Abstract

Abstract
Prognosis after intracranial hemorrhage (ICH) is influenced by a complex interplay between imaging and tabular data. Rapid and reliable prognosis are crucial for effective patient stratification and informed treatment decision-making. In this study, we aim to enhance image-based prognosis by learning a robust feature representation shared between prognosis and the clinical and demographic variables most highly correlated with it. Our approach mimics clinical decision-making by reinforcing the model to learn valuable prognostic data embedded in the image. We propose a 3D multi-task image model to predict prognosis, Glasgow Coma Scale and age, improving accuracy and interpretability. Our method outperforms current state-of-the-art baseline image models, and demonstrates superior performance in ICH prognosis compared to four board-certified neuroradiologists using only CT scans as input. We further validate our model with interpretability saliency maps. Code is available at https://github.com/MiriamCobo/MultitaskLearning_ICH_Prognosis.git.

Abstract
The development of deep learning algorithms has extensively empowered humanity's task automatization capacity. However, the huge improvement in the performance of these models is highly correlated with their increasing level of complexity, limiting their usefulness in human-oriented applications, which are usually deployed in resource-constrained devices. This led to the development of compression techniques that drastically reduce the computational and memory costs of deep learning models without significant performance degradation. These compressed models are especially essential when implementing multi-model fusion solutions where multiple models are required to operate simultaneously. This paper aims to systematize the current literature on this topic by presenting a comprehensive survey of model compression techniques in biometrics applications, namely quantization, knowledge distillation and pruning. We conduct a critical analysis of the comparative value of these techniques, focusing on their advantages and disadvantages and presenting suggestions for future work directions that can potentially improve the current methods. Additionally, we discuss and analyze the link between model bias and model compression, highlighting the need to direct compression research toward model fairness in future works.

Abstract
[No abstract available]

Abstract
Lung cancer remains one of the most common and lethal forms of cancer, with approximately 1.8 million deaths annually, often diagnosed at advanced stages. Early detection is crucial, but it depends on physicians’ accurate interpretation of computed tomography (CT) scans, a process susceptible to human limitations and variability. ByMe has developed a medical image annotation and anonymization tool designed to address these challenges through a human-centered approach. The tool enables physicians to seamlessly add structured attribute-based annotations (e.g., size, location, morphology) directly within their established workflows, ensuring intuitive interaction.Integrated with Picture Archiving and Communication Systems (PACS), the tool streamlines the annotation process and enhances usability by offering a dedicated worklist for retrospective and prospective case analysis. Robust anonymization features ensure compliance with privacy regulations such as the General Data Protection Regulation (GDPR), enabling secure dataset sharing for research and developing artificial intelligence (AI) models. Designed to empower AI integration, the tool not only facilitates the creation of high-quality datasets but also lays the foundation for incorporating AI-driven insights directly into clinical workflows. Focusing on usability, workflow integration, and privacy, this innovation bridges the gap between precision medicine and advanced technology. By providing the means to develop and train AI models for lung cancer detection, it holds the potential to significantly accelerate diagnosis as well as enhance its accuracy and consistency.

Abstract
Deep Inferior Epigastric Perforator (DIEP) flap breast reconstruction relies on the precise identification of perforator vessels supplying blood to transferred tissue. Traditional manual mapping from preoperative imaging is time-consuming and subjective. To address this, AVA, a semi-automated perforator detection algorithm, was developed to analyze angiography images. AVA follows a three-step process: automated anatomical segmentation, manual annotation of perforators, and segmentation of perforator courses. This approach enhances accuracy, reduces subjectivity, and accelerates the mapping process while generating quantitative reports for surgical planning. To streamline integration into clinical workflows, AVA has been embedded into PACScenter, a medical imaging platform, leveraging DICOM encapsulation for seamless data exchange within a Vendor Neutral Archive (VNA). This integration allows surgeons to interactively annotate perforators, adjust parameters iteratively, and visualize detailed anatomical structures. AVA-PACScenter integration eliminates workflow disruptions by providing real-time perforator analysis within the surgical environment, ultimately improving preoperative planning and intraoperative guidance. Currently undergoing clinical feasibility testing, this integration aims to enhance DIEP flap reconstruction efficiency by reducing manual inputs, improving mapping precision, and facilitating long-term report storage within Dicoogle. By automating perforator analysis, AVA represents a significant advancement toward data-driven, patient-centered surgical planning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.