{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:59:14Z","timestamp":1777658354905,"version":"3.51.4"},"reference-count":27,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","award":["001"],"award-info":[{"award-number":["001"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Problem: An application of Explainable Artificial Intelligence Methods for COVID CT-Scan classifiers is presented. Motivation: It is possible that classifiers are using spurious artifacts in dataset images to achieve high performances, and such explainable techniques can help identify this issue. Aim: For this purpose, several approaches were used in tandem, in order to create a complete overview of the classificatios. Methodology: The techniques used included GradCAM, LIME, RISE, Squaregrid, and direct Gradient approaches (Vanilla, Smooth, Integrated). Main results: Among the deep neural networks architectures evaluated for this image classification task, VGG16 was shown to be most affected by biases towards spurious artifacts, while DenseNet was notably more robust against them. Further impacts: Results further show that small differences in validation accuracies can cause drastic changes in explanation heatmaps for DenseNet architectures, indicating that small changes in validation accuracy may have large impacts on the biases learned by the networks. Notably, it is important to notice that the strong performance metrics achieved by all these networks (Accuracy, F1 score, AUC all in the 80 to 90% range) could give users the erroneous impression that there is no bias. However, the analysis of the explanation heatmaps highlights the bias.<\/jats:p>","DOI":"10.3390\/s21165657","type":"journal-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T04:22:20Z","timestamp":1629692540000},"page":"5657","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7536-0081","authenticated-orcid":false,"given":"Iam","family":"Palatnik de Sousa","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22453-900, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9790-1328","authenticated-orcid":false,"given":"Marley M. B. R.","family":"Vellasco","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22453-900, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4513-0004","authenticated-orcid":false,"given":"Eduardo","family":"Costa da Silva","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22453-900, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,23]]},"reference":[{"key":"ref_1","unstructured":"Zhao, J., Zhang, Y., He, X., and Xie, P. (2020). COVID-CT-Dataset: A CT scan dataset about COVID-19. arXiv."},{"key":"ref_2","first-page":"1","article-title":"Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images","volume":"10","author":"Wang","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cohen, J.P., Morrison, P., Dao, L., Roth, K., Duong, T.Q., and Ghassemi, M. (2020). COVID-19 Image Data Collection: Prospective Predictions Are the Future. arXiv.","DOI":"10.59275\/j.melba.2020-48g7"},{"key":"ref_4","unstructured":"Chan, J. (2021, August 19). DLAI3 Hackathon Phase3 COVID-19 CXR Challenge. Available online: https:\/\/www.kaggle.com\/c\/dlai3-phase3\/overview."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"113909","DOI":"10.1016\/j.eswa.2020.113909","article-title":"Coronavirus disease (COVID-19) detection in Chest X-Ray images using majority voting based classifier ensemble","volume":"165","author":"Chandra","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_6","first-page":"9887","article-title":"COVID-Classifier: An automated machine learning model to assist in the diagnosis of COVID-19 infection in chest X-ray images","volume":"165","author":"Khuzani","year":"2020","journal-title":"medRxiv"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"427","DOI":"10.3389\/fmed.2020.00427","article-title":"Deep learning-based decision-tree classifier for COVID-19 diagnosis from chest X-ray imaging","volume":"7","author":"Yoo","year":"2020","journal-title":"Front. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"42370","DOI":"10.1109\/ACCESS.2021.3065456","article-title":"Bias analysis on public X-ray image datasets of pneumonia and COVID-19 patients","volume":"9","author":"Igual","year":"2021","journal-title":"IEEE Access"},{"key":"ref_9","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"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","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"103865","DOI":"10.1016\/j.compbiomed.2020.103865","article-title":"Concept attribution: Explaining CNN decisions to physicians","volume":"123","author":"Graziani","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Li, F.-F. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"He, X., Yang, X., Zhang, S., Zhao, J., Zhang, Y., Xing, E., and Xie, P. (2020). Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans. medRxiv.","DOI":"10.1101\/2020.04.13.20063941"},{"key":"ref_16","unstructured":"He, X. (2021, August 19). DenseNet169 Baseline. Available online: https:\/\/github.com\/UCSD-AI4H\/COVID-CT\/tree\/master\/baseline%20methods\/Self-Trans."},{"key":"ref_17","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1007\/s10489-020-01867-1","article-title":"COVID-19 detection and disease progression visualization: Deep learning on chest X-rays for classification and coarse localization","volume":"51","author":"Zebin","year":"2021","journal-title":"Appl. Intell."},{"key":"ref_19","first-page":"100427","article-title":"X-ray image based COVID-19 detection using pre-trained deep learning models","volume":"20","author":"Horry","year":"2020","journal-title":"engrXiv"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., and Summers, R. (2017, January 21\u201326). Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the IEEE CVPR, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref_21","unstructured":"Tan, M., and Le, Q.V. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). 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, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","article-title":"SLIC superpixels compared to state-of-the-art superpixel methods","volume":"34","author":"Achanta","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Palatnik de Sousa, I., Maria Bernardes Rebuzzi Vellasco, M., and Costa da Silva, E. (2019). Local Interpretable Model-Agnostic Explanations for Classification of Lymph Node Metastases. Sensors, 19.","DOI":"10.3390\/s19132969"},{"key":"ref_25","unstructured":"Petsiuk, V., Das, A., and Saenko, K. (2018). Rise: Randomized input sampling for explanation of black-box models. arXiv."},{"key":"ref_26","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F., and Wattenberg, M. (2017). Smoothgrad: Removing noise by adding noise. arXiv."},{"key":"ref_27","unstructured":"Sundararajan, M., Taly, A., and Yan, Q. (2017). Axiomatic attribution for deep networks. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/16\/5657\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:49:27Z","timestamp":1760165367000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/16\/5657"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":27,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["s21165657"],"URL":"https:\/\/doi.org\/10.3390\/s21165657","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,23]]}}}