{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T22:08:36Z","timestamp":1782425316906,"version":"3.54.5"},"reference-count":56,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"vor","delay-in-days":118,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>The global prevalence of skin cancer necessitates the development of AI\u2010assisted technologies for accurate and interpretable diagnosis of skin lesions. This study presents a novel deep learning framework for enhancing the interpretability and reliability of skin lesion predictions from clinical images, which are more inclusive, accessible, and representative of real\u2010world conditions than dermoscopic images. We comprehensively analyzed 13 deep learning models from four main convolutional neural network architecture classes: DenseNet, ResNet, MobileNet, and EfficientNet. Different data augmentation strategies and model optimization algorithms were explored to access the performances of the deep learning models in binary and multiclass classification scenarios. In binary classification, the DenseNet\u2010161 model, initialized with random weights, obtained a top accuracy of 79.40%, while the EfficientNet\u2010B7 model, initialized with pretrained weights from ImageNet, reached an accuracy of 85.80%. Furthermore, in the multiclass classification experiments, DenseNet121, initialized with random weights and trained with AdamW, obtained the best accuracy of 65.1%. Likewise, when initialized with pretrained weights, the DenseNet121 model attained a top accuracy of 75.07% in multiclass classification. Detailed interpretability analyses were carried out leveraging the SHAP and CAM algorithms to provide insights into the decision rationale of the investigated models. The SHAP algorithm was beneficial in understanding the feature attributions by visualizing how specific regions of the input image influenced the model predictions. Our study emphasizes using clinical images for developing AI algorithms for skin lesion diagnosis, highlighting the practicality and relevance in real\u2010world applications, especially where dermoscopic tools are not readily accessible. Beyond accessibility, these developments also ensure that AI\u2010assisted diagnostic tools are deployed in diverse clinical settings, thus promoting inclusiveness and ultimately improving early detection and treatment of skin cancers.<\/jats:p>","DOI":"10.1155\/int\/2751767","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T04:40:12Z","timestamp":1745901612000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Interpretable Deep Learning for Classifying Skin Lesions"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8653-5572","authenticated-orcid":false,"given":"Mojeed Opeyemi","family":"Oyedeji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6929-6880","authenticated-orcid":false,"given":"Emmanuel","family":"Okafor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3562-2788","authenticated-orcid":false,"given":"Hussein","family":"Samma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6052-7221","authenticated-orcid":false,"given":"Motaz","family":"Alfarraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"e_1_2_11_2_2","volume-title":"Transfer Learning With Class-Weighted and Focal Loss Function for Automatic Skin Cancer Classification","author":"Le D. N. T.","year":"2020"},{"key":"e_1_2_11_3_2","volume-title":"Identifying Melanoma Images Using Efficientnet Ensemble: Winning Solution to the Siim-Isic Melanoma Classification Challenge","author":"Ha Q."},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2019.05.023"},{"key":"e_1_2_11_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2019.103545"},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03387-w"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.161"},{"key":"e_1_2_11_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"e_1_2_11_9_2","volume-title":"SIIM-ISIC 2020 Challenge Dataset","author":"International Skin Imaging Collaboration","year":"2020"},{"key":"e_1_2_11_10_2","doi-asserted-by":"crossref","unstructured":"MendoncaT. FerreiraP. M. MarquesJ. S. MarcalA. R. S. andRozeiraJ. PH\u00b2-A Dermoscopic Image Database for Research and Benchmarking Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2013 5437\u20135440 https:\/\/doi.org\/10.1109\/embc.2013.6610779 2-s2.0-84886463000.","DOI":"10.1109\/EMBC.2013.6610779"},{"key":"e_1_2_11_11_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-020-00534-8"},{"key":"e_1_2_11_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.06.018"},{"key":"e_1_2_11_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105725"},{"key":"e_1_2_11_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30642-7_30"},{"key":"e_1_2_11_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107122"},{"key":"e_1_2_11_16_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2020.00177"},{"key":"e_1_2_11_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103738"},{"key":"e_1_2_11_18_2","volume-title":"WonDerM: Skin Lesion Classification With Fine-Tuned Neural Networks","author":"Lee Y. C.","year":"2018"},{"key":"e_1_2_11_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102305"},{"key":"e_1_2_11_20_2","doi-asserted-by":"publisher","DOI":"10.1080\/24751839.2018.1479932"},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2022.112445"},{"key":"e_1_2_11_22_2","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202300211"},{"key":"e_1_2_11_23_2","doi-asserted-by":"publisher","DOI":"10.3389\/fsurg.2022.1029991"},{"key":"e_1_2_11_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09111-w"},{"key":"e_1_2_11_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105568"},{"key":"e_1_2_11_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01201-4_33"},{"key":"e_1_2_11_27_2","doi-asserted-by":"crossref","unstructured":"GrohM. HarrisC. SoenksenL.et al. Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology With the Fitzpatrick 17k Dataset 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2021 IEEE https:\/\/doi.org\/10.1109\/cvprw53098.2021.00201.","DOI":"10.1109\/CVPRW53098.2021.00201"},{"key":"e_1_2_11_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.11.005"},{"key":"e_1_2_11_29_2","unstructured":"LundbergS. M.andLeeS.-I. A Unified Approach to Interpreting Model Predictions Proceedings of the 31st International Conference on Neural Information Processing Systems NIPS\u201917 2017 Red Hook NY Curran Associates Inc 4768\u20134777."},{"key":"e_1_2_11_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31384-3"},{"key":"e_1_2_11_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0138-9"},{"key":"e_1_2_11_32_2","first-page":"3457","volume-title":"AISTATS, Vol. 130 of Proceedings of Machine Learning Research, PMLR","author":"Covert I.","year":"2021"},{"key":"e_1_2_11_33_2","doi-asserted-by":"crossref","unstructured":"RibeiroM. T. SinghS. andGuestrinC. Why Should I Trust You?: Explaining the Predictions of Any Classifier Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining KDD\u201916 2016 ACM https:\/\/doi.org\/10.1145\/2939672.2939778 2-s2.0-84984985889.","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_11_34_2","unstructured":"ShrikumarA. GreensideP. andKundajeA. Learning Important Features Through Propagating Activation Differences Proceedings of the 34th International Conference on Machine Learning-Volume 70 ICML\u201917 2017 3145\u20133153."},{"key":"e_1_2_11_35_2","doi-asserted-by":"crossref","unstructured":"SelvarajuR. R. CogswellM. DasA. VedantamR. ParikhD. andBatraD. Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization 2017 IEEE International Conference on Computer Vision (ICCV) 2017 618\u2013626 https:\/\/doi.org\/10.1109\/iccv.2017.74 2-s2.0-85041910265.","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_11_36_2","doi-asserted-by":"crossref","unstructured":"ChattopadhayA. SarkarA. HowladerP. andBalasubramanianV. N. Grad-Cam++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) 2018 IEEE 839\u2013847.","DOI":"10.1109\/WACV.2018.00097"},{"key":"e_1_2_11_37_2","unstructured":"RamaswamyH. G. Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-Free Localization Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision 2020 983\u2013991."},{"key":"e_1_2_11_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108798"},{"key":"e_1_2_11_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2024.111356"},{"key":"e_1_2_11_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111624"},{"key":"e_1_2_11_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.medntd.2023.100243"},{"key":"e_1_2_11_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2022.08.005"},{"key":"e_1_2_11_43_2","unstructured":"OzerC. GulerA. CanseverA. T. andOksuzI. Explainable Image Quality Assessment for Medical Imaging 2023 https:\/\/doi.org\/10.48550\/ARXIV.2303.14479."},{"key":"e_1_2_11_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13820-0"},{"key":"e_1_2_11_45_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76550-z"},{"key":"e_1_2_11_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.gvc.2021.200032"},{"key":"e_1_2_11_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3281910"},{"key":"e_1_2_11_48_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep Residual Learning for Image Recognition 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 IEEE https:\/\/doi.org\/10.1109\/cvpr.2016.90 2-s2.0-84986274465.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_11_49_2","doi-asserted-by":"crossref","unstructured":"HuangG. LiuZ. Van Der MaatenL. andWeinbergerK. Q. Densely Connected Convolutional Networks 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 IEEE https:\/\/doi.org\/10.1109\/cvpr.2017.243 2-s2.0-85035343801.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_11_50_2","unstructured":"TanM.andLeQ. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks International Conference on Machine Learning 2019 PMLR 6105\u20136114."},{"key":"e_1_2_11_51_2","unstructured":"HowardA. G. ZhuM. ChenB.et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications 2017 https:\/\/doi.org\/10.48550\/ARXIV.1704.04861."},{"key":"e_1_2_11_52_2","unstructured":"KingaD.andAdamJ. B. A Method for Stochastic Optimization 5 International Conference on Learning Representations (ICLR) 2015 San Diego California."},{"key":"e_1_2_11_53_2","volume-title":"On the Variance of the Adaptive Learning Rate and Beyond","author":"Liu L.","year":"2019"},{"key":"e_1_2_11_54_2","unstructured":"LoshchilovI.andHutterF. Decoupled Weight Decay Regularization International Conference on Learning Representations 2017."},{"key":"e_1_2_11_55_2","doi-asserted-by":"crossref","unstructured":"ZhouB. KhoslaA. LapedrizaA. OlivaA. andTorralbaA. Learning Deep Features for Discriminative Localization Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016 2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_2_11_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108012"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/2751767","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/2751767","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/2751767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:02:15Z","timestamp":1772992935000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/2751767"}},"subtitle":[],"editor":[{"given":"Alexander","family":"Ho\u0161ovsk\u00fd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/2751767"],"URL":"https:\/\/doi.org\/10.1155\/int\/2751767","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-04-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2751767"}}