Abstract
Robust object detection in side-scan sonar (SSS) is challenging due to the impact of adversarial perturbations and environmental noise, which limit reliable deployment in autonomous underwater vehicles (AUVs). While existing approaches primarily focus on denoising techniques and data augmentation, they do not explicitly enhance the model's robustness against adversarial perturbations. To overcome these limitations, we introduce ROSAR, a framework that extends our prior work on knowledge distillation (KD) by integrating adversarial retraining, jointly tackling the dual challenges of model robustness and effi-ciency in SSS object detection. To support adversarial retraining and robustness evaluation, we introduce three novel, publicly available SSS datasets, each capturing different sonar setups and noise conditions. Furthermore, we define two SSS safety properties that guide the generation of adversarial datasets for retraining. Through a comparative analysis of projected gradient descent (PGD) and patch-based adversarial attacks, ROSAR demonstrates significant improvements in model robustness and detection accuracy under SSS-specific conditions, enhancing the model's robustness by up to 1.85%. ROSAR is publicly available at https://github.com/remaro-network/ROSAR-framework.

Abstract
Breast cancer, the most prevalent cancer among women, poses a significant healthcare challenge, demanding effective early detection for optimal treatment outcomes. Mammography, the gold standard for breast cancer detection, employs low-dose X-rays to reveal tissue details, particularly cancerous masses and calcium deposits. This work focuses on evaluating the impact of incorporating anatomical knowledge to improve the performance and robustness of a breast cancer classification model. In order to achieve this, a methodology was devised to generate anatomical pseudo-labels, simulating plausible anatomical variations in cancer masses. These variations, encompassing changes in mass size and intensity, closely reflect concepts from the BI-RADs scale. Besides anatomical-based augmentation, we propose a novel loss term promoting the learning of cancer grading by our model. Experiments were conducted on publicly available datasets simulating both in-distribution and out-of-distribution scenarios to thoroughly assess the model's performance under various conditions.

Abstract
Deep-learning techniques can improve the efficiency of medical diagnosis while challenging human experts’ accuracy. However, the rationale behind these classifier’s decisions is largely opaque, which is dangerous in sensitive applications such as healthcare. Case-based explanations explain the decision process behind these mechanisms by exemplifying similar cases using previous studies from other patients. Yet, these may contain personally identifiable information, which makes them impossible to share without violating patients’ privacy rights. Previous works have used GANs to generate anonymous case-based explanations, which had limited visual quality. We solve this issue by employing a latent diffusion model in a three-step procedure: generating a catalogue of synthetic images, removing the images that closely resemble existing patients, and using this anonymous catalogue during an explanation retrieval process. We evaluate the proposed method on the MIMIC-CXR-JPG dataset and achieve explanations that simultaneously have high visual quality, are anonymous, and retain their explanatory value.

Abstract

Abstract
Contrastive Analysis (CA) regards the problem of identifying patterns in images that allow distinguishing between a background (BG) dataset (i.e. healthy subjects) and a target (TG) dataset (i.e. unhealthy subjects). Recent works on this topic rely on variational autoencoders (VAE) or contrastive learning strategies to learn the patterns that separate TG samples from BG samples in a supervised manner. However, the dependency on target (unhealthy) samples can be challenging in medical scenarios due to their limited availability. Also, the blurred reconstructions of VAEs lack utility and interpretability. In this work, we redefine the CA task by employing a self-supervised contrastive encoder to learn a latent representation encoding only common patterns from input images, using samples exclusively from the BG dataset during training, and approximating the distribution of the target patterns by leveraging data augmentation techniques. Subsequently, we exploit state-of-the-art generative methods, i.e. diffusion models, conditioned on the learned latent representation to produce a realistic (healthy) version of the input image encoding solely the common patterns. Thorough validation on a facial image dataset and experiments across three brain MRI datasets demonstrate that conditioning the generative process of state-of-the-art generative methods with the latent representation from our self-supervised contrastive encoder yields improvements in the generated image quality and in the accuracy of image classification. The code is available at https://github.com/CristianoPatricio/unsupervised-contrastive-cond-diff.

Abstract
Concept-based models naturally lend themselves to the development of inherently interpretable skin lesion diagnosis, as medical experts make decisions based on a set of visual patterns of the lesion. Nevertheless, the development of these models depends on the existence of concept-annotated datasets, whose availability is scarce due to the specialized knowledge and expertise required in the annotation process. In this work, we show that vision-language models can be used to alleviate the dependence on a large number of concept-annotated samples. In particular, we propose an embedding learning strategy to adapt CLIP to the downstream task of skin lesion classification using concept-based descriptions as textual embeddings. Our experiments reveal that vision-language models not only attain better accuracy when using concepts as textual embeddings, but also require a smaller number of concept-annotated samples to attain comparable performance to approaches specifically devised for automatic concept generation.