Interpretable methods based on prototypical patches recognize various components in an image in order to explain their reasoning to humans. However, existing prototype-based methods can learn prototypes that are not in line with human visual perception, i.e., the same prototype can refer to different concepts in the real world, making interpretation not intuitive. Driven by the principle of explainability-by-design, we introduce PIP-Net (Patch-based Intuitive Prototypes Network): an interpretable image classification model that learns prototypical parts in a self-supervised fashion which correlate better with human vision. PIP-Net can be interpreted as a sparse scoring sheet where the presence of a prototypical part in an image adds evidence for a class. The model can also abstain from a decision for out-of-distribution data by saying “I haven't seen this before”. We only use image-level labels and do not rely on any part annotations. PIP-Net is globally interpretable since the set of learned prototypes shows the entire reasoning of the model. A smaller local explanation locates the relevant prototypes in one image. We show that our prototypes correlate with ground-truth object parts, indicating that PIP-Net closes the “semantic gap” between latent space and pixel space. Hence, our PIP-Net with interpretable prototypes enables users to interpret the decision making process in an intuitive, faithful and semantically meaningful way. Code is available at https://github.com/M-Nauta/PIPNet.

The goal of Explainable AI (XAI) is to make the reasoning of a machine learning model accessible to humans, such that users of an AI system can evaluate and judge the underlying model. Due to the blackbox nature of XAI methods it is, however, hard to disentangle the contribution of a model and the explanation method to the final output. It might be unclear on whether an unexpected output is caused by the model or the explanation method. Explanation models, therefore, need to be evaluated in technical (e.g. fidelity to the model) and user-facing (correspondence to domain knowledge) terms. A recent survey has identified 29 different automated approaches to quantitatively evaluate explanations. In this work, we take an additional perspective and analyse which toolkits and data sets are available. We investigate which evaluation metrics are implemented in the toolkits and whether they produce the same results. We find that only a few aspects of explanation quality are currently covered, data sets are rare and evaluation results are not comparable across different toolkits. Our survey can serve as a guide for the XAI community for identifying future directions of research, and most notably, standardisation of evaluation.

Proximal femur fractures represent a major health concern, and substantially contribute to the morbidity of elderly. Correct classification and diagnosis of hip fractures has a significant impact on mortality, costs and hospital stay. In this paper, we present a method and empirical validation for automatic subclassification of proximal femur fractures and Dutch radiological report generation that does not rely on manually curated data. The fracture classification model was trained on 11,000 X-ray images obtained from 5000 electronic health records in a general hospital. To generate the Dutch reports, we first trained an embedding model on 20,000 radiological reports of pelvic region fractures, and used its embeddings in the report generation model. We trained the report generation model on the 5000 radiological reports associated with the fracture cases. Our report generation model is on par with state-of-the-art in terms of BLEU and ROUGE scores. This is promising, because in contrast to those earlier works, our approach does not require manual preprocessing of either images or the reports. This boosts the applicability of automatic clinical report generation in practice. A quantitative and qualitative user study among medical students found no significant difference in provenance of real and generated reports. A qualitative, in-depth clinical relevance study with medical domain experts showed that from a human perspective the quality of the generated reports approximates the quality of the original reports and highlights challenges in creating sufficiently detailed and versatile training data for automatic radiology report generation.

Prototype-based methods use interpretable representations to address the black-box nature of deep learning models, in contrast to post-hoc explanation methods that only approximate such models. We propose the Neural Prototype Tree (ProtoTree), an intrinsically interpretable deep learning method for fine-grained image recognition. ProtoTree combines prototype learning with decision trees, and thus results in a globally interpretable model by design. Additionally, ProtoTree can locally explain a single prediction by outlining a decision path through the tree. Each node in our binary tree contains a trainable prototypical part. The presence or absence of this learned prototype in an image determines the routing through a node. Decision making is therefore similar to human reasoning: Does the bird have a red throat? And an elongated beak? Then it’s a hummingbird! We tune the accuracy-interpretability trade-off using ensemble methods, pruning and binarizing. We apply pruning without sacrificing accuracy, resulting in a small tree with only 8 learned prototypes along a path to classify a bird from 200 species. An ensemble of 5 ProtoTrees achieves competitive accuracy on the CUB-200-2011 and Stanford Cars data sets. Code is available at github.com/M-Nauta/ProtoTree.

While deep neural networks (DNNs) have been shown to outperform humans on many vision tasks, their intransparent decision making process inhibits wide-spread uptake, especially in high-risk scenarios. The BagNet architecture was designed to learn visual features that are easier to explain than the feature representation of other convolutional neural networks (CNNs). Previous experiments with BagNet were focused on natural images providing rich texture and color information. In this paper, we investigate the performance and interpretability of BagNet on a data set of human sketches, i.e., a data set with limited color and no texture information. We also introduce a heatmap interpretability score (HI score) to quantify model interpretability and present a user study to examine BagNet interpretability from user perspective. Our results show that BagNet is by far the most interpretable CNN architecture in our experiment setup based on the HI score.

Social media accounts are valuable for hackers for spreading phishing links, malware and spam. Furthermore, some people deliberately hack an acquaintance to damage his or her image. This paper describes a classification for detecting hacked Twitter accounts. The model is mainly based on features associated with behavioural change such as changes in language, source, URLs, retweets, frequency and time. We experiment with a Twitter data set containing tweets of more than 100 Dutch users including 37 who were hacked. The model detects 99% of the malicious tweets which proves that behavioural changes can reveal a hack and that anomaly-based features perform better than regular features. Our approach can be used by social media systems such as Twitter to automatically detect a hack of an account only a short time after the fact allowing the legitimate owner of the account to be warned or protected, preventing reputational damage and annoyance.