{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T18:15:17Z","timestamp":1783707317686,"version":"3.55.0"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["L252088"],"award-info":[{"award-number":["L252088"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate segmentation and classification of lung nodules in computed tomography (CT) scans remains a critical challenge in early lung cancer detection within distributed healthcare Internet of Things (IoT) environments. This paper presents a novel two-stage framework called Adaptive Geometric-Attention Network (AGA-Net) that integrates geometric constraints with multi-scale attention mechanisms for precise nodule segmentation followed by uncertainty-aware malignancy classification in federated learning scenarios. Unlike existing approaches that rely on traditional convolutional architectures, our method introduces a Geometric-Constrained Attention Module (GCAM) that leverages the spherical nature of lung nodules and a Multi-Scale Uncertainty Quantification Network (MUQ-Net) for robust classification under privacy-preserving constraints. The proposed framework demonstrates superior performance across three benchmark datasets: LUNA16, LIDC-IDRI, and NSCLC-Radiomics, achieving a Dice coefficient of 0.927 for segmentation and AUC of 0.951 for malignancy classification while maintaining computational efficiency validated on IoT-class edge hardware including the NVIDIA Jetson AGX Orin and Jetson Orin Nano. The integration of geometric priors with attention mechanisms, uncertainty quantification, and federated learning capabilities provides both high accuracy and clinical interpretability, making it suitable for next-generation computer-aided diagnosis systems deployable on healthcare IoT edge devices.<\/jats:p>","DOI":"10.1371\/journal.pone.0341096","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:40:51Z","timestamp":1783705251000},"page":"e0341096","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive geometric-attention network for two-stage lung nodule segmentation and malignancy classification in federated healthcare IoT edge environments"],"prefix":"10.1371","volume":"21","author":[{"given":"Muhammad","family":"Sufyan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Azhar","family":"Imran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad","family":"Sabah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0640-807X","authenticated-orcid":true,"given":"Raheem","family":"Sarwar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"issue":"1","key":"pone.0341096.ref001","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s11831-024-10141-3","article-title":"Lung Cancer Detection Systems Applied to Medical Images: A State-of-the-Art Survey","volume":"32","author":"SL Tan","year":"2024","journal-title":"Arch Computat Methods Eng"},{"issue":"3","key":"pone.0341096.ref002","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1007\/s42979-025-03799-4","article-title":"AttentNet: Fully convolutional 3D attention for lung nodule detection","volume":"6","author":"M Almahasneh","year":"2025","journal-title":"SN Computer Science"},{"issue":"2","key":"pone.0341096.ref003","doi-asserted-by":"crossref","DOI":"10.32604\/cmc.2023.046821","article-title":"Multilevel Attention Unet Segmentation Algorithm for Lung Cancer Based on CT Images","volume":"78","author":"H Wang","year":"2024","journal-title":"Computers, Materials & Continua"},{"issue":"32","key":"pone.0341096.ref004","doi-asserted-by":"crossref","first-page":"39747","DOI":"10.1007\/s11042-025-20752-y","article-title":"Optimizing pulmonary nodule segmentation in CT imaging: A comparative study of anchor-based and anchor-free detectors using attention mechanism","volume":"84","author":"KV Aishwarya","year":"2025","journal-title":"Multimedia Tools and Applications"},{"key":"pone.0341096.ref005","doi-asserted-by":"crossref","first-page":"27050","DOI":"10.1109\/ACCESS.2025.3539122","article-title":"Attention enhanced inceptionnext-based hybrid deep learning model for lung cancer detection","volume":"13","author":"B Ozdemir","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0341096.ref006","article-title":"Federated Online Learning with Filters for Lung Nodule Segmentation in Low-Dose Computed Tomography Images","author":"CS Lee","year":"2025","journal-title":"IEEE Intelligent Systems"},{"key":"pone.0341096.ref007","doi-asserted-by":"crossref","first-page":"107515","DOI":"10.1016\/j.bspc.2025.107515","article-title":"A multi-scale self-calibrating lung nodule detection based on SPC-UNet","volume":"104","author":"M Zhang","year":"2025","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0341096.ref008","doi-asserted-by":"crossref","first-page":"108132","DOI":"10.1016\/j.bspc.2025.108132","article-title":"Multi-scale information residual network: Deep residual network of prostate cancer segmentation based on multi scale information guidance","volume":"110","author":"X Chen","year":"2025","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0341096.ref009","doi-asserted-by":"crossref","first-page":"124149","DOI":"10.1016\/j.eswa.2024.124149","article-title":"Multiside graph neural network-based attention for local co-occurrence features fusion in lung nodule classification","volume":"252","author":"AA Saihood","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"pone.0341096.ref010","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s11831-024-10141-3","article-title":"Lung cancer detection systems applied to medical images: a state-of-the-art survey","volume":"32","author":"SL Tan","year":"2025","journal-title":"Archives of Computational Methods in Engineering"},{"key":"pone.0341096.ref011","article-title":"A two-stage U-Net framework for interactive segmentation of lung nodules in CT scans","author":"L Fernandes","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0341096.ref012","doi-asserted-by":"crossref","first-page":"3819","DOI":"10.1007\/s13042-024-02484-x","article-title":"An intelligent generative adversarial network multistage lung cancer detection and subtypes classification","volume":"16","author":"M Aharonu","year":"2024","journal-title":"Int J Mach Learn & Cyber"},{"key":"pone.0341096.ref013","doi-asserted-by":"crossref","first-page":"109613","DOI":"10.1016\/j.compbiomed.2024.109613","article-title":"Attention-guided CenterNet deep learning approach for lung cancer detection","volume":"186","author":"H Dawood","year":"2025","journal-title":"Comput Biol Med"},{"issue":"1","key":"pone.0341096.ref014","doi-asserted-by":"crossref","first-page":"4743","DOI":"10.1038\/s41598-024-55178-3","article-title":"An improved V-Net lung nodule segmentation model based on pixel threshold separation and attention mechanism","volume":"14","author":"X Ma","year":"2024","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0341096.ref015","doi-asserted-by":"crossref","first-page":"44","DOI":"10.21608\/ijaici.2025.335358.1002","article-title":"Review of lung cancer detection","volume":"1","author":"RM Mahmoud Ali","year":"2025","journal-title":"International Journal of Applied Intelligent Computing and Informatics"},{"issue":"22","key":"pone.0341096.ref016","doi-asserted-by":"crossref","first-page":"3777","DOI":"10.3390\/cancers16223777","article-title":"UCapsNet: A Two-Stage Deep Learning Model Using U-Net and Capsule Network for Breast Cancer Segmentation and Classification in Ultrasound Imaging","volume":"16","author":"G Madhu","year":"2024","journal-title":"Cancers (Basel)"},{"key":"pone.0341096.ref017","first-page":"409","article-title":"Presenting an automatic hierarchical method to segmentation of pulmonary nodules in CT-scan images","volume":"57","author":"M Asadi","year":"2025","journal-title":"AUT Journal of Electrical Engineering"},{"key":"pone.0341096.ref018","doi-asserted-by":"crossref","first-page":"106389","DOI":"10.1016\/j.bspc.2024.106389","article-title":"SF2T: Leveraging Swin Transformer and Two-stream Networks for Lung Nodule Detection","volume":"95","author":"F Cui","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0341096.ref019","doi-asserted-by":"crossref","first-page":"119756","DOI":"10.1109\/ACCESS.2024.3450492","article-title":"Efficient Two Stage Segmentation Framework for Chest X-Ray Images With U-Net Model Fusion","volume":"12","author":"C Sumathi","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0341096.ref020","doi-asserted-by":"crossref","unstructured":"Cai G, Zhang R, He H, Zhang Z, Ergu D, Cao Y. Msdet: Receptive field enhanced multiscale detection for tiny pulmonary nodule. In: 2025 IEEE International Conference on Multimedia and Expo (ICME), 2025. 1\u20136.","DOI":"10.1109\/ICME59968.2025.11209142"},{"issue":"9","key":"pone.0341096.ref021","doi-asserted-by":"crossref","first-page":"234","DOI":"10.3390\/jimaging10090234","article-title":"A Multi-Task Model for Pulmonary Nodule Segmentation and Classification","volume":"10","author":"T Tang","year":"2024","journal-title":"J Imaging"},{"key":"pone.0341096.ref022","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1016\/j.aej.2025.03.032","article-title":"CPLOYO: A pulmonary nodule detection model with multi-scale feature fusion and nonlinear feature learning","volume":"122","author":"M Wang","year":"2025","journal-title":"Alexandria Engineering Journal"},{"key":"pone.0341096.ref023","doi-asserted-by":"crossref","unstructured":"Murugan B, Dhanasekaran S, Kumar P. Automatic lung tumor volume estimation using PSO-TSVM method. In: 2024 IEEE International Conference on Communication, Computing and Signal Processing (IICCCS). IEEE. 2024. 1\u20136.","DOI":"10.1109\/IICCCS61609.2024.10763605"},{"key":"pone.0341096.ref024","unstructured":"Neelameghasri K, Mohan M, Pavitha U. Detection and classification of lung cancer using CNN models. In: 2024 5th International Conference on Circuits, Control, Communication and Computing (I4C). IEEE. 2024."},{"issue":"4","key":"pone.0341096.ref025","doi-asserted-by":"crossref","first-page":"1381","DOI":"10.1007\/s12530-023-09564-3","article-title":"Lung tumor cell classification with lightweight MobileNetV2 and attention-based SCAM enhanced faster R-CNN","volume":"15","author":"V Jenipher","year":"2024","journal-title":"Evolving Systems"},{"key":"pone.0341096.ref026","doi-asserted-by":"crossref","first-page":"112483","DOI":"10.1016\/j.asoc.2024.112483","article-title":"An intelligent model of pulmonary emphysema detection using adaptive image segmentation and multi-dilated densenet with attention mechanism","volume":"168","author":"I Linginani","year":"2025","journal-title":"Applied Soft Computing"},{"issue":"1","key":"pone.0341096.ref027","doi-asserted-by":"crossref","first-page":"12313","DOI":"10.1038\/s41598-025-97187-w","article-title":"Lung nodule detection using a multi-scale convolutional neural network and global channel spatial attention mechanisms","volume":"15","author":"Y Li","year":"2025","journal-title":"Sci Rep"},{"issue":"17","key":"pone.0341096.ref028","doi-asserted-by":"crossref","first-page":"25450","DOI":"10.1007\/s11227-024-06381-6","article-title":"Deformable attention mechanism-based YOLOv7 structure for lung nodule detection","volume":"80","author":"Y Liu","year":"2024","journal-title":"J Supercomput"},{"key":"pone.0341096.ref029","unstructured":"Ramezani H. Transformer-Based CT Anomaly Detection and Auto-Segmentation of Sparse Lung Nodules."},{"key":"pone.0341096.ref030","first-page":"65","volume-title":"Informatics","author":"Y Zamanidoost","year":"2025"},{"key":"pone.0341096.ref031","doi-asserted-by":"crossref","first-page":"107371","DOI":"10.1016\/j.bspc.2024.107371","article-title":"GSC-DVIT: A vision transformer based deep learning model for lung cancer classification in CT images","volume":"103","author":"D Mannepalli","year":"2025","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0341096.ref032","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1201\/9781032699806-7","article-title":"Metaheuristics and deep learning in lung nodule detection and classification","volume-title":"Metaheuristics for enterprise data intelligence","author":"RV Kaulgud","year":"2024"},{"issue":"5","key":"pone.0341096.ref033","doi-asserted-by":"crossref","first-page":"2127","DOI":"10.1007\/s11042-024-20009-0","article-title":"A survey on comparative study of lung nodules applying machine learning and deep learning techniques","volume":"84","author":"KV Aishwarya","year":"2025","journal-title":"Multimedia Tools and Applications"},{"key":"pone.0341096.ref034","doi-asserted-by":"crossref","first-page":"1435041","DOI":"10.3389\/fonc.2024.1435041","article-title":"An integrated method for detecting lung cancer via CT scanning via optimization, deep learning, and IoT data transmission","volume":"14","author":"S Karimullah","year":"2024","journal-title":"Front Oncol"},{"key":"pone.0341096.ref035","doi-asserted-by":"crossref","first-page":"119039","DOI":"10.1109\/ACCESS.2024.3447697","article-title":"Pulmonary nodule segmentation using deep learning: A review","volume":"12","author":"Y Wang","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0341096.ref036","doi-asserted-by":"crossref","unstructured":"Cai G, Cai Y, Zhang Z, Cao Y, Wu L, Ergu D. Medical ai for early detection of lung cancer: A survey. In: 2024. https:\/\/doi.org\/arXiv:241014769","DOI":"10.1016\/j.engappai.2025.111577"},{"issue":"14","key":"pone.0341096.ref037","doi-asserted-by":"crossref","first-page":"8141","DOI":"10.1007\/s00521-024-09425-3","article-title":"Dual-stage classification for lung cancer detection and staging using hybrid deep learning techniques","volume":"36","author":"J Subash","year":"2024","journal-title":"Neural Computing and Applications"},{"issue":"8","key":"pone.0341096.ref038","doi-asserted-by":"crossref","first-page":"5526","DOI":"10.21037\/qims-24-234","article-title":"Fully automated classification of pulmonary nodules in positron emission tomography-computed tomography imaging using a two-stage multimodal learning approach","volume":"14","author":"T Li","year":"2024","journal-title":"Quant Imaging Med Surg"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0341096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:41:00Z","timestamp":1783705260000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0341096"}},"subtitle":[],"editor":[{"given":"Abdel-Razzak M.","family":"Al-Hinnawi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":38,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,10]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0341096","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]}}}