{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T19:47:50Z","timestamp":1784576870649,"version":"3.55.0"},"reference-count":60,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,5,2]],"date-time":"2024-05-02T00:00:00Z","timestamp":1714608000000},"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. Big Data"],"abstract":"<jats:p>Chest X-ray (CXR) imaging is widely employed by radiologists to diagnose thoracic diseases. Recently, many deep learning techniques have been proposed as computer-aided diagnostic (CAD) tools to assist radiologists in minimizing the risk of incorrect diagnosis. From an application perspective, these models have exhibited two major challenges: (1) They require large volumes of annotated data at the training stage and (2) They lack explainable factors to justify their outcomes at the prediction stage. In the present study, we developed a class activation mapping (CAM)-based ensemble model, called Ensemble-CAM, to address both of these challenges via weakly supervised learning by employing explainable AI (XAI) functions. Ensemble-CAM utilizes class labels to predict the location of disease in association with interpretable features. The proposed work leverages ensemble and transfer learning with class activation functions to achieve three objectives: (1) minimizing the dependency on strongly annotated data when locating thoracic diseases, (2) enhancing confidence in predicted outcomes by visualizing their interpretable features, and (3) optimizing cumulative performance via fusion functions. Ensemble-CAM was trained on three CXR image datasets and evaluated through qualitative and quantitative measures via heatmaps and Jaccard indices. The results reflect the enhanced performance and reliability in comparison to existing standalone and ensembled models.<\/jats:p>","DOI":"10.3389\/fdata.2024.1366415","type":"journal-article","created":{"date-parts":[[2024,5,2]],"date-time":"2024-05-02T04:54:29Z","timestamp":1714625669000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Toward explainable AI in radiology: Ensemble-CAM for effective thoracic disease localization in chest X-ray images using weak supervised learning"],"prefix":"10.3389","volume":"7","author":[{"given":"Muhammad","family":"Aasem","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Javed Iqbal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,5,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"4765","DOI":"10.3390\/math10244765","article-title":"A survey on tools and techniques for localizing abnormalities in X-ray images using deep learning","volume":"10","author":"Aasem","year":"2022","journal-title":"Mathematics"},{"key":"B2","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: a survey on explainable artificial intelligence","volume":"6","author":"Adabi","year":"2018","journal-title":"IEEE Access"},{"key":"B3","doi-asserted-by":"publisher","first-page":"821","DOI":"10.3390\/s22030821","article-title":"E-TBNET: light deep neural network for automatic detection of tuberculosis with X-ray DR imaging","volume":"22","author":"An","year":"2022","journal-title":"Sensors"},{"key":"B4","author":"Anouk Stein","year":"2018","journal-title":"Rsna pneumonia detection challenge"},{"key":"B5","doi-asserted-by":"publisher","first-page":"200109","DOI":"10.1016\/j.iswa.2022.200109","article-title":"Argumentation approaches for explanaible ai in medical informatics","volume":"16","author":"Caroprese","year":"2022","journal-title":"Intell. Syst. Appl"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/B978-0-323-90184-0.00003-5","article-title":"\u201cChapter 1 - Introduction,\u201d","volume-title":"Deep Learning for Chest Radiographs, Primers in Biomedical Imaging Devices and Systems","author":"Chandola","year":"2021"},{"key":"B7","first-page":"839","article-title":"\u201cGRAD-CAM++: generalized gradient-based visual explanations for deep convolutional networks,\u201d","author":"Chattopadhay","year":"2018"},{"key":"B8","doi-asserted-by":"publisher","first-page":"132665","DOI":"10.1109\/ACCESS.2020.3010287","article-title":"Can AI help in screening viral and COVID-19 pneumonia?","volume":"8","author":"Chowdhury","year":"2020","journal-title":"IEEE Access"},{"key":"B9","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.compmedimag.2007.02.002","article-title":"Computer-aided diagnosis in medical imaging: historical review, current status and future potential","volume":"31","author":"Doi","year":"2007","journal-title":"Comput. Med. Imaging Graph"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0025-5564(75)90047-4","article-title":"A model of inexact reasoning","volume":"23","author":"ea Shortliffe","year":"1975","journal-title":"Med. Math. Biosci"},{"key":"B11","doi-asserted-by":"publisher","first-page":"e210056","DOI":"10.1148\/ryai.2021210056","article-title":"Are artificial intelligence challenges becoming radiology's new \u201cbee's knees\u201d?","volume":"3","author":"Elhalawani","year":"2021","journal-title":"Radiol. Artif. Intell"},{"key":"B12","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"B13","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s13735-019-00183-w","article-title":"A survey of traditional and deep learning-based feature descriptors for high dimensional data in computer vision","volume":"9","author":"Georgiou","year":"2020","journal-title":"Int. J. Multimed. Inf. Retr"},{"key":"B14","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/RBME.2022.3185953","article-title":"Explainable artificial intelligence methods in combating pandemics: a systematic review","volume":"16","author":"Giuste","year":"2023","journal-title":"IEEE Rev. Biomed. Eng"},{"key":"B15","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.patrec.2019.11.040","article-title":"Thorax disease classification with attention guided convolutional neural network","volume":"131","author":"Guan","year":"2020","journal-title":"Pattern Recognit. Lett"},{"key":"B16","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","article-title":"\u201cIdentity mappings in deep residual networks,\u201d","author":"He","year":"2016"},{"key":"B17","first-page":"100","article-title":"\u201cA survey on convolutional neural network accelerators: GPU, FPGA and ASIC,\u201d","author":"Hu","year":"2022"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4700","DOI":"10.1109\/CVPR.2017.243","article-title":"\u201cDensely connected convolutional networks,\u201d","author":"Huang","year":"2017"},{"key":"B19","first-page":"247","article-title":"\u201cRule-based methods for the computer assisted diagnosis of medical images,\u201d","author":"Ion","year":"2009"},{"key":"B20","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1609\/aaai.v33i01.3301590","article-title":"Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"33","author":"Irvin","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv:1705.09850","article-title":"Abnormality detection and localization in chest X-rays using deep convolutional neural networks","author":"Islam","year":"2017","journal-title":"arXiv"},{"key":"B22","doi-asserted-by":"publisher","first-page":"100150","DOI":"10.1016\/j.xjidi.2022.100150","article-title":"Deep learning in dermatology: a systematic review of current approaches, outcomes and limitations","volume":"3","author":"Jeong","year":"2022","journal-title":"JID Innov"},{"key":"B23","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/S0933-3657(97)00021-3","article-title":"Fuzzy logic in computer-aided breast cancer diagnosis: analysis of lobulation","volume":"11","author":"Kovalerchuk","year":"1997","journal-title":"Artif. Intell. Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"B25","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B26","first-page":"422","author":"Ma","year":"2021","journal-title":"Survey of image classification algorithms based on deep learning 11911"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17795-9","article-title":"\u201cDeep learning vs. traditional computer vision,\u201d","author":"Mahony","year":"2020"},{"key":"B28","doi-asserted-by":"publisher","first-page":"101635","DOI":"10.1016\/j.sysarc.2019.101635","article-title":"A survey of techniques for optimizing deep learning on GPUs","volume":"99","author":"Mittal","year":"2019","journal-title":"J. Syst. Architect"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICEST55168.2022.9828625","article-title":"\u201cA survey of three types of processing units: CPU, GPU and TPU,\u201d","author":"Nikoli\u0107","year":"2022"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2698","DOI":"10.1109\/TMI.2020.3042773","article-title":"Learning hierarchical attention for weakly-supervised chest X-ray abnormality localization and diagnosis","volume":"40","author":"Ouyang","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B31","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1148\/radiol.220182","article-title":"Methods for clinical evaluation of artificial intelligence algorithms for medical diagnosis","volume":"306","author":"Park","year":"2023","journal-title":"Radiology"},{"key":"B32","first-page":"111","author":"Ponomaryov","year":"2021","journal-title":"Chest X-ray classification using transfer learning on multi-GPU 11736"},{"key":"B33","doi-asserted-by":"publisher","first-page":"e180031","DOI":"10.1148\/ryai.2019180031","article-title":"Challenges related to artificial intelligence research in medical imaging and the importance of image analysis competitions","volume":"1","author":"Prevedello","year":"2019","journal-title":"Radiol. Artif. Intell"},{"key":"B34","doi-asserted-by":"publisher","first-page":"104319","DOI":"10.1016\/j.compbiomed.2021.104319","article-title":"Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images","volume":"132","author":"Rahman","year":"2021","journal-title":"Comput. Biol. Med"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.05225","article-title":"Chexnet: radiologist-level pneumonia detection on chest X-rays with deep learning","author":"Rajpurkar","year":"2017","journal-title":"arXiv"},{"key":"B36","doi-asserted-by":"publisher","first-page":"200148","DOI":"10.1016\/j.iswa.2022.200148","article-title":"A multi-modal bone suppression, lung segmentation, and classification approach for accurate COVID-19 detection using chest radiographs","volume":"16","author":"Rani","year":"","journal-title":"Intell. Syst. Appl"},{"key":"B37","doi-asserted-by":"publisher","first-page":"107024","DOI":"10.1016\/j.cmpb.2022.107024","article-title":"Spatial feature and resolution maximization gan for bone suppression in chest radiographs","volume":"224","author":"Rani","year":"","journal-title":"Comput. Methods Programs Biomed"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv:2003.13969","article-title":"A thorough comparison study on adversarial attacks and defenses for common thorax disease classification in chest X-rays","author":"Rao","year":"2020","journal-title":"arXiv"},{"key":"B39","doi-asserted-by":"publisher","first-page":"e190043","DOI":"10.1148\/ryai.2020190043","article-title":"On the interpretability of artificial intelligence in radiology: challenges and opportunities","volume":"2","author":"Reyes","year":"2020","journal-title":"Radiol. Artif. Intell"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.10348","article-title":"Dermatologist level dermoscopy skin cancer classification using different deep learning convolutional neural networks algorithms","author":"Rezvantalab","year":"2018","journal-title":"arXiv"},{"key":"B41","unstructured":"\u201cLocalization with limited annotation for chest X-rays,\u201d\u201d5265\n            RozenbergE.\n            FreedmanD.\n            BronsteinA.\n          \n            DalcaA. V.\n            McDermottM. B. A.\n            AlsentzerE.\n            FinlaysonS. G.\n            OberstM.\n            FalckF.\n            Beaulieu-JonesB.\n          Proceedings of the Machine Learning for Health NeurIPS Workshop2020"},{"key":"B42","doi-asserted-by":"publisher","first-page":"4510","DOI":"10.1109\/CVPR.2018.00474","article-title":"\u201cMobilenetv2: inverted residuals and linear bottlenecks,\u201d","author":"Sandler","year":"2018"},{"key":"B43","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"GRAD-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis"},{"key":"B44","doi-asserted-by":"publisher","first-page":"8068","DOI":"10.3390\/s22208068","article-title":"A survey on medical explainable AI (XAI): recent progress, explainability approach, human interaction and scoring system","volume":"22","author":"Sheu","year":"2022","journal-title":"Sensors"},{"key":"B45","doi-asserted-by":"publisher","first-page":"2376","DOI":"10.1109\/JBHI.2021.3074893","article-title":"Covid-19 automatic diagnosis with radiographic imaging: explainable attention transfer deep neural networks","volume":"25","author":"Shi","year":"2021","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B46","doi-asserted-by":"publisher","first-page":"53040","DOI":"10.1109\/ACCESS.2019.2912200","article-title":"Review of deep learning algorithms and architectures","volume":"7","author":"Shrestha","year":"2019","journal-title":"IEEE Access"},{"key":"B47","doi-asserted-by":"publisher","first-page":"e190187","DOI":"10.1148\/ryai.2019190187","article-title":"Making ai even smarter using ensembles: a challenge to future challenges and implications for clinical care","volume":"1","author":"Siegel","year":"2019","journal-title":"Radiol. Artif. Intell"},{"key":"B48","doi-asserted-by":"publisher","first-page":"20732","DOI":"10.1038\/s41598-022-25027-2","article-title":"Computer-aided diagnosis through medical image retrieval in radiology","volume":"12","author":"Silva","year":"2022","journal-title":"Sci. Rep"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6199","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013","journal-title":"arXiv"},{"key":"B51","first-page":"6105","author":"Tan","year":"2019","journal-title":"Efficientnet: rethinking model scaling for convolutional neural networks"},{"key":"B52","doi-asserted-by":"publisher","first-page":"7068349","DOI":"10.1155\/2018\/7068349","article-title":"Deep learning for computer vision: a brief review","volume":"2018","author":"Voulodimos","year":"2018","journal-title":"Comput. Intell. Neurosci"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1206.4656","article-title":"Machine learning that matters","author":"Wagstaff","year":"2012","journal-title":"arXiv"},{"key":"B54","doi-asserted-by":"publisher","first-page":"3462","DOI":"10.1109\/CVPR.2017.369","article-title":"\u201cChest X-ray 8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases,\"","author":"Wang","year":"2017"},{"key":"B55","doi-asserted-by":"publisher","first-page":"E167","DOI":"10.1148\/radiol.2020203511","article-title":"Deepcovid-XR: an artificial intelligence algorithm to detect COVID-19 on chest radiographs trained and tested on a large us clinical data set","volume":"299","author":"Wehbe","year":"2021","journal-title":"Radiology"},{"key":"B56","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1109\/ISBI45749.2020.9098482","article-title":"\u201cAutomatic bounding box annotation of chest X-ray data for localization of abnormalities,\u201d","author":"Wu","year":"2020"},{"key":"B57","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/3233547.3233573","article-title":"\u201cWeakly supervised deep learning for thoracic disease classification and localization on chest X-rays,\u201d","author":"Yan","year":"2018"},{"key":"B58","doi-asserted-by":"publisher","first-page":"112821","DOI":"10.1016\/j.eswa.2019.112821","article-title":"A systematic survey of computer-aided diagnosis in medicine: past and present developments","volume":"138","author":"Yanase","year":"2019","journal-title":"Expert Syst. Appl"},{"key":"B59","doi-asserted-by":"publisher","first-page":"e210064","DOI":"10.1148\/ryai.210064","article-title":"External validation of deep learning algorithms for radiologic diagnosis: a systematic review","volume":"4","author":"Yu","year":"2022","journal-title":"Radiol. Artif. Intell"},{"key":"B60","doi-asserted-by":"publisher","first-page":"8697","DOI":"10.1109\/CVPR.2018.00907","article-title":"\u201cLearning transferable architectures for scalable image recognition,\u201d","author":"Zoph","year":"2018"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1366415\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,2]],"date-time":"2024-05-02T04:54:35Z","timestamp":1714625675000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1366415\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,2]]},"references-count":60,"alternative-id":["10.3389\/fdata.2024.1366415"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2024.1366415","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,2]]},"article-number":"1366415"}}