arXiv subjects

Gonzalo R. Ríos-Muñoz

Publications and source records attributed to Gonzalo R. Ríos-Muñoz.

4 recordsLinked to original sources

arXiv2025

Multimodal Posterior Sampling-based Uncertainty in PD-L1 Segmentation from H&E Images

Accurate assessment of PD-L1 expression is critical for guiding immunotherapy, yet current immunohistochemistry (IHC) based methods are resource-intensive. We present nnUNet-B: a Bayesian segmentation framework that infers PD-L1 expression directly from H&E-stained histology images using Multimodal Posterior Sampling (MPS). Built upon nnUNet-v2, our method samples diverse model checkpoints during cyclic training to approximate the posterior, enabling both accurate segmentation and epistemic uncertainty estimation via entropy and standard deviation. Evaluated on a dataset of lung squamous cell carcinoma, our approach achieves competitive performance against established baselines with mean Dice Score and mean IoU of 0.805 and 0.709, respectively, while providing pixel-wise uncertainty maps. Uncertainty estimates show strong correlation with segmentation error, though calibration remains imperfect. These results suggest that uncertainty-aware H&E-based PD-L1 prediction is a promising step toward scalable, interpretable biomarker assessment in clinical workflows.

cs.CV↗

arXiv2025

CLARAE: Clarity Preserving Reconstruction AutoEncoder for Denoising and Rhythm Classification of Intracardiac Electrograms

Intracavitary atrial electrograms (EGMs) provide high-resolution insights into cardiac electrophysiology but are often contaminated by noise and remain high-dimensional, limiting real-time analysis. We introduce CLARAE (CLArity-preserving Reconstruction AutoEncoder), a one-dimensional encoder--decoder designed for atrial EGMs, which achieves both high-fidelity reconstruction and a compact 64-dimensional latent representation. CLARAE is designed to preserve waveform morphology, mitigate reconstruction artifacts, and produce interpretable embeddings through three principles: downsampling with pooling, a hybrid interpolation--convolution upsampling path, and a bounded latent space. We evaluated CLARAE on 495,731 EGM segments (unipolar and bipolar) from 29 patients across three rhythm types (AF, SR300, SR600). Performance was benchmarked against six state-of-the-art autoencoders using reconstruction metrics, rhythm classification, and robustness across signal-to-noise ratios from -5 to 15 dB. In downstream rhythm classification, CLARAE achieved F1-scores above 0.97 for all rhythm types, and its latent space showed clear clustering by rhythm. In denoising tasks, it consistently ranked among the top performers for both unipolar and bipolar signals. In order to promote reproducibility and enhance accessibility, we offer an interactive web-based application. This platform enables users to explore pre-trained CLARAE models, visualize the reconstructions, and compute metrics in real time. Overall, CLARAE combines robust denoising with compact, discriminative representations, offering a practical foundation for clinical workflows such as rhythm discrimination, signal quality assessment, and real-time mapping.

eess.SP↗

arXiv2025

The impact of gamification on learning outcomes: experiences from a Biomedical Engineering course

This study examines the integration of digital tools in project-based learning within a Biomedical Engineering course to enhance collaboration, transparency, and assessment fairness. Building on prior pilot experiences, we implemented a structured learning environment that combined experiment tracking, real-time collaboration, and peer-assessment practices. The intervention was deployed across two consecutive academic years, involving master's-level students in Biomedical Image Processing. Data were collected through project outcomes, peer-assessment rubrics, and student surveys. Results show that the integration of digital platforms supported accountability, improved the quality of collaborative work, and fostered greater equity in the evaluation process. Students highlighted increased engagement, enhanced teamwork, and clearer criteria for performance assessment. Faculty reported more efficient monitoring of progress and improved feedback practices. Despite challenges such as technical adoption and the need for instructor guidance, the study demonstrates the potential of structured tool integration to support active and transparent learning environments. Findings contribute to the broader discourse on digital pedagogy, offering a replicable model for higher education contexts in science and technology.

cs.CY↗

arXiv2025

Latent Representations of Intracardiac Electrograms for Atrial Fibrillation Driver Detection

Atrial Fibrillation (AF) is the most prevalent sustained arrhythmia, yet current ablation therapies, including pulmonary vein isolation, are frequently ineffective in persistent AF due to the involvement of non-pulmonary vein drivers. This study proposes a deep learning framework using convolutional autoencoders for unsupervised feature extraction from unipolar and bipolar intracavitary electrograms (EGMs) recorded during AF in ablation studies. These latent representations of atrial electrical activity enable the characterization and automation of EGM analysis, facilitating the detection of AF drivers. The database consisted of 11,404 acquisitions recorded from 291 patients, containing 228,080 unipolar EGMs and 171,060 bipolar EGMs. The autoencoders successfully learned latent representations with low reconstruction loss, preserving the morphological features. The extracted embeddings allowed downstream classifiers to detect rotational and focal activity with moderate performance (AUC 0.73-0.76) and achieved high discriminative performance in identifying atrial EGM entanglement (AUC 0.93). The proposed method can operate in real-time and enables integration into clinical electroanatomical mapping systems to assist in identifying arrhythmogenic regions during ablation procedures. This work highlights the potential of unsupervised learning to uncover physiologically meaningful features from intracardiac signals.

cs.LG↗