{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:03:23Z","timestamp":1784304203590,"version":"3.55.0"},"reference-count":42,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"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":["Risk Analysis"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The high nominal accuracy achieved by deep learning models in predicting malignant skin lesions is frequently undermined by their susceptibility to operational uncertainty. Image acquisition conditions, such as lighting, device settings, and skin characteristics, introduce variations in optical parameters that compromise the model's reliability in real\u2010world clinical settings. This instability produces an unquantified diagnostic risk, which makes the safe clinical implementation of these powerful systems difficult. With this critical gap in mind, this paper proposes and utilizes global sensitivity analysis to rigorously quantify the robustness of a convolutional neural network architecture with respect to five critical optical image parameters. The analysis aims to quantify the model's instability, moving beyond simple accuracy to provide a robust, risk\u2010quantified assessment. This approach is essential for establishing the level of confidence required for the accreditation and safe clinical deployment of AI\u2010based diagnostic\u00a0systems.<\/jats:p>","DOI":"10.1111\/risa.70237","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:07:04Z","timestamp":1774937224000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Global Sensitivity Analysis for Robust XAI: Quantifying Clinical Risk and Prediction Instability in Dermoscopic Image Classification"],"prefix":"10.1111","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3569-6274","authenticated-orcid":false,"given":"Giulia","family":"Vannucci","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Information Technology Polytechnic and Basic Sciences School, University of Naples Federico II  Napoli Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renato Patrik Williame","family":"Coppolecchia","sequence":"additional","affiliation":[{"name":"Department of Physics University of Naples Federico II  Napoli Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberta","family":"Siciliano","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Technology Polytechnic and Basic Sciences School, University of Naples Federico II  Napoli Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"issue":"1","key":"e_1_2_10_2_1","first-page":"1","article-title":"Hair Removal From Dermoscopy Images Using Mathematical Morphology","volume":"21","author":"Abbas Q.","year":"2011","journal-title":"International Journal of Imaging Systems and Technology"},{"key":"e_1_2_10_3_1","article-title":"Preprocessing Techniques for Dermoscopy Images: A Review","volume":"126","author":"Abdolrazzaghi M.","year":"2022","journal-title":"Artificial Intelligence in Medicine"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-665X\/ab9f12"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1515\/jtse-2018-0025"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2015.06.032"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","unstructured":"Chen L.\u2010C. G.Papandreou F.Schroff andH.Adam.2018. \u201cEncoder\u2010Decoder With Atrous Separable Convolution for Semantic Image Segmentation.\u201d InProceedings of the European Conference on Computer Vision (ECCV) 801\u2013818.Springer.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.70002"},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","unstructured":"Chollet F.2017. \u201cXception: Deep Learning With Depthwise Separable Convolutions.\u201d InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 1251\u20131258.IEEE.","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1097\/CMR.0000000000000857"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2024.1267290"},{"key":"e_1_2_10_13_1","volume-title":"Digital Image Processing","author":"Gonzalez R. C.","year":"2009"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","unstructured":"He K. G.Gkioxari P.Dollar andR.Girshick.2017. \u201cMask R\u2010CNN.\u201d InProceedings of the IEEE International Conference on Computer Vision 2961\u20132969. IEEE. 19.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2005.11.017"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/0951-8320(96)00002-6"},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","unstructured":"Huang G. Z.Liu L.Van Der Maaten andK. Q.Weinberger.2017. \u201cDensely Connected Convolutional Networks.\u201d InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 4700\u20134708.IEEE.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.12.132"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7547-8_5"},{"issue":"3","key":"e_1_2_10_21_1","first-page":"311","article-title":"Digital Image Smoothing and the Removal of Hair From Skin Images","volume":"52","author":"Lee T. S.","year":"1990","journal-title":"Computer Vision, Graphics, and Image Processing"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1273253"},{"key":"e_1_2_10_23_1","first-page":"4768","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg S. M.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2011.08.008"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtbi.2008.04.011"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.2196\/18091"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IIPHDW.2018.8388338"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2004.05304.x"},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","unstructured":"Ratul A. R. M.Hamed Mozaffari W.\u2010S.Lee andE.Parimbelli.2019. \u201cSkin Lesions Classification Using Deep Learning Based on Dilated Convolution.\u201dPreprint BioRxiv November 30.https:\/\/doi.org\/10.1101\/860700.","DOI":"10.1101\/860700"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2020.104954"},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"Ronneberger O. P.Fischer andT.Brox.2015. \u201cU\u2010net: Convolutional Networks for Biomedical Image Segmentation.\u201d InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention 234\u2013241.Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2021.105226"},{"key":"e_1_2_10_33_1","volume-title":"Global Sensitivity Analysis: The Primer","author":"Saltelli A.","year":"2008"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1021\/cr040659d"},{"key":"e_1_2_10_35_1","first-page":"112","article-title":"Sensitivity Estimates for Nonlinear Mathematical Models","volume":"2","author":"Sobol' I. M.","year":"1990","journal-title":"Matematicheskoe Modelirovanie"},{"key":"e_1_2_10_36_1","first-page":"407","article-title":"Sensitivity analysis for non\u2010linear mathematical models","volume":"1","author":"Sobol' I. M.","year":"1993","journal-title":"Mathematical Modelling and Computational Experiment"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-3216-7_4"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2009.05.007"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcskn.2024.100276"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2024.105977"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.161"},{"key":"e_1_2_10_42_1","first-page":"2273","volume-title":"Sensitivity Analysis","author":"Vannucci G.","year":"2025"},{"key":"e_1_2_10_43_1","doi-asserted-by":"crossref","unstructured":"Vannucci G. R.Siciliano andA.Saltelli.2026. \u201cGlobal Sensitivity Analysis in Random Forests: Unveiling Generative Variable Importance.\u201d Statistical Methods and Applications (in press).","DOI":"10.1007\/s10260-026-00839-y"}],"container-title":["Risk Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/risa.70237","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/risa.70237","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/risa.70237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:09:07Z","timestamp":1784300947000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/risa.70237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/risa.70237"],"URL":"https:\/\/doi.org\/10.1111\/risa.70237","archive":["Portico"],"relation":{},"ISSN":["0272-4332","1539-6924"],"issn-type":[{"value":"0272-4332","type":"print"},{"value":"1539-6924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"2025-12-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70237"}}