{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T17:06:02Z","timestamp":1779210362889,"version":"3.51.4"},"reference-count":39,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Evaluating the trustworthiness of black-box machine learning models remains a significant methodological challenge. Their lack of transparency and interpretability limits applicability, because stakeholders often seek transparency before trusting the results of black-box machine learning models. Explainable AI (XAI) methods provide for human-understandable justifications and informed decision-making of these black-box architectures. Therefore, it is imperative to select the proper XAI model tailored to specific tasks. In this research, we focus on examining four XAI techniques: PEEK, LRP, GRAD-CAM, and LIME to understand how they perform against each other for image classification tasks. We evaluate the performance, robustness, generalizability, noise stability, and computational efficiency of these methods using a globally recognized dataset. With 7390 images, the Oxford IIT pet dataset provides a comprehensive resource for training a custom Convolutional Neural Network (CNN) and VGG16, enabling a consistent evaluation of each XAI method. First, we analyze the saliency maps of the input images and observe the regions predicted by these XAI methods, and then leverage a noise analysis approach to evaluate their performance in terms of accuracy. We further explore the robustness, run-time, and \u201cfaithfulness\u201d metrics of each XAI method. In general, we find that these methods can identify a set of input-data features that are critical for accurate classification but also intuitive, such as the outline, face, and eyes of subjects. However, our analysis reveals only marginal consensus among XAI methods in identifying those critical features. Grad-CAM demonstrates strong robustness and stability in VGG16, but the performance on the shallow CNN model remained inconsistent.<\/jats:p>","DOI":"10.3390\/e28050562","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:07:26Z","timestamp":1779206846000},"page":"562","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Comparative Analysis of Explainable AI (XAI) Techniques for Transparent and Reliable Image Classification"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0765-1060","authenticated-orcid":false,"given":"Sovon","family":"Chakraborty","sequence":"first","affiliation":[{"name":"Department of Computer Science, Old Dominion University, Norfolk, VA 23529, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2704-118X","authenticated-orcid":false,"given":"Shakib Mahmud","family":"Dipto","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Old Dominion University, Norfolk, VA 23529, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3278-2268","authenticated-orcid":false,"given":"Kevin R.","family":"Pilkiewicz","sequence":"additional","affiliation":[{"name":"Environmental Laboratory, US Army Engineer Research and Development Center, Vicksburg, MS 39180, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9014-1859","authenticated-orcid":false,"given":"Michael L.","family":"Mayo","sequence":"additional","affiliation":[{"name":"Environmental Laboratory, US Army Engineer Research and Development Center, Vicksburg, MS 39180, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9199-2479","authenticated-orcid":false,"given":"Pratip","family":"Rana","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Old Dominion University, Norfolk, VA 23529, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103352","DOI":"10.1016\/j.inffus.2025.103352","article-title":"Towards eXplicitly eXplainable Artificial Intelligence","volume":"123","author":"Kalmykov","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Maathuis, C., Cidota, M.A., Datcu, D., and Marin, L. (2025). Integrating Explainable Artificial Intelligence in Extended Reality Environments: A Systematic Survey. Mathematics, 13.","DOI":"10.3390\/math13020290"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"128111","DOI":"10.1016\/j.neucom.2024.128111","article-title":"Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction","volume":"599","author":"Mersha","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Do\u0161ilovi\u0107, F.K., Br\u010di\u0107, M., and Hlupi\u0107, N. (2018). Explainable artificial intelligence: A survey. 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), IEEE.","DOI":"10.23919\/MIPRO.2018.8400040"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100160","DOI":"10.1016\/j.dsm.2025.07.002","article-title":"Unveiling the Footprints of eXplainable AI in Industry 4.0\/5.0: A Systematic Review and Bibliometric Exploration","volume":"9","author":"Oladimeji","year":"2026","journal-title":"Data Sci. Manag."},{"key":"ref_6","unstructured":"Komera, O. (2026, February 11). Explainable AI (XAI): Bridging the Gap Between Complexity and Interpretability. 2025. Available online: https:\/\/www.researchgate.net\/profile\/Omkar-Komera\/publication\/389818744_Explainable_AI_XAI_Bridging_the_Gap_Between_Complexity_and_Interpretability\/links\/67d325347c5b5569dcbb577f\/Explainable-AI-XAI-Bridging-the-Gap-Between-Complexity-and-Interpretability.pdf."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4476","DOI":"10.1038\/s41598-025-34713-w","article-title":"An attention enhanced CNN ensemble for interpretable and accurate cotton leaf disease classification","volume":"16","author":"Haque","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_8","first-page":"29","article-title":"A Survey of Data-Driven and Knowledge-Aware Explainable AI","volume":"34","author":"Li","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"102909","DOI":"10.1016\/j.techsoc.2025.102909","article-title":"The Role of Explainable Artificial Intelligence (XAI) in Innovation Processes: A Knowledge Management Perspective","volume":"82","author":"Mancuso","year":"2025","journal-title":"Technol. Soc."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"120785","DOI":"10.1109\/ACCESS.2025.3581136","article-title":"A Survey of Post-Hoc XAI Methods from a Visualization Perspective: Challenges and Opportunities","volume":"13","author":"Bhati","year":"2025","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Arora, N., and Gajjar, Y. (2025). Evolution, Need, and Application of Explainable AI in Supply Chain Management. Explainable AI and Blockchain for Secure and Agile Supply Chains, Chapman and Hall\/CRC.","DOI":"10.1201\/9781003497363-2"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Komal, G.K.S., Sharma, S., and Kumar, R. (2025). Explainable AI in Medical Imaging, Personalized Medicine, and Bias Reduction: A New Era in Healthcare. Explainable Artificial Intelligence in the Healthcare Industry, John Wiley & Sons, Inc.","DOI":"10.1002\/9781394249312.ch21"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2660","DOI":"10.1109\/TNNLS.2016.2599820","article-title":"Evaluating the Visualization of What a Deep Neural Network Has Learned","volume":"28","author":"Samek","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_14","unstructured":"Doshi-Velez, F., and Kim, B. (2017). Towards a Rigorous Science of Interpretable Machine Learning. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Wu, Y., Li, Y., Cai, L., and Ihnaini, B. (2025). A Comprehensive Review of Explainable Artificial Intelligence (XAI) in Computer Vision. Sensors, 25.","DOI":"10.3390\/s25134166"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Meni, M., Mahendrakar, T., Raney, O.D., White, R.T., Mayo, M.L., and Pilkiewicz, K.R. (2024, January 8\u201312). Taking a PEEK into YOLOv5 for Satellite Component Recognition via Entropy-Based Visual Explanations. Proceedings of the AIAA SciTech 2024 Forum, Orlando, FL, USA.","DOI":"10.2514\/6.2024-2766"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Swain, S., and Tripathy, A.K. (2024). Automatic Detection of Potholes Using VGG-16 Pre-Trained Network and Convolutional Neural Network. Heliyon, 10.","DOI":"10.1016\/j.heliyon.2024.e30957"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104201","DOI":"10.1016\/j.rineng.2025.104201","article-title":"Temporal Integration of ResNet Features with LSTM for Enhanced Skin Lesion Classification","volume":"25","author":"Padhy","year":"2025","journal-title":"Results Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Soni, A., Sethy, P.K., Dewangan, A.K., Nanthaamornphong, A., Behera, S.K., and Devi, B. (2024). Enhancing Oral Squamous Cell Carcinoma Detection: A Novel Approach Using Improved EfficientNet Architecture. BMC Oral Health, 24.","DOI":"10.1186\/s12903-024-04307-5"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rahman, A., Kundu, D., Debnath, T., Rahman, M., Das, U.K., Miah, A.S.M., and Muhammad, G. (2025). From AI to the Era of Explainable AI in Healthcare 5.0: Current State and Future Outlook. Expert Syst., 42.","DOI":"10.1111\/exsy.70060"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lieu, M. (2025). A Comprehensive Guide to Interpretable AI-Powered Discoveries in Astronomy. Universe, 11.","DOI":"10.3390\/universe11060187"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5587","DOI":"10.1007\/s00146-025-02302-0","article-title":"Transparency and Accountability: Unpacking the Real Problems of Explainable AI","volume":"40","author":"Hussain","year":"2025","journal-title":"AI Soc."},{"key":"ref_23","unstructured":"Selvaraju, R.R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., and Batra, D. (2016). Grad-CAM: Why Did You Say That?. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"120525","DOI":"10.1016\/j.atherosclerosis.2025.120525","article-title":"Coronary Lipid Burden Indices Predict Non-Culprit Major Adverse Cardiac Events Independently of Novel LDL Estimates: Insights from the LRP Study","volume":"410","author":"Kuku","year":"2025","journal-title":"Atherosclerosis"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Knab, P., Marton, S., Schlegel, U., and Bartelt, C. (2025). Which LIME Should I Trust? Concepts, Challenges, and Solutions. World Conference on Explainable Artificial Intelligence, Springer Nature.","DOI":"10.1007\/978-3-032-08324-1_2"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Gulum, M.A., Trombley, C.M., Ozen, M., Esen, E., Aksamoglu, M., and Kantardzic, M. (2024). Why Are Explainable AI Methods for Prostate Lesion Detection Rated Poorly by Radiologists?. Appl. Sci., 14.","DOI":"10.3390\/app14114654"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"120212","DOI":"10.1016\/j.ins.2024.120212","article-title":"Fuzzy Inference System with Interpretable Fuzzy Rules: Advancing Explainable Artificial Intelligence for Disease Diagnosis\u2014A Comprehensive Review","volume":"662","author":"Cao","year":"2024","journal-title":"Inf. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"107161","DOI":"10.1016\/j.cmpb.2022.107161","article-title":"Application of Explainable Artificial Intelligence for Healthcare: A Systematic Review of the Last Decade (2011\u20132022)","volume":"226","author":"Loh","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_29","unstructured":"Zhao, C., and Xu, W. (2025). Human\u2013AI Interaction Design Standards. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Alvanpour, A., Acun, C., Spurlock, K., Robinson, C.K., Das, S.K., Popa, D.O., and Nasraoui, O. (2025). Comparative Analysis of Post Hoc Explainable Methods for Robotic Grasp Failure Prediction. Electronics, 14.","DOI":"10.3390\/electronics14091868"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"498","DOI":"10.12732\/ijam.v38i1s.29","article-title":"Comparative Analysis of AI and XAI Techniques across Diverse Performance Metrics on Varied Datasets","volume":"38","author":"Dhas","year":"2025","journal-title":"Int. J. Appl. Math."},{"key":"ref_32","first-page":"3977","article-title":"A Comparative Study and Systematic Analysis of XAI Models and Their Applications in Healthcare","volume":"31","author":"Gupta","year":"2024","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Jegan, R.K., Baskaran, S., and Jayan, S. (2025, January 10\u201311). Comparative Study of Machine Learning Models and XAI Methods with Statistical Analysis. Proceedings of the 2nd Asian Conference on Intelligent Technologies (ACOIT), Kolar, India.","DOI":"10.1109\/ACOIT66109.2025.11436712"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Bommer, P.L., Kretschmer, M., Hedstr\u00f6m, A., Bareeva, D., and H\u00f6hne, M.M.C. (2024). Finding the Right XAI Method\u2014A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science. Artif. Intell. Earth Syst., 3.","DOI":"10.1175\/AIES-D-23-0074.1"},{"key":"ref_35","unstructured":"Zhang, Y., Gu, S., Song, J., Pan, B., Bai, G., and Zhao, L. (2023). XAI Benchmark for Visual Explanation. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., and Jawahar, C.V. (2012). Cats and Dogs. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"7859","DOI":"10.1038\/s41467-024-51970-x","article-title":"Thermodynamics-inspired explanations of artificial intelligence","volume":"15","author":"Mehdi","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_38","unstructured":"Takahashi, J., Kodera, S., and Takeda, N. (December, January 30). Contrastive Learning for Multi-Class ECG Classification with Jaccard Score\u2013Based Sigmoid Loss. Proceedings of the NeurIPS 2025 Workshop on Learning from Time Series for Health, San Diego, CA, USA."},{"key":"ref_39","first-page":"33120","article-title":"New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound","volume":"35","author":"Gupta","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/5\/562\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:09:52Z","timestamp":1779206992000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/5\/562"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":39,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["e28050562"],"URL":"https:\/\/doi.org\/10.3390\/e28050562","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]}}}