Abstract
Deep learning techniques have demonstrated significant potential in computer-assisted diagnosis based on medical imaging. However, their integration into clinical workflows remains limited, largely due to concerns about interpretability. To address this challenge, we propose Efficient-Proto-Caps, a lightweight and inherently interpretable model that combines capsule networks with prototype learning for lung nodule characterization. Additionally, an innovative Davies-Bouldin Index with multiple centroids per cluster is employed as a loss function to promote clustering of lung nodule visual attribute representations. When evaluated on the LIDC-IDRI dataset, the most widely recognized benchmark for lung cancer prediction, our model achieved an overall accuracy of 89.7 % in predicting lung nodule malignancy and associated visual attributes. This performance is statistically comparable to that of the baseline model, while utilizing a backbone with only approximately 2 % of the parameters of the baseline model’s backbone. State-of-the-art models achieved better performance in lung nodule malignancy prediction; however, our approach relies on multiclass malignancy predictions and provides a decision rationale aligned with globally accepted clinical guidelines. These results underscore the potential of our approach, as the integration of lightweight and less complex designs into accurate and inherently interpretable models represents a significant advancement toward more transparent and clinically viable computer-assisted diagnostic systems. Furthermore, these findings highlight the model’s potential for broader applicability, extending beyond medicine to other domains where final classifications are grounded in concept-based or example-based attributes. © 2013 IEEE.

Abstract
Due to the high variability in Hematoxylin and Eosin (H&E)-stained Whole Slide Images (WSIs), hidden stratification, and batch effects, generalizing beyond the training distribution is one of the main challenges in Deep Learning (DL) for Computational Pathology (CPath). But although DL depends on large volumes of diverse and annotated data, it is common to have a significant number of annotated samples from one or multiple source distributions, and another partially annotated or unlabeled dataset representing a target distribution for which we want to generalize, the so-called Domain Adaptation (DA). In this work, we focus on the task of generalizing from a single source distribution to a target domain. As it is still not clear which domain adaptation strategy is best suited for CPath, we evaluate three different DA strategies, namely FixMatch, CycleGAN, and a self-supervised feature extractor, and show that DA is still a challenge in CPath.

Abstract
Objective.The detection of arterial pulsating signals at the skin periphery with Photoplethysmography (PPG) are easily distorted by motion artifacts. This work explores the alternatives to the aid of PPG reconstruction with movement sensors (accelerometer and/or gyroscope) which to date have demonstrated the best pulsating signal reconstruction. Approach. A generative adversarial network with fully connected layers is proposed for the reconstruction of distorted PPG signals. Artificial corruption was performed to the clean selected signals from the BIDMC Heart Rate dataset, processed from the larger MIMIC II waveform database to create the training, validation and testing sets. Main results. The heart rate (HR) of this dataset was further extracted to evaluate the performance of the model obtaining a mean absolute error of 1.31 bpm comparing the HR of the target and reconstructed PPG signals with HR between 70 and 115 bpm. Significance. The model architecture is effective at reconstructing noisy PPG signals regardless the length and amplitude of the corruption introduced. The performance over a range of HR (70-115 bpm), indicates a promising approach for real-time PPG signal reconstruction without the aid of acceleration or angular velocity inputs.

Abstract
Segmentation of lung nodules in CT images is an important step during the clinical evaluation of patients with lung cancer. Furthermore, early assessment of the cancer is crucial to increase the overall survival chances of patients with such disease, and the segmentation of lung nodules can help detect the cancer in its early stages. Consequently, there are many works in the literature that explore the use of neural networks for the segmentation of lung nodules. However, these frameworks tend to rely on accurate labelling of the nodule centre to then crop the input image. Although such works are able to achieve remarkable results, they do not take into account that the healthcare professional may fail to correctly label the centre of the nodule. Therefore, in this work, we propose a new framework based on the U-Net model that allows to correct such inaccuracies in an interactive fashion. It is composed of two U-Net models in cascade, where the first model is used to predict a rough estimation of the lung nodule location and the second model refines the generated segmentation mask. Our results show that the proposed framework is able to be more robust than the studied baselines. Furthermore, it is able to achieve state-of-the-art performance, reaching a Dice of 91.12% when trained and tested on the LIDC-IDRI public dataset.

Abstract

Abstract
AbstractMicroorganisms evolved adaptive responses that enable them to survive stressful challenges in ever changing environments by adjusting metabolism through the modulation of gene expression, protein levels and activity, and flow of metabolites. More frequent challenges allow natural selection ampler opportunities to select from a larger number of phenotypes that are compatible with survival. Understanding the causal relationships between physiological and metabolic requirements that are needed for cellular stress adaptation and gene expression changes that are used by organisms to achieve those requirements may have a significant impact in our ability to interpret and/or guide evolution.Here, we study those causal relationships during heat shock adaptation in the yeastSaccharomyces cerevisiae. We do so by combining dozens of independent experiments measuring whole genome gene expression changes during stress response with a nonlinear simplified kinetic model of central metabolism.This combination is used to create a quantitative, multidimensional, genotype-to-phenotype mapping of the metabolic and physiological requirements that enable cell survival to the feasible changes in gene expression that modulate metabolism to achieve those requirements. Our results clearly show that the feasible changes in gene expression that enable survival to heat shock are specific for this stress. In addition, they suggest that genetic programs for adaptive responses to desiccation/rehydration and to pH shifts might be selected by physiological requirements that are qualitatively similar, but quantitatively different to those for heat shock adaptation. In contrast, adaptive responses to other types of stress do not appear to be constrained by the same qualitative physiological requirements. Our model also explains at the mechanistic level how evolution might find different sets of changes in gene expression that lead to metabolic adaptations that are equivalent in meeting physiological requirements for survival. Finally, our results also suggest that physiological requirements for heat shock adaptation might be similar between unicellular ascomycetes that live in similar environments. Our analysis is likely to be scalable to other adaptive response and might inform efforts in developing biotechnological applications to manipulate cells for medical, biotechnological, or synthetic biology purposes.