Abstract
The high incidence of cervical cancer in women has prompted the research of automatic screening methods. This work focuses on two of the steps present in such systems, more precisely, the identification of cervical lesions and their respective classification. The development of automatic methods for these tasks is associated with some shortcomings, such as acquiring sufficient and representative clinical data. These limitations are addressed through a hybrid pipeline based on a deep learning model (RetinaNet) for the detection of abnormal regions, combined with random forest and SVM classifiers for their categorization, and complemented by the use of domain knowledge in its design. Additionally, the nuclei in each detected region are segmented, providing a set of nuclei-specific features whose impact on the classification result is also studied. Each module is individually assessed in addition to the complete system, with the latter achieving a precision, recall and F1 score of 0.04, 0.20 and 0.07, respectively. Despite the low precision, the system demonstrates potential as an analysis support tool with the capability of increasing the overall sensitivity of the human examination process.

Abstract
The increasing popularity of attention mechanisms in deep learning algorithms for computer vision and natural language processing made these models attractive to other research domains. In healthcare, there is a strong need for tools that may improve the routines of the clinicians and the patients. Naturally, the use of attention-based algorithms for medical applications occurred smoothly. However, being healthcare a domain that depends on high-stake decisions, the scientific community must ponder if these high-performing algorithms fit the needs of medical applications. With this motto, this paper extensively reviews the use of attention mechanisms in machine learning methods (including Transformers) for several medical applications based on the types of tasks that may integrate several works pipelines of the medical domain. This work distinguishes itself from its predecessors by proposing a critical analysis of the claims and potentialities of attention mechanisms presented in the literature through an experimental case study on medical image classification with three different use cases. These experiments focus on the integrating process of attention mechanisms into established deep learning architectures, the analysis of their predictive power, and a visual assessment of their saliency maps generated by post-hoc explanation methods. This paper concludes with a critical analysis of the claims and potentialities presented in the literature about attention mechanisms and proposes future research lines in medical applications that may benefit from these frameworks.

Abstract
Facial expressions are one of the most common way to externalize our emotions. However, the same emotion can have different effects on the same person and has different effects on different people. Based on this, we developed a system capable of detecting the facial expressions of a person in real-time, occluding the eyes (simulating the use of virtual reality glasses). To estimate the position of the eyes, in order to occlude them, Multi-task Cascade Convolutional Neural Networks (MTCNN) were used. A residual network, a VGG, and the combination of both models, were used to perform the classification of 7 different types of facial expressions (Angry, Disgust, Fear, Happy, Sad, Surprise, Neutral), classifying the occluded and non-occluded dataset. The combination of both models, achieved an accuracy of 64.9% for the occlusion dataset and 62.8% for no occlusion, using the FER-2013 dataset. The primary goal of this work was to evaluate the influence of occlusion, and the results show that the majority of the classification is done with the mouth and chin. Nevertheless, the results were far from the state-of-the-art, which is expect to be improved, mainly by adjusting the MTCNN.

Abstract
Contrastive Analysis (CA) detects anomalies by contrasting patterns unique to a target group (e.g., unhealthy subjects) from those in a background group (e.g., healthy subjects). In the context of brain MRIs, existing CA approaches rely on supervised contrastive learning or variational autoencoders (VAEs) using both healthy and unhealthy data, but such reliance on target samples is challenging in clinical settings. Unsupervised Anomaly Detection (UAD) learns a reference representation of healthy anatomy, eliminating the need for target samples. Deviations from this reference distribution can indicate potential anomalies. In this context, diffusion models have been increasingly adopted in UAD due to their superior performance in image generation compared to VAEs. Nonetheless, precisely reconstructing the anatomy of the brain remains a challenge. In this work, we bridge CA and UAD by reformulating contrastive analysis principles for the unsupervised setting. We propose an unsupervised framework to improve the reconstruction quality by training a self-supervised contrastive encoder on healthy images to extract meaningful anatomical features. These features are used to condition a diffusion model to reconstruct the healthy appearance of a given image, enabling interpretable anomaly localization via pixel-wise comparison. We validate our approach through a proof-of-concept on a facial image dataset and further demonstrate its effectiveness on four brain MRI datasets, outperforming baseline methods in anomaly localization on the NOVA benchmark.

Abstract
Medical case retrieval plays a crucial role in clinical decision-making by enabling healthcare professionals to find relevant cases based on patient records, diagnostic images, and textual descriptions. Given the inherently multimodal nature of medical data, effective retrieval requires models that can bridge the gap between different modalities. Traditional retrieval approaches often rely on unimodal representations, limiting their ability to capture cross-modal relationships. Recent advances in dense model-based techniques have shown promise in overcoming these limitations by encoding multimodal information into a shared latent space, facilitating retrieval based on semantic similarity. This paper investigates the potential of dense models to enhance multimodal search systems. We evaluate various dense model-based approaches to assess which model characteristics have the greatest impact on retrieval effectiveness, using the medical case-based retrieval task from ImageCLEFmed 2013 as a benchmark. Our findings indicate that different dense model approaches substantially impact retrieval effectiveness, and that applying the CombMAX fusion methodto combine their output results further improves effectiveness. Extending context length, however, yielded mixed results depending on the input data. Additionally, domain-specific models—those trained on medical data—outperformed general models trained on broad, non-specialized datasets within their respective fields. Furthermore, when text is the dominant information source, text-only models surpassed multimodal models

Abstract
3D models are crucial in predicting aesthetic outcomes in breast reconstruction, supporting personalized surgical planning, and improving patient communication. In response to this necessity, this is the first application of Radiance Fields to 3D breast reconstruction. Building on this, the work compares six SoTA 3D reconstruction models. It introduces a novel variant tailored to medical contexts: Depth-Splatfacto, designed to improve denoising and geometric consistency through pseudo-depth supervision. Additionally, we extended model training to grayscale, which enhances robustness under grayscale-only input constraints. Experiments on a breast cancer patient dataset demonstrate that Splatfacto consistently outperforms others, delivering the highest reconstruction quality (PSNR 27.11, SSIM 0.942) and the fastest training times (×1.3 faster at 200k iterations). At the same time, the depth-enhanced variant offers an efficient and stable alternative with minimal fidelity loss. The grayscale train improves speed by ×1.6 with a PSNR drop of 0.70. Depth-Splatfacto further improves robustness, reducing PSNR variance by 10% and making images less blurry across test cases. These results establish a foundation for future clinical applications, supporting personalized surgical planning and improved patient-doctor communication. © 2025 Elsevier B.V., All rights reserved.