{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:48:59Z","timestamp":1781282939285,"version":"3.54.1"},"reference-count":17,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Nowadays, Artificial Intelligence (AI) has revolutionized many fields and the medical field is no exception. Thanks to technological advancements and the emergence of Deep Learning (DL) techniques AI has brought new possibilities and significant improvements to medical practice. Despite the excellent results of DL models in terms of accuracy and performance, they remain black boxes as they do not provide meaningful insights into their internal functioning. This is where the field of Explainable AI (XAI) comes in, aiming to provide insights into the underlying workings of these black box models. In this present paper the visual explainability of deep models on chest radiography images are addressed. This research uses two datasets, the first on COVID-19, viral pneumonia, normality (healthy patients) and the second on pulmonary opacities. Initially the pretrained CNN models (VGG16, VGG19, ResNet50, MobileNetV2, Mixnet and EfficientNetB7) are used to classify chest radiography images. Then, the visual explainability methods (GradCAM, LIME, Vanilla Gradient, Gradient Integrated Gradient and SmoothGrad) are performed to understand and explain the decisions made by these models. The obtained results show that MobileNetV2 and VGG16 are the best models for the first and second datasets, respectively. As for the explainability methods, the results were subjected to doctors and were validated by calculating the mean opinion score. The doctors deemed GradCAM, LIME and Vanilla Gradient as the most effective methods, providing understandable and accurate explanations.<\/jats:p>","DOI":"10.3390\/a18040210","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T03:32:53Z","timestamp":1744169573000},"page":"210","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An Efficient Explainability of Deep Models on Medical Images"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2211-2420","authenticated-orcid":false,"given":"Salim","family":"Khiat","sequence":"first","affiliation":[{"name":"Signals, Systems and Data Laboratory, Computer Systems Engineering Department, Polytechnic National School of Oran, Oran 31000, Algeria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1530-9524","authenticated-orcid":false,"given":"Sidi Ahmed","family":"Mahmoudi","sequence":"additional","affiliation":[{"name":"Computer Science and Management Department, University of Mons, 7000 Mons, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5179-9623","authenticated-orcid":false,"given":"S\u00e9drick","family":"Stassin","sequence":"additional","affiliation":[{"name":"Computer Science and Management Department, University of Mons, 7000 Mons, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lillia","family":"Boukerroui","sequence":"additional","affiliation":[{"name":"Computer Systems Engineering Department, Polytechnic National School of Oran, Oran 31000, Algeria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Besma","family":"Sena\u00ef","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Science and Technology of Oran Mohamed Boudiaf, Oran 31000, Algeria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8272-9425","authenticated-orcid":false,"given":"Sa\u00efd","family":"Mahmoudi","sequence":"additional","affiliation":[{"name":"Computer Science and Management Department, University of Mons, 7000 Mons, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Islam, N., Alam, G.R., Apon, T.S., Uddin, Z., Allheeib, N., Menshawi, A., and Hassan, M.M. (2023). Interpretable Differential Diagnosis of Non-COVID Viral Pneumonia, Lung Opacity and COVID-19 Using Tuned Transfer Learning and Explainable AI. Healthcare, 11.","DOI":"10.3390\/healthcare11030410"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ahsan, M., Nazim, R., Siddique, Z., and Huebner, P. (2021). Detection of COVID-19 Patients from CT Scan and Chest X-ray Data Using Modified MobileNetV2 and LIME. Healthcare, 9.","DOI":"10.3390\/healthcare9091099"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"106156","DOI":"10.1016\/j.compbiomed.2022.106156","article-title":"Explanatory classification of CXR images into COVID-19, Pneumonia and Tuberculosis using deep learning and XAI","volume":"Volume 150","author":"Bhandari","year":"2022","journal-title":"Computers in Biology and Medicine"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"100499","DOI":"10.1016\/j.dajour.2024.100499","article-title":"An explainable artificial intelligence model for multiple lung diseases classification from chest X-ray images using fine-tuned transfer learning","volume":"12","author":"Mahamud","year":"2024","journal-title":"Decis. Anal. J."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chetoui, M., Akhloufi, M.A., Yousefi, B., and Bouattane, E.M. (2021). Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network Architecture. Big Data Cogn. Comput., 5.","DOI":"10.3390\/bdcc5040073"},{"key":"ref_6","unstructured":"Tsang, S.-H. (2024, July 01). Review: MobileNetV2\u2014Light Weight Model (Image Classification) Outperforms MobileNetV1, NASNet, and ShuffleNet V1. Towards Data Science. Kaggle. Available online: https:\/\/www.kaggle.com\/."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102470","DOI":"10.1016\/j.media.2022.102470","article-title":"Explainable artificial intelligence(XAI) in deep learning-based medical image analysis","volume":"79","author":"Velden","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Antoniadi, A.M., Du, Y., Guendouz, Y., Wei, L., Mazo, C., Becker, B.A., and Mooney, C. (2021). Current Challenges Andfuture Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review. Appl. Sci., 11, Available online: https:\/\/www.mdpi.com\/2076-3417\/11\/11\/5088.","DOI":"10.3390\/app11115088"},{"key":"ref_9","unstructured":"Sousa, I.P. (2021). Intelig\u00eancia Artificial Explic\u00e1vel para Classificadores de Imagens M\u00e9dicas. [Ph.D. Thesis, PUC-Rio]."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference On Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy should i trust you?\u201d explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD international CONFERENCE on knowledge DISCOVERY and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_12","unstructured":"Rahman, M.M. (2022). Deep Interpretability Methods for Neuroimaging. [Doctoral Dissertation, College of Arts and Sciences, Georgia State University]."},{"key":"ref_13","unstructured":"(2024, July 01). Python. Available online: https:\/\/www.python.org\/."},{"key":"ref_14","unstructured":"(2024, July 01). TensorFlow. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_15","unstructured":"(2024, July 01). Keras. Available online: https:\/\/keras.io\/."},{"key":"ref_16","unstructured":"(2024, July 01). tf-Explain. Available online: https:\/\/tf-explain.readthedocs.io\/."},{"key":"ref_17","unstructured":"Hofman, R.R., Mueller, S.T., Klein, G., and Litman, J. (2018). Metrics for explainable AI: Challenges and prospects. arXiv."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/4\/210\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:12:56Z","timestamp":1760029976000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/4\/210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,9]]},"references-count":17,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["a18040210"],"URL":"https:\/\/doi.org\/10.3390\/a18040210","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,9]]}}}