introduction of the national lung cancer screening program on short-term mortality in Korea","volume":"186","author":"W Kim","year":"2023","journal-title":"Lung Cancer"},{"issue":"1","key":"pone.0359211.ref008","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/s00408-023-00596-9","article-title":"Solitary lung nodule: CT-guided transthoracic biopsy vs transbronchial biopsy with endobronchial ultrasound and flexible bronchoscope, a meta-analysis of randomized controlled trials","volume":"201","author":"ATN Ho","year":"2023","journal-title":"Lung"},{"issue":"2","key":"pone.0359211.ref009","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1111\/1759-7714.14733","article-title":"Diagnostic yield of radial probe endobronchial ultrasonography-guided transbronchial biopsy without fluoroscopy in peripheral pulmonary lesions: A systematic review and meta-analysis","volume":"14","author":"J Lee","year":"2023","journal-title":"Thorac Cancer"},{"issue":"13","key":"pone.0359211.ref010","doi-asserted-by":"crossref","first-page":"2350","DOI":"10.3390\/cancers16132350","article-title":"Evolving precision first-line systemic treatment for patients with unresectable non-small cell lung cancer","volume":"16","author":"T Li","year":"2024","journal-title":"Cancers (Basel)"},{"issue":"9","key":"pone.0359211.ref011","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1513\/AnnalsATS.202111-1302OC","article-title":"Confirmatory mediastinoscopy after negative endobronchial ultrasound-guided transbronchial needle aspiration for mediastinal staging of lung cancer: Systematic review and meta-analysis","volume":"19","author":"J Sanz-Santos","year":"2022","journal-title":"Ann Am Thorac Soc"},{"issue":"6","key":"pone.0359211.ref012","doi-asserted-by":"crossref","first-page":"690","DOI":"10.3390\/bioengineering10060690","article-title":"Automated classification of lung cancer subtypes using deep learning and CT-scan based radiomic analysis","volume":"10","author":"B Dunn","year":"2023","journal-title":"Bioengineering (Basel)"},{"key":"pone.0359211.ref013","doi-asserted-by":"crossref","first-page":"60279","DOI":"10.1109\/ACCESS.2023.3285821","article-title":"Lung cancer classification using modified U-net based lobe segmentation and nodule detection","volume":"11","author":"I Naseer","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0359211.ref014","doi-asserted-by":"crossref","first-page":"59880","DOI":"10.1109\/ACCESS.2024.3394030","article-title":"Enhancing lung cancer classification and prediction with deep learning and multi-omics data","volume":"12","author":"TIA Mohamed","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0359211.ref015","doi-asserted-by":"crossref","unstructured":"Wahengbam M, Sriram M. Lung cancer classification using deep learning-based techniques. International Conference on Advancements in Smart Computing and Information Security. Cham: Springer Nature Switzerland; 2023. p. 390\u2013403. https:\/\/doi.org\/10.1007\/978-3-031-59097-9_29","DOI":"10.1007\/978-3-031-59097-9_29"},{"issue":"1","key":"pone.0359211.ref016","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/s11760-023-02635-7","article-title":"Classification of lung cancer with deep learning Res-U-Net and molecular imaging","volume":"18","author":"N Malligeswari","year":"2023","journal-title":"Signal Image Video Process"},{"issue":"2","key":"pone.0359211.ref017","doi-asserted-by":"crossref","first-page":"2049","DOI":"10.1007\/s44174-025-00335-z","article-title":"Deep learning-based lung cancer histopathology classification: Emphasizing accuracy and customisation","volume":"4","author":"S Kashyap","year":"2025","journal-title":"Biomed Mater Devices"},{"key":"pone.0359211.ref018","doi-asserted-by":"crossref","first-page":"4185835","DOI":"10.1155\/2022\/4185835","article-title":"Cloud\u2010based lung tumor detection and stage classification using deep learning techniques","volume":"1","author":"G Kasinathan","year":"2022","journal-title":"Biomed Res Int"},{"issue":"9","key":"pone.0359211.ref019","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.13607","article-title":"Lung cancer computed tomography image classification using Attention based Capsule Network with dispersed dynamic routing","volume":"41","author":"R Paramasivam","year":"2024","journal-title":"Expert Syst"},{"issue":"3","key":"pone.0359211.ref020","doi-asserted-by":"crossref","first-page":"523","DOI":"10.3390\/cancers17030523","article-title":"Overall staging prediction for non-small cell lung cancer (NSCLC): A local pilot study with artificial neural network approach","volume":"17","author":"EYW Cheung","year":"2025","journal-title":"Cancers (Basel)"},{"key":"pone.0359211.ref021"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:34:01Z","timestamp":1791826441000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359211"}},"subtitle":[],"editor":[{"given":"Subramani","family":"Neelakandan","sequence":"first","affiliation":[{"name":"Hanyang University - ERICA Campus","place":["KOREA, REPUBLIC OF"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,12]]},"references-count":21,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359211","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,12]]}}}