Abstract
Computer Vision, and hence Artificial Intelligence-based extraction of information from images, has increasingly received attention over the last years, for instance in medical diagnostics. While the algorithms’ complexity is a reason for their increased performance, it also leads to the ‘black box’ problem, consequently decreasing trust towards AI. In this regard, “Explainable Artificial Intelligence” (XAI) allows to open that black box and to improve the degree of AI transparency. In this paper, we first discuss the theoretical impact of explainability on trust towards AI, followed by showcasing how the usage of XAI in a health-related setting can look like. More specifically, we show how XAI can be applied to understand why Computer Vision, based on deep learning, did or did not detect a disease (malaria) on image data (thin blood smear slide images). Furthermore, we investigate, how XAI can be used to compare the detection strategy of two different deep learning models often used for Computer Vision: Convolutional Neural Network and Multi-Layer Perceptron. Our empirical results show that i) the AI sometimes used questionable or irrelevant data features of an image to detect malaria (even if correctly predicted), and ii) that there may be significant discrepancies in how different deep learning models explain the same prediction. Our theoretical discussion highlights that XAI can support trust in Computer Vision systems, and AI systems in general, especially through an increased understandability and predictability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Grace, K., Salvatier, J., Dafoe, A., Zhang, B., Evans, O.: Viewpoint: when will AI exceed human performance? Evidence from AI experts. J. Artif. Intell. Res. 62, 729–754 (2018)
Maedche, A., et al.: AI-based digital assistants. Bus. Inf. Syst. Eng. 61(4), 535–544 (2019)
Ciresan, D., Meier, U., Masci, J., Schmidhuber, J.: Multi-column deep neural network for traffic sign classification. Neural Netw. 32, 333–338 (2012)
Lu, Y.: Artificial intelligence: a survey on evolution, models, applications and future trends. J. Manag. Anal. 6(1), 1–29 (2019)
Kulkarni, S., Seneviratne, N., Baig, M.S., Khan, A.H.H.: Artificial intelligence in medicine: where are we now? Acad. Radiol. 27(1), 62–70 (2020)
Rajaraman, S., et al.: Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. PeerJ 6, 1–17 (2018)
Rajaraman, S., Jaeger, S., Antani, S.K.: Performance evaluation of deep neural ensembles toward malaria parasite detection in thin-blood smear images. PeerJ 7, 1–16 (2019)
Teso, S., Kersting, K.: Explanatory interactive machine learning. In: Conitzer, V., Hadfield, G., Vallor, S. (eds.) AIES’19: AAAI/ACM Conference on AI, Ethics, and Society, pp. 239–245. Association for Computing Machinery, New York (2019)
Schwartz-Ziv, R., Tishby, N.: Opening the blackbox of Deep Neural Networks via Information (2017). https://arxiv.org/abs/1703.00810. Accessed 09 Feb 2020
Zednik, C.: Solving the black box problem: a normative framework for explainable artificial intelligence. Philos. Technol. 1–24 (2019)
Gunning, D., Aha, D.W.: DARPA’s Explainable Artificial Intelligence (XAI) program. AI Mag. 40(2), 44–58 (2019)
DARPA: Explainable Artificial Intelligence (XAI), DARPA program Update 2017, pp. 1–36 (2017). https://www.darpa.mil/attachments/XAIProgramUpdate.pdf. Accessed 27 Jan 2020
Corritore, C.L., Kracher, B., Wiedenbeck, S.: Online trust: concepts, evolving themes, a model. Int. J. Hum. Comput. Stud. 58(6), 737–758 (2003)
Söllner, M., Hoffmann, A., Hoffmann, H., Wacker, A., Leimeister, J.M.: Understanding the formation of trust in it artifacts. In: George, J.F. (eds.) Proceedings of the 33rd International Conference on Information Systems, ICIS 2012, pp. 1–18 (2012)
Jayaraman, P.P., et al.: Healthcare 4.0: a review of frontiers in digital health. Wiley Interdisc. Rev. Data Min. Knowl. Discov. 10(2), e1350 (2019)
Gilbert, F.J., Smye, S.W., Schönlieb, C.-B.: Artificial intelligence in clinical imaging: a health system approach. Clin. Radiol. 75(1), 3–6 (2020)
Meske, C., Amojo, I.: Social bots as initiators for human interaction in enterprise social networks. In: Proceedings of the 29th Australasian Conference on Information Systems (ACIS), paper 35, pp. 1–22 (2018)
Kemppainen, L., Pikkarainen, M., Hurmelinna-Laukkanen, P., Reponen, J.: Connected health innovation: data access challenges in the interface of AI companies and hospitals. Technol. Innov. Manag. Rev. 9(12), 43–55 (2019)
Poncette, A.-S., Meske, C., Mosch, L., Balzer, F.: How to overcome barriers for the implementation of new information technologies in intensive care medicine. In: Yamamoto, S., Mori, H. (eds.) HCII 2019. LNCS, vol. 11570, pp. 534–546. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-22649-7_43
Stieglitz, S., Meske, C., Ross, B., Mirbabaie, M.: Going back in time to predict the future - the complex role of the data collection period in social media analytics. Inf. Syst. Front. 22(2), 395–409 (2018). https://doi.org/10.1007/s10796-018-9867-2
Walsh, S., et al.: Decision support systems in oncology. JCO Clin. Cancer Inf. 3, 1–9 (2019)
Ferroni, P., et al.: Breast cancer prognosis using a machine learning approach. Cancers 11(3), 328 (2019)
Song, D.-Y., Kim, S.Y., Bong, G., Kim, J.M., Yoo, H.J.: The use of artificial intelligence in screening and diagnosis of autism spectrum disorder: a literature review. J. Korean Acad. Child Adolesc. Psychiatry 30(4), 145–152 (2019)
Woldaregay, A.Z., et al.: Data-driven modeling and prediction of blood glucose dynamics: machine learning applications in type 1 diabetes. Artif. Intell. Med. 98, 109–134 (2019)
Gi-Martin, M., Montero, J.M., San-Segundo, R.: Parkinson’s disease detection from drawing movements using convolutional neural networks. Electronics 8(8), 907 (2019)
Spathis, D., Vlamos, P.: Diagnosing asthma and chronic obstructive pulmonary disease with machine learning. Health Inf. J. 25(3), 811–827 (2019)
Eggerth, A., Hayn, D., Schreier, G.: Medication management needs information and communications technology-based approaches, including telehealth and artificial intelligence. Brit. J. Clin. Pharmacol. 1–8 (2019)
Khanna, S.: Artificial intelligence: contemporary applications and future compass. Int. Dent. J. 60(4), 269–272 (2010)
Esteva, A., et al.: A guide to deep learning in healthcare. Nat. Med. 25(1), 24–29 (2019)
Lewis, S.J., Gandomkar, Z., Brennan, P.C.: Artificial intelligence in medical imaging practice: looking to the future. J. Med. Radiat. Sci. 66, 292–295 (2019)
Jiang, F., et al.: Artificial intelligence in healthcare: past, present and future. Stroke Vascul. Neurol. 2(4), 230–243 (2017)
Son, J., Shin, J.Y., Kim, H.D., Jung, K.-H., Park, K.H., Park, S.J.: Development and validation of deep learning models for screening multiple abnormal findings in retinal fundus images. Ophthalmology 127(1), 85–94 (2019)
Chen, M., Zhou, P., Wu, D., Hu, L., Hassan, M.M., Alamri, A.: AI-Skin: skin disease recognition based on self-learning and wide data collection through a closed-loop framework. Inf. Fusion 54, 1–9 (2020)
Valliani, A.A., Ranti, D., Oermann, E.K.: Deep learning in neurology: a systematic review. Neurol. Ther. 8(2), 351–365 (2019)
Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386–408 (1958)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Jang, D.-H., et al.: Developing neural network models for early detection of cardiac arrest in emergency department. Am. J. Emerg. Med. 38(1), 43–49 (2020)
Kim, M., et al.: Deep learning medical imaging. Neurospine 16(4), 657–668 (2019)
Saba, L., et al.: The present and future of deep learning in radiology. Eur. J. Radiol. 114, 14–24 (2019)
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on Explainable Artificial Intelligence (XAI). IEEE Access 6, 52138–52160 (2018)
Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., Yang, G.-Z.: XAI – explainable artificial intelligence. Sci. Robot. 4(37), eaay7120 (2019)
Dosilovic, F.K., Brcic, M., Hlupic, N.: Explainable artificial intelligence: a survey. In: Proceedings of 41st International Convention on Information and Communication Technology, Electronics and Microelectronics, Opatija Croatia, pp. 210–215 (2018)
Kühl, N., Lobana, J., Meske, C.: Do you comply with AI? Personalized explanations of learning algorithms and their impact on employees compliance behavior. In: 40th International Conference on Information Systems, pp. 1–6 (2019, forthcoming)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51(5), 93 (2018)
Ras, G., van Gerven, M., Haselager, P.: Explanation methods in deep learning: users, values, concerns and challenges 1–15 (2018). arXiv:1803.07517. Accessed 27 Jan 2020
Meske, C.: Digital workplace transformation – on the role of self-determination in the context of transforming work environments. In: Proceedings of the 27th European Conference on Information Systems (ECIS), pp. 1–18 (2019)
Yan, Z., Kantola, R., Zhang, P.: A research model for human-computer trust interaction. In: Proceedings of the 2011 IEEE 10th International Conference on Trust, Security and Privacy in Computing and Communications, pp. 274–281 (2011)
Mühl, K., Strauch, C., Grabmaier, C., Reithinger, S., Huckauf, A., Baumann, M.: Get ready for being chauffeured: passenger’s preferences and trust while being driven by human automation. Hum. Factors, pp. 1–17 (2019)
Qasim, A.F., Meziane, F., Aspin, R.: Digital watermarking: applicability for developing trust in medical imaging workflows state of the art review. Comput. Sci. Rev. 27, 45–60 (2018)
Gulati, S., Sousa, S., Lamas, D.: Design, development and evaluation of a human-computer trust scale. Behav. Technol. 38(10), 1004–1015 (2019)
McKnight, D.H., Carter, M., Thatcher, J.B., Clay, P.F.: Trust in specific technology: an investigation of its components and measures. ACM Trans. Manag. Inf. Syst. (TMIS) 2(2), 12–32 (2011)
Mayer, R.C., Davis, J.H., Schoorman, F.D.: An integrative model of organizational trust. Acad. Manag. Rev. 20(3), 709–734 (1995)
Muir, B.M., Moray, N.: Trust in automation. Part II. Experimental studies of trust and human intervention in a process control simulation. Ergonomics 39(3), 429–460 (1996)
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?” Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
de Sousa, I.P., et al.: Local interpretable model-agnostic explanations for classification of lymph node metastases. Sensors 19(13), 2969 (2019)
Weitz, K., Hassan, T., Schmid, U., Garbas, J.-U.: Deep-learned faces of pain and emotions: elucidating the differences of facial expressions with the help of explainable AI methods. TM-Tech. Mess. 86(7–8), 404–412 (2019)
Kaggle Malaria Cell Images Dataset. https://www.kaggle.com/iarunava/cell-images-for-detecting-malaria. Accessed 27 Jan 2020
National Library of Medicine – Malaria Datasets. https://lhncbc.nlm.nih.gov/publication/pub9932. Accessed 27 Jan 2020
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Meske, C., Bunde, E. (2020). Transparency and Trust in Human-AI-Interaction: The Role of Model-Agnostic Explanations in Computer Vision-Based Decision Support. In: Degen, H., Reinerman-Jones, L. (eds) Artificial Intelligence in HCI. HCII 2020. Lecture Notes in Computer Science(), vol 12217. Springer, Cham. https://doi.org/10.1007/978-3-030-50334-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-50334-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50333-8
Online ISBN: 978-3-030-50334-5
eBook Packages: Computer ScienceComputer Science (R0)