In this paper, we present the potential of Explainable Artificial Intelligence methods for decision support in medical image analysis scenarios. Using three types of explainable methods applied to the same medical image data set, we aimed to improve the comprehensibility of the decisions provided by the Convolutional Neural Network (CNN). In vivo gastral images obtained by a video capsule endoscopy (VCE) were the subject of visual explanations, with the goal of increasing health professionals’ trust in black-box predictions. We implemented two post hoc interpretable machine learning methods, called Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), and an alternative explanation approach, the Contextual Importance and Utility (CIU) method. The produced explanations were assessed by human evaluation. We conducted three user studies based on explanations provided by LIME, SHAP and CIU. Users from different non-medical backgrounds carried out a series of tests in a web-based survey setting and stated their experience and understanding of the given explanations. Three user groups (n = 20, 20, 20) with three distinct forms of explanations were quantitatively analyzed. We found that, as hypothesized, the CIU-explainable method performed better than both LIME and SHAP methods in terms of improving support for human decision-making and being more transparent and thus understandable to users. Additionally, CIU outperformed LIME and SHAP by generating explanations more rapidly. Our findings suggest that there are notable differences in human decision-making between various explanation support settings. In line with that, we present three potential explainable methods that, with future improvements in implementation, can be generalized to different medical data sets and can provide effective decision support to medical experts.

As autonomous agents become more self-governing, ubiquitous and sophisticated, it is vital that humans should have effective interactions with them. Agents often use Machine Learning (ML) for acquiring expertise, but traditional ML methods produce opaque results which are difficult to interpret. Hence, these autonomous agents should be able to explain their behaviour and decisions before they can be trusted by humans. This paper focuses on analyzing the human understanding of the explainable agents behaviour. It conducts a preliminary human-agent interaction study to investigate the effect of explanations on the introduced bias in human-agent decision making for the human participants. We test the hypothesis where different explanation types are used to detect the bias introduced in the autonomous agents decisions. We present three user groups: Agents without explanation, and explainable agents using two different algorithms which automatically generate different explanations for agent actions. Quantitative analysis of three user groups (n = 20, 25, 20) in which users detect the bias in agents' decisions for each explanation type for 15 test data cases is conducted for three different explanations types. Although the interaction study does not give significant findings, but it shows the notable differences between the explanation based recommendations and non-XAI recommendations in human-agent decision making.

In the present paper we present the potential of Explainable Artificial Intelligence methods for decision-support in medical image analysis scenarios. With three types of explainable methods applied to the same medical image data set our aim was to improve the comprehensibility of the decisions provided by the Convolutional Neural Network (CNN). The visual explanations were provided on in-vivo gastral images obtained from a Video capsule endoscopy (VCE), with the goal of increasing the health professionals' trust in the black box predictions. We implemented two post-hoc interpretable machine learning methods LIME and SHAP and the alternative explanation approach CIU, centered on the Contextual Value and Utility (CIU). The produced explanations were evaluated using human evaluation. We conducted three user studies based on the explanations provided by LIME, SHAP and CIU. Users from different non-medical backgrounds carried out a series of tests in the web-based survey setting and stated their experience and understanding of the given explanations. Three user groups (n=20, 20, 20) with three distinct forms of explanations were quantitatively analyzed. We have found that, as hypothesized, the CIU explainable method performed better than both LIME and SHAP methods in terms of increasing support for human decision-making as well as being more transparent and thus understandable to users. Additionally, CIU outperformed LIME and SHAP by generating explanations more rapidly. Our findings suggest that there are notable differences in human decisionmaking between various explanation support settings. In line with that, we present three potential explainable methods that can with future improvements in implementation be generalized on different medical data sets and can provide great decision-support for medical experts.

Many techniques have been proposed in recent years that attempt to explain results of image classifiers, notably for the case when the classifier is a deep neural network. This paper presents an implementation of the Contextual Importance and Utility method for explaining image classifications. It is an R package that can be used with the most usual image classification models. The paper shows results for typical benchmark images, as well as for a medical data set of gastroenterological images. For comparison, results produced by the LIME method are included. Results show that CIU produces similar or better results than LIME with significantly shorter calculation times. However, the main purpose of this paper is to bring the existence of this package to general knowledge and use, rather than comparing with other explanation methods.