The application of deep learning in medical imaging has significantly advanced diagnostic capabilities, enhancing both accuracy and efficiency. Despite these benefits, the lack of transparency in these AI models, often termed "black boxes," raises concerns about their reliability in clinical settings. Explainable AI (XAI) aims to mitigate these concerns by developing methods that make AI decisions understandable and trustworthy. In this study, we propose Tumor Aware Counterfactual Explanations (TACE), a framework designed to generate reliable counterfactual explanations for medical images. Unlike existing methods, TACE focuses on modifying tumor-specific features without altering the overall organ structure, ensuring the faithfulness of the counterfactuals. We achieve this by including an additional step in the generation process which allows to modify only the region of interest (ROI), thus yielding more reliable counterfactuals as the rest of the organ remains unchanged. We evaluate our method on mammography images and brain MRI. We find that our method far exceeds existing state-of-the-art techniques in quality, faithfulness, and generation speed of counterfactuals. Indeed, more faithful explanations lead to a significant improvement in classification success rates, with a 10.69% increase for breast cancer and a 98.02% increase for brain tumors. The code of our work is available at https://github.com/ispamm/TACE.

The progression of X-ray technology introduces diverse image styles that need to be adapted to the preferences of radiologists. To support this task, we introduce a novel deep learning-based metric that quantifies style differences of non-matching image pairs. At the heart of our metric is an encoder capable of generating X-ray image style representations. This encoder is trained without any explicit knowledge of style distances by exploiting Simple Siamese learning. During inference, the style representations produced by the encoder are used to calculate a distance metric for non-matching image pairs. Our experiments investigate the proposed concept for a disclosed reproducible and a proprietary image processing pipeline along two dimensions: First, we use a t-distributed stochastic neighbor embedding (t-SNE) analysis to illustrate that the encoder outputs provide meaningful and discriminative style representations. Second, the proposed metric calculated from the encoder outputs is shown to quantify style distances for non-matching pairs in good alignment with the human perception. These results confirm that our proposed method is a promising technique to quantify style differences, which can be used for guided style selection as well as automatic optimization of image pipeline parameters.

Large pre-trained language models have achieved impressive results on various style classification tasks, but they often learn spurious domain-specific words to make predictions (Hayati et al., 2021). While human explanation highlights stylistic tokens as important features for this task, we observe that model explanations often do not align with them. To tackle this issue, we introduce StyLEx, a model that learns from human-annotated explanations of stylistic features and jointly learns to perform the task and predict these features as model explanations. Our experiments show that StyLEx can provide human-like stylistic lexical explanations without sacrificing the performance of sentence-level style prediction on both in-domain and out-of-domain datasets. Explanations from StyLEx show significant improvements in explanation metrics (sufficiency, plausibility) and when evaluated with human annotations. They are also more understandable by human judges compared to the widely-used saliency-based explanation baseline.

Most humans can recognize a cat or dog at an early age. Asked to articulate how they know if an animal is a cat or a dog, an adult might fumble for an explanation by describing experience, something such as "cats appraise you in a distant fashion, but dogs try to jump up on you and lick your face." We don't really articulate what we know, in other words. The signature achievement of artificial intelligence in the past two decades is classifying pictures of cats and dogs, among other things, by assigning them to categories. But AI programs never explain how they "know" what they supposedly "know."

Neural networks are capable of completing a wide range of tasks. Understanding how they arrive at their decisions, on the other hand, is frequently a mystery that goes unexplored. Explaining a neural model's decision process could have a significant social impact in domains where human oversight is crucial, like medical image processing and autonomous driving. These revelations could be instrumental in advising healthcare practitioners and possibly enhancing scientific breakthroughs. For a visual explanation of classifiers, there have been approaches such as attention maps.

Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize these properties. Here we present StylEx, a method for doing this, by training a generative model to specifically explain multiple attributes that underlie classifier decisions. A natural source for such attributes is the StyleSpace of StyleGAN, which is known to generate semantically meaningful dimensions in the image. However, because standard GAN training is not dependent on the classifier, it may not represent these attributes which are important for the classifier decision, and the dimensions of StyleSpace may represent irrelevant attributes. To overcome this, we propose a training procedure for a StyleGAN, which incorporates the classifier model, in order to learn a classifier-specific StyleSpace. Explanatory attributes are then selected from this space. These can be used to visualize the effect of changing multiple attributes per image, thus providing image-specific explanations. We apply StylEx to multiple domains, including animals, leaves, faces and retinal images. For these, we show how an image can be modified in different ways to change its classifier output. Our results show that the method finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are human-interpretable as measured in user-studies.