{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T18:13:50Z","timestamp":1788459230224,"version":"build-2803163510"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:00:00Z","timestamp":1687305600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:00:00Z","timestamp":1687305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>A key issue in critical contexts such as medical diagnosis is the interpretability of the deep learning models adopted in decision-making systems. Research in eXplainable Artificial Intelligence (XAI) is trying to solve this issue. However, often XAI approaches are only tested on generalist classifier and do not represent realistic problems such as those of medical diagnosis. In this paper, we aim at improving the trust and confidence of users towards automatic AI decision systems in the field of medical skin lesion diagnosis by customizing an existing XAI approach for explaining an AI model able to recognize different types of skin lesions. The explanation is generated through the use of synthetic exemplar and counter-exemplar images of skin lesions and our contribution offers the practitioner a way to highlight the crucial traits responsible for the classification decision. A validation survey with domain experts, beginners, and unskilled people shows that the use of explanations improves trust and confidence in the automatic decision system. Also, an analysis of the latent space adopted by the explainer unveils that some of the most frequent skin lesion classes are distinctly separated. This phenomenon may stem from the intrinsic characteristics of each class and may help resolve common misclassifications made by human experts.<\/jats:p>","DOI":"10.1007\/s41060-023-00401-z","type":"journal-article","created":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:19:19Z","timestamp":1687306759000},"page":"183-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Improving trust and confidence in medical skin lesion diagnosis through explainable deep learning"],"prefix":"10.1007","volume":"20","author":[{"given":"Carlo","family":"Metta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Beretta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riccardo","family":"Guidotti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Gallinari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salvatore","family":"Rinzivillo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fosca","family":"Giannotti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,21]]},"reference":[{"key":"401_CR1","doi-asserted-by":"crossref","unstructured":"Pedreschi, D., Giannotti, F., Guidotti, R., Monreale, A., Ruggieri, S., Turini, F.: Meaningful explanations of black box AI decision systems, in AAAI. AAAI Press, pp. 9780\u20139784 (2019)","DOI":"10.1609\/aaai.v33i01.33019780"},{"key":"401_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1\u201338 (2019)","journal-title":"Artif. Intell."},{"key":"401_CR3","doi-asserted-by":"crossref","unstructured":"Metta, C., Guidotti, R., Yin, Y., Gallinari, P., Rinzivillo, S.: Exemplars and counterexemplars explanations for image classifiers, targeting skin lesion labeling, in IEEE ISCC, (2021)","DOI":"10.3233\/FAIA220209"},{"key":"401_CR4","doi-asserted-by":"crossref","unstructured":"Panigutti, C., Perotti, A., Pedreschi, D.: Doctor XAI: an ontology-based approach to black-box sequential data classification explanations, in FAT*. ACM, pp. 629\u2013639 (2020)","DOI":"10.1145\/3351095.3372855"},{"key":"401_CR5","doi-asserted-by":"crossref","unstructured":"Markus, A. F., Kors, J. A., Rijnbeek, P. R.: The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies, J. Biomed. Inform., 113, (2021)","DOI":"10.1016\/j.jbi.2020.103655"},{"key":"401_CR6","doi-asserted-by":"publisher","first-page":"52 138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52 138-52 160 (2018)","journal-title":"IEEE Access"},{"issue":"5","key":"401_CR7","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2019","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 931\u20139342 (2019)","journal-title":"ACM Comput. Surv."},{"key":"401_CR8","unstructured":"Sundararajan, M., et\u00a0al.: Axiomatic attribution for dnn, in ICML. JMLR, (2017)"},{"key":"401_CR9","unstructured":"Shrikumar, A., Greenside, P., Shcherbina, A., Kundaje, A.: Not just a black box: learning important features through propagating activation differences, CoRR, vol. https:\/\/arxiv.org\/abs\/1605.01713, (2016)"},{"issue":"7","key":"401_CR10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S., Binder, A., et al.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)","journal-title":"PLoS ONE"},{"key":"401_CR11","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T., Singh, S., Guestrin, C.: Why should I trust you?: explaining the predictions of any classifier, in KDD. ACM, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"401_CR12","unstructured":"Lundberg, S. M., Lee, S.: A unified approach to interpreting model predictions, in NIPS, 4765\u20134774 (2017)"},{"key":"401_CR13","doi-asserted-by":"crossref","unstructured":"Guidotti, R., Monreale, A., Cariaggi, L.: Investigating neighborhood generation methods for explanations of obscure image classifiers, in PAKDD (1), ser. Lecture Notes in Computer Science, vol. 11439. Springer, pp. 55\u201368 (2019)","DOI":"10.1007\/978-3-030-16148-4_5"},{"key":"401_CR14","doi-asserted-by":"crossref","unstructured":"Guidotti, R., Monreale, A., Matwin, S., Pedreschi, D.: Black box explanation by learning image exemplars in the latent feature space, in ECML\/PKDD (1), ser. Lecture Notes in Computer Science, vol. 11906. Springer, pp. 189\u2013205 (2019)","DOI":"10.1007\/978-3-030-46150-8_12"},{"key":"401_CR15","doi-asserted-by":"crossref","unstructured":"Metta, C., Guidotti, R., Yin, Y., Gallinari, P., Rinzivillo, S.: Exemplars and counterexemplars explanations for skin lesion classifiers, in Frontiers in Artificial Intelligence and Applications, vol. 354, (2022)","DOI":"10.3233\/FAIA220209"},{"key":"401_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition, in CVPR. IEEE Computer Society, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"401_CR17","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Pedreschi, D., Turini, F., Giannotti, F.: Local rule-based explanations of black box decision systems, (2018)"},{"key":"401_CR18","unstructured":"Ozer, C., Oksuz, I.: Explainable image quality analysis of chest x-rays, in MIDL, vol. 143, pp. 567\u2013580 (2021)"},{"key":"401_CR19","doi-asserted-by":"crossref","unstructured":"Boutorh, A., Rahim, H., Bendoumia, Y.: Explainable ai models for covid-19 diagnosis using ct-scan images and clinical data, International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics, 185\u2013199, (2022)","DOI":"10.1007\/978-3-031-20837-9_15"},{"key":"401_CR20","doi-asserted-by":"crossref","unstructured":"Farahani, F.V., Fiok, K., Lahijanian, B., Karwowski, W., Douglas, P. K.: Explainable ai: a review of applications to neuroimaging data, Frontiers in Neuroscience, 16, (2022)","DOI":"10.3389\/fnins.2022.906290"},{"key":"401_CR21","doi-asserted-by":"crossref","unstructured":"Jampani, V., et\u00a0al.: Assessment of computational visual attention models on medical images, in ICVGIP, 80, 1\u20138 (2012)","DOI":"10.1145\/2425333.2425413"},{"key":"401_CR22","doi-asserted-by":"crossref","unstructured":"Yoo, S. H., et\u00a0al.: Deep learning-based decision-tree classifier for covid-19 diagnosis from chest x-ray imaging, Frontiers in Medicine, 7, (2020)","DOI":"10.3389\/fmed.2020.00427"},{"key":"401_CR23","unstructured":"Papanastasopoulos, Z., et\u00a0al.: Explainable ai for medical imaging: deep-learning cnn ensemble for classification of estrogen receptor status from breast mri, in SPIE, 11314, (2012)"},{"key":"401_CR24","unstructured":"Wang, C., Liu, Y., Wang, F., Zhang, C., Wang, Y., Yuan, M., Yang, G.: Towards reliable and explainable ai model for solid pulmonary nodule diagnosis, arXiv:2204.04219, (2022)"},{"key":"401_CR25","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.1007\/s11548-022-02619-x","volume":"17","author":"C Wang","year":"2022","unstructured":"Wang, C., Liu, Y., Wang, F., Zhang, C., Wang, Y., Yuan, M., Yang, G.: Explainability of deep neural networks for mri analysis of brain tumors. Int. J. Comput. Assist. Radiol. Surg. 17, 1673\u20131683 (2022)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"401_CR26","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41746-022-00699-2","volume":"5","author":"H Chen","year":"2022","unstructured":"Chen, H., Gomez, C., Huang, C.: Explainable medical imaging ai needs human-centered design: guidelines and evidence from a systematic review,. npj Digit. Med. 5, 156 (2022)","journal-title":"npj Digit. Med."},{"key":"401_CR27","unstructured":"Dhurandhar, A., et\u00a0al.: Explanations based on the missing: towards contrastive explanations with pertinent negatives, Advances in Neural Information Processing Systems, 592\u2013603, (2018)"},{"key":"401_CR28","doi-asserted-by":"crossref","unstructured":"Liu, S., Kailkhura, B., Loveland, D., Han, Y.: Generative counterfactual introspection for explainable deep learning, in IEEE Global Conference on Signal and Information Processing. IEEE, (2019)","DOI":"10.1109\/GlobalSIP45357.2019.8969491"},{"key":"401_CR29","unstructured":"Joshi, S., Koyejo, O., Vijitbenjaronk, W., Kim, B., Ghosh, J.: Towards realistic individual recourse and actionable explanations in black-box decision making systems, in CoRR. https:\/\/arxiv.org\/abs\/1907.09615, (2019)"},{"key":"401_CR30","doi-asserted-by":"crossref","unstructured":"Samangouei, P., et\u00a0al.: Model explanation via decision boundary crossing transformations, in Proceedings of the European Conference on Computer Vision. ECCV, pp. 666\u2013681 (2018)","DOI":"10.1007\/978-3-030-01249-6_41"},{"key":"401_CR31","unstructured":"Singla, S., Pollack, B., Chen, J., Batmanghelich, K.: Explanation by progressive exaggeration, in ICLR, (2020)"},{"key":"401_CR32","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets, in NeurIPS Proceedings, (2014)"},{"issue":"10","key":"401_CR33","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"401_CR34","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I. J.: Adversarial autoencoders,\u201d CoRR, https:\/\/arxiv.org\/abs\/1511.05644, (2015)"},{"issue":"6","key":"401_CR35","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MIS.2019.2957223","volume":"34","author":"R Guidotti","year":"2019","unstructured":"Guidotti, R., Monreale, A., Giannotti, F., Pedreschi, D., Ruggieri, S., Turini, F.: Factual and counterfactual explanations for black box decision making. IEEE Intell. Syst. 34(6), 14\u201323 (2019)","journal-title":"IEEE Intell. Syst."},{"key":"401_CR36","doi-asserted-by":"crossref","unstructured":"Thanh-Tung, H., Tran, T.: Catastrophic forgetting and mode collapse in gans, in IJCNN, (2020)","DOI":"10.1109\/IJCNN48605.2020.9207181"},{"key":"401_CR37","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X., and, X. C.: Improved techniques for training gans, in NIPS, (2016)"},{"key":"401_CR38","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P. -A.: Extracting and composing robust features with denoising autoencoders, in ICML, (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"401_CR39","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation, in ICLR, (2018)"},{"key":"401_CR40","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1001\/archderm.138.12.1562","volume":"138","author":"WH Kruskal","year":"2002","unstructured":"Kruskal, W.H., Wallis, W.A.: Use of ranks in one-criterion variance analysis. Arch Dermatol. 138, 1562\u20131566 (2002)","journal-title":"Arch Dermatol."},{"key":"401_CR41","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1037\/0022-3514.77.6.1121","volume":"77","author":"J Kruger","year":"1999","unstructured":"Kruger, J., Dunning, D.: Unskilled and unaware of it: how difficulties in recognizing one\u2019s own incompetence lead to inflated self-assessments. Pers. Soc. Psychol. 77, 1121\u20131134 (1999)","journal-title":"Pers. Soc. Psychol."},{"key":"401_CR42","unstructured":"Petsiuk, V., Das, A., Saenko, K.: Rise: randomized input sampling for explanation of black-box models, in British Machine Vision Conference (BMVC), (2018)"},{"key":"401_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BF02289565","volume":"29","author":"JB Kruskal","year":"1964","unstructured":"Kruskal, J.B.: Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis. Psychometrika 29, 1\u201327 (1964)","journal-title":"Psychometrika"},{"key":"401_CR44","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1080\/01621459.1952.10483441","volume":"47","author":"L Izikson","year":"1952","unstructured":"Izikson, L., Sober, A.J., Mihm, M.C., Zembowicz, A., et al.: Prevalence of melanoma clinically resembling seborrheic keratosis: analysis of 9204 cases. J. Am. Stat. Assoc. 47, 583\u2013621 (1952)","journal-title":"J. Am. Stat. Assoc."},{"key":"401_CR45","unstructured":"Ho, T. K.: Random decision forests, in ICDAR. IEEE Computer Society, pp. 278\u2013282 (1995)"},{"key":"401_CR46","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.ejca.2019.07.009","volume":"119","author":"W Sondermann","year":"2019","unstructured":"Sondermann, W., Utikal, J.S., Enk, A.H., et al.: Prediction of melanoma evolution in melanocytic nevi via artificial intelligence: a call for prospective data. EJC Euro. J. Cancer 119, 30\u201334 (2019)","journal-title":"EJC Euro. J. Cancer"},{"key":"401_CR47","unstructured":"Haggenm\u00fcller, S., Maron, R.C., and Helker, A., et\u00a0al.: Skin cancer classification via convolutional neural networks: systematic review of studies involving human experts,\u201d EJC, Euro. J. Cancer, 156, (2021)"},{"key":"401_CR48","doi-asserted-by":"crossref","unstructured":"Celebi, M.E., Codella, N., Halpern, A., Shen, D., et\u00a0at.: Guest editorial skin lesion image analysis for melanoma detection, IEEE J. Biomed. Health Inform., 23(2), (2019)","DOI":"10.1109\/JBHI.2019.2897338"},{"key":"401_CR49","doi-asserted-by":"crossref","unstructured":"Kawahara, J., Hamarneh, G.: Fully convolutional neural networks to detect clinical dermoscopic features, IEEE J. Biomed. Health Inform., 23(2), (2019)","DOI":"10.1109\/JBHI.2018.2831680"},{"key":"401_CR50","doi-asserted-by":"crossref","unstructured":"Mahmouei, S. S., Aldeen, M., Stoecker, W.\u00a0V., and Garnavi, R. et\u00a0al.: Biologically inspired quadtree color detection in dermoscopy images of melanoma, IEEE J. Biomed. Health Inform., 23(2), (2019)","DOI":"10.1109\/JBHI.2018.2841428"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-023-00401-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-023-00401-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-023-00401-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T03:35:38Z","timestamp":1748403338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-023-00401-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,21]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["401"],"URL":"https:\/\/doi.org\/10.1007\/s41060-023-00401-z","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,21]]},"assertion":[{"value":"22 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}