{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T16:14:18Z","timestamp":1790612058067,"version":"4.1.0"},"reference-count":62,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Pneumonia remains a leading cause of morbidity and mortality worldwide, particularly among children and older adults, making rapid and reliable interpretation of chest X-rays essential for timely clinical decision-making. This study proposes HybridCATNet, an explainable and uncertainty-aware deep learning framework for automated pneumonia detection from chest radiographs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>HybridCATNet integrates a convolutional neural network and a vision transformer to capture both fine-grained local radiographic features and long-range anatomical dependencies. To incorporate clinically relevant image priors, a nine-channel early multi-channel fusion strategy combines raw grayscale chest radiographs, lung-segmented masks, and edge-enhanced structural maps. A Cascaded Spatial\u2013Channel Attention Module further refines diagnostic feature representation, while Bayesian dropout is employed during inference to estimate predictive uncertainty. The model was trained and evaluated on a balanced multi-institutional dataset comprising 8,478 authentic chest radiographs without synthetic oversampling using 10-fold cross-validation. Generalizability was further assessed on two independent external validation cohorts. Explainability was evaluated using Grad-CAM and SHAP.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>HybridCATNet achieved an area under the receiver operating characteristic curve (ROC-AUC) of 0.9953, an accuracy of 96.93%, a sensitivity of 98.13%, and a specificity of 95.72% in 10-fold cross-validation. External validation demonstrated robust cross-domain performance, with an accuracy of at least 94.8% across both independent cohorts. Explainability analysis showed strong agreement between model-generated attention maps and radiologist-annotated pathological regions, achieving an intersection-over-union of 0.812 and a faithfulness correlation of 0.921.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results demonstrate that HybridCATNet provides accurate, interpretable, and uncertainty-aware pneumonia detection while maintaining strong generalization across external datasets. By integrating multi-channel image fusion, hybrid CNN\u2013Transformer feature learning, attention-guided refinement, predictive uncertainty estimation, and explainability, the proposed framework offers a clinically transparent decision-support approach with potential to assist pneumonia screening and improve confidence in AI-assisted radiographic diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdgth.2026.1769444","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T05:52:05Z","timestamp":1784699525000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["HybridCATNet: an explainable CNN\u2013Transformer framework with early multi-channel fusion and uncertainty estimation for pneumonia detection from chest X-rays"],"prefix":"10.3389","volume":"8","author":[{"family":"Abdullah","sequence":"first","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN)","place":["Mexico City, Mexico"]},{"name":"Department of Computer Sciences, Bahria University","place":["Lahore, Pakistan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Ateeb","family":"Ather","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, Bahria University","place":["Lahore, Pakistan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kinza","family":"Sardar","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, University of Management and Technology","place":["Lahore, Pakistan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zulaikha","family":"Fatima","sequence":"additional","affiliation":[{"name":"Faculty of Allied Health Sciences, Superior University, Lahore Campus","place":["Lahore, Pakistan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9 Luis Oropeza","family":"Rodr\u00edguez","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN)","place":["Mexico City, Mexico"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos Guzm\u00e1n","family":"S\u00e1nchez-Mejorada","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN)","place":["Mexico City, Mexico"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rolando Quintero","family":"T\u00e9llez","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN)","place":["Mexico City, Mexico"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miguel Jes\u00fas","family":"Torres Ruiz","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN)","place":["Mexico City, Mexico"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s44263-023-00033-2","article-title":"Early user perspectives on using computer-aided detection software for interpreting chest X-ray images to enhance access and quality of care for persons with tuberculosis","volume":"1","author":"Creswell","year":"2023","journal-title":"BMC Global Public Health"},{"key":"B2","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.jmir.2021.04.002","article-title":"Inter-rater reliability in quality assurance (QA) of pediatric chest X-rays","volume":"52","author":"Hlabangana","year":"2021","journal-title":"J Med Imaging Radiat Sci"},{"key":"B3","first-page":"465","article-title":"Enhancing pneumonia detection transparency: exploring an explainable AI model","volume-title":"International Conference on Power Engineering and Intelligent Systems (PEIS)","author":"Ambaliya","year":"2024"},{"key":"B4","doi-asserted-by":"publisher","first-page":"314","DOI":"10.3390\/cancers15010314","article-title":"An explainable AI-enabled framework for interpreting pulmonary diseases from chest radiographs","volume":"15","author":"Naz","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B5","doi-asserted-by":"publisher","first-page":"3233","DOI":"10.3390\/app10093233","article-title":"Transfer learning with a deep convolutional neural network (CNN) for pneumonia detection using chest X-ray","volume":"10","author":"Rahman","year":"2020","journal-title":"Appl Sci"},{"key":"B6","doi-asserted-by":"crossref","first-page":"263","DOI":"10.4018\/979-8-3693-9816-6.ch011","article-title":"Convolutional neural networks (CNNs) for medical imaging: revolutionizing diagnostic accuracy and treatment planning","volume-title":"Deep Learning in Medical Signal and Image Processing","author":"Aishwarya","year":"2025"},{"key":"B7","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-025-01114-9","article-title":"Breast cancer diagnosis with MFF-HistoNet: a multi-modal feature fusion network integrating CNNs and quantum tensor networks","volume":"12","author":"Mahmood","year":"2025","journal-title":"J Big Data"},{"key":"B8","doi-asserted-by":"publisher","first-page":"156","DOI":"10.3390\/computers15030156","article-title":"A leakage-aware multimodal machine learning framework for nutrition supply\u2013demand forecasting using temporal and spatial data fusion","volume":"15","author":"Abdullah","year":"2026","journal-title":"Computers"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e38","DOI":"10.1002\/mef2.38","article-title":"Recent advances of transformers in medical image analysis: a comprehensive review","volume":"2","author":"Xia","year":"2023","journal-title":"MedComm\u2013Future Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"8747","DOI":"10.21037\/qims-23-542","article-title":"Transformers in medical image segmentation: a narrative review","volume":"13","author":"Khan","year":"2023","journal-title":"Quant Imaging Med Surg"},{"key":"B11","author":"Carr","year":"2025"},{"key":"B12","author":"Kimera","year":"2024"},{"key":"B13","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s40537-022-00648-6","article-title":"The use of generative adversarial networks to alleviate class imbalance in tabular data: a survey","volume":"9","author":"Sauber-Cole","year":"2022","journal-title":"J Big Data"},{"key":"B14","first-page":"24024","article-title":"Teaching AI the anatomy behind the scan: addressing anatomical flaws in medical image segmentation with learnable prior","author":"Jeon","year":"2025"},{"key":"B15","doi-asserted-by":"publisher","first-page":"2692","DOI":"10.1109\/TIP.2018.2889531","article-title":"Structure-texture image decomposition using deep variational priors","volume":"28","author":"Kim","year":"2018","journal-title":"IEEE Trans Image Process"},{"key":"B16","doi-asserted-by":"publisher","first-page":"34678","DOI":"10.1109\/ACCESS.2024.3372588","article-title":"Pneumonia detection using chest radiographs with novel EfficientNetV2L model","volume":"12","author":"Ali","year":"2024","journal-title":"IEEE Access"},{"key":"B17","doi-asserted-by":"publisher","first-page":"611","DOI":"10.3390\/info15100611","article-title":"Pneumonia image classification using DenseNet architecture","volume":"15","author":"Bundea","year":"2024","journal-title":"Information"},{"key":"B18","doi-asserted-by":"publisher","first-page":"12","DOI":"10.7759\/cureus.99649","article-title":"Squeeze-and-Excitation enhanced convolutional neural networks for multi-class pneumonia classification on chest radiographs","volume":"17","author":"Huang","year":"2025","journal-title":"Cureus"},{"key":"B19","doi-asserted-by":"publisher","first-page":"3996","DOI":"10.11591\/ijece.v15i4.pp3996-4003","article-title":"Multi-class pneumonia detection using fine-tuned vision transformer model","volume":"15","author":"Trivedi","year":"2025","journal-title":"Int J Electr Comput Eng"},{"key":"B20","doi-asserted-by":"publisher","first-page":"4580","DOI":"10.3390\/s25154580","article-title":"Segmentation-assisted fusion-based classification for automated CXR image analysis","volume":"25","author":"Kang","year":"2025","journal-title":"Sensors"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1522730","article-title":"Approach for enhancing the accuracy of semantic segmentation of chest X-ray images by edge detection and deep learning integration","volume":"8","author":"Mochurad","year":"2025","journal-title":"Front Artif Intell"},{"key":"B22","author":"Sloan","year":"2025"},{"key":"B23","doi-asserted-by":"publisher","first-page":"332","DOI":"10.30871\/jaic.v8i2.8426","article-title":"Application of MobileNetV2 and SVM combination for enhanced accuracy in pneumonia classification","volume":"8","author":"Meindiawan","year":"2024","journal-title":"J Appl Informat Comput"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0323239","article-title":"An optimized transformer model for efficient detection of thoracic diseases in chest X-rays with multi-scale feature fusion","volume":"20","author":"Yu","year":"2025","journal-title":"PLoS One"},{"key":"B25","first-page":"1","article-title":"Attention-Enhanced CBAM-VGG-16 for optimized pneumonia detection in chest x-ray imaging","volume-title":"2025 IEEE International Conference on Computer, Electronics, Electrical Engineering & Their Applications (IC2E3)","author":"Sharma","year":"2025"},{"key":"B26","doi-asserted-by":"publisher","first-page":"3","DOI":"10.31449\/inf.v49i3.9065","article-title":"A novel CNN with spatial and channel attention for automated chest x-ray diagnosis","volume":"49","author":"Priyanka","year":"2025","journal-title":"Informatica"},{"key":"B27","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3991\/ijoe.v21i12.55953","article-title":"An attention-enhanced hybrid deep learning model based on VGG16 and VGG19 for pneumonia detection from chest x-ray images","volume":"21","author":"Mac","year":"2025","journal-title":"Int J Online Biomed Eng"},{"key":"B28","doi-asserted-by":"publisher","first-page":"114045","DOI":"10.1016\/j.asoc.2025.114045","article-title":"Medical image classification with KAN-integrated transformers and dilated neighborhood attention","volume":"186","author":"Manzari","year":"2025","journal-title":"Appl Soft Comput"},{"key":"B29","doi-asserted-by":"publisher","first-page":"055025","DOI":"10.1088\/2057-1976\/adebf5","article-title":"Dual-branch attention fusion network for pneumonia detection","volume":"11","author":"Li","year":"2025","journal-title":"Biomed Phys Eng Express"},{"key":"B30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CENIM64038.2024.10882716","article-title":"Ensemble CNN models for accurate pneumonia classification in chest x-ray images","volume-title":"2024 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM)","author":"Widiarto","year":"2024"},{"key":"B31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICETI4T63625.2025.11132185","article-title":"Pneumonia identification based on transfer learning over chest x-ray images","volume-title":"2025 International Conference on Emerging Trends in Industry 4.0 Technologies (ICETI4T)","author":"Khojare","year":"2025"},{"key":"B32","first-page":"153","article-title":"CoMViT: an efficient vision backbone for supervised classification in medical imaging","volume-title":"International Workshop on Medical Image Computing in Resource Constrained Settings","author":"Safdar","year":"2026"},{"key":"B33","doi-asserted-by":"publisher","first-page":"e180041","DOI":"10.1148\/ryai.2019180041","article-title":"Augmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia","volume":"1","author":"Shih","year":"2019","journal-title":"Radiol Artif Intell"},{"key":"B34","author":"Xu","year":"2024"},{"key":"B35","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12880-023-01177-1","article-title":"Attention-enhanced architecture for improved pneumonia detection in chest x-ray images","volume":"24","author":"Li","year":"2024","journal-title":"BMC Med Imaging"},{"key":"B36","first-page":"4700","article-title":"Densely connected convolutional networks","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","author":"Huang","year":"2017"},{"key":"B37","author":"Rajpurkar","year":"2017"},{"key":"B38","first-page":"108","article-title":"Advancing pneumonia classification and detection: comparative analysis of deep learning models using convolutional neural networks","author":"Shakeri","year":"2024"},{"key":"B39","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1002\/ima.22812","article-title":"A deep learning approach for classification of COVID and pneumonia using DenseNet-201","volume":"33","author":"Sanghvi","year":"2023","journal-title":"Int J Imaging Syst Technol"},{"key":"B40","doi-asserted-by":"publisher","first-page":"612","DOI":"10.3390\/info15100612","article-title":"Traumatic brain injury structure detection using advanced wavelet transformation fusion algorithm with proposed CNN-ViT","volume":"15","author":"Abdullah","year":"2024","journal-title":"Information"},{"key":"B41","doi-asserted-by":"publisher","first-page":"97","DOI":"10.3390\/computers15020097","article-title":"An interpretable multi-dataset learning framework for breast cancer prediction using clinical and biomedical tabular data","volume":"15","author":"Ather","year":"2026","journal-title":"Computers"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.3390\/cancers18081305","article-title":"AI-driven breast cancer diagnosis: a systematic review of imaging modalities, deep learning, and explainability","volume":"18","author":"Sabry","year":"2026","journal-title":"Cancers (Basel)"},{"key":"B43","doi-asserted-by":"publisher","first-page":"14721","DOI":"10.1038\/s41598-026-50418-0","article-title":"A novel intelligent hybrid reinforcement learning framework for autonomous decision making in complex health cognitive systems","volume":"16","author":"Abdullah","year":"2026","journal-title":"Sci Rep"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-026-55510-z","article-title":"Explainable and clinically audited hybrid self-supervised framework for multi-class DFU classification and mobile deployment","author":"Abdullah","year":"2026","journal-title":"Sci Rep"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1780837","DOI":"10.3389\/fmedt.2026.1780837","article-title":"Enhancing context-aware SARS disorder management: a proposed multi-agent simulation framework with machine learning and bio-sensor data integration","volume":"8","author":"Abdullah","year":"2026","journal-title":"Front Med Technol"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-026-51410-4","article-title":"An attention-enhanced ViT-HLNN hybrid ensemble framework for multi-class gastrointestinal disease classification","author":"Abdullah","year":"2026","journal-title":"Sci Rep"},{"key":"B47","doi-asserted-by":"publisher","first-page":"148","DOI":"10.3390\/technologies14030148","article-title":"Rhythmx\u2122: an interpretable self-supervised contrastive learning framework for heartbeat classification","volume":"14","author":"Abdullah","year":"2026","journal-title":"Technologies"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2939","DOI":"10.1007\/s00371-021-02166-7","article-title":"A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets","volume":"38","author":"Bayoudh","year":"2022","journal-title":"Vis Comput"},{"key":"B49","doi-asserted-by":"publisher","first-page":"515","DOI":"10.3390\/computers14120515","article-title":"Fair and explainable multitask deep learning on synthetic endocrine trajectories for real-time prediction of stress, performance, and neuroendocrine states","volume":"14","author":"Abdullah","year":"2025","journal-title":"Computers"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369","article-title":"ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","author":"Wang","year":"2017","journal-title":"IEEE CVPR"},{"key":"B51","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.procs.2023.01.018","article-title":"A deep learning based model for the detection of pneumonia from chest X-ray images using VGG-16 and neural networks","volume":"218","author":"Sharma","year":"2023","journal-title":"Procedia Comput Sci"},{"key":"B52","doi-asserted-by":"publisher","first-page":"9025","DOI":"10.1038\/s41598-023-35922-x","article-title":"Pneumonia detection with QCSA network on chest X-ray","volume":"13","author":"Singh","year":"2023","journal-title":"Sci Rep"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1561","DOI":"10.3390\/healthcare11111561","article-title":"Detection of pneumonia from chest X-ray images utilizing MobileNet model","volume":"11","author":"Reshan","year":"2023","journal-title":"Healthcare"},{"key":"B54","doi-asserted-by":"publisher","first-page":"390","DOI":"10.3390\/diagnostics14040390","article-title":"A deep convolutional neural network for pneumonia detection in X-ray images with attention ensemble","volume":"14","author":"An","year":"2024","journal-title":"Diagnostics"},{"key":"B55","doi-asserted-by":"publisher","first-page":"9821","DOI":"10.3390\/app15179821","article-title":"NGBoost classifier using deep features for pneumonia chest X-ray classification","volume":"15","author":"Satish Chandra","year":"2025","journal-title":"Appl Sci"},{"key":"B56","doi-asserted-by":"publisher","first-page":"e0256630","DOI":"10.1371\/journal.pone.0256630","article-title":"Pneumonia detection in chest X-ray images using an ensemble of deep learning models","volume":"16","author":"Kundu","year":"2021","journal-title":"PLoS One"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0273-z","article-title":"Automated abnormality classification of chest radiographs using deep convolutional neural networks","volume":"3","author":"Yu-Xing","year":"2020","journal-title":"npj Digit Med"},{"key":"B58","first-page":"1","article-title":"Investigation of pneumonia detection using convolutional neural networks","author":"Cic\u0117nas","year":"2022"},{"key":"B59","first-page":"757","article-title":"Learning to recognize abnormalities in chest x-rays with location-aware dense networks","volume-title":"Iberoamerican Congress on Pattern Recognition","author":"Guendel","year":"2018"},{"key":"B60","doi-asserted-by":"publisher","first-page":"6381","DOI":"10.1038\/s41598-019-42294-8","article-title":"Comparison of deep learning approaches for multi-label chest X-ray classification","volume":"9","author":"Baltruschat","year":"2019","journal-title":"Sci Rep"},{"key":"B61","doi-asserted-by":"publisher","first-page":"e1002683","DOI":"10.1371\/journal.pmed.1002683","article-title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study","volume":"15","author":"Zech","year":"2018","journal-title":"PLoS Med"},{"key":"B62","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1007\/s42600-022-00242-y","article-title":"COVID-19 detection using chest X-rays: is lung segmentation important for generalization?","volume":"38","author":"Bassi","year":"2022","journal-title":"Res Biomed Eng"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1769444\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T05:52:07Z","timestamp":1784699527000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1769444\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":62,"alternative-id":["10.3389\/fdgth.2026.1769444"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1769444","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]},"article-number":"1769444"}}