papers

Publications (65)

cs.LG2026

On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings

David Restrepo, Miguel L Martins, Chenwei Wu +5

Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contri…

cs.CV2026

Mask-HybridGNet: Graph-based segmentation with emergent anatomical correspondence from pixel-level supervision

Nicolás Gaggion, Maria J. Ledesma-Carbayo, Stergios Christodoulidis +2

Graph-based medical image segmentation represents anatomical structures using boundary graphs, providing fixed-topology landmarks and inherent population-level correspondences. How…

cs.CV2026

Self-Supervised Temporal Regularization for Landmark-Based Cardiac Segmentation with Automatic AHA Regional Mapping

David Montalvo-García, Nicolás Gaggion, María J. Ledesma-Carbayo +1

Graph-based cardiac segmentation with implicit anatomical correspondences provides topological guarantees and population-level analysis capabilities, but models trained on independ…

cs.CV2016

Rigid Slice-To-Volume Medical Image Registration through Markov Random Fields

Roque Porchetto, Franco Stramana, Nikos Paragios +1

Rigid slice-to-volume registration is a challenging task, which finds application in medical imaging problems like image fusion for image guided surgeries and motion correction for…

stat.ML2018

Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease

Sarah Parisot, Sofia Ira Ktena, Enzo Ferrante +4

Graphs are widely used as a natural framework that captures interactions between individual elements represented as nodes in a graph. In medical applications, specifically, nodes c…

cs.CV2017

Deformable Registration through Learning of Context-Specific Metric Aggregation

Enzo Ferrante, Puneet K Dokania, Rafael Marini +1

We propose a novel weakly supervised discriminative algorithm for learning context specific registration metrics as a linear combination of conventional similarity measures. Conven…

cs.LG2021

Domain Generalization via Gradient Surgery

Lucas Mansilla, Rodrigo Echeveste, Diego H. Milone +1

In real-life applications, machine learning models often face scenarios where there is a change in data distribution between training and test domains. When the aim is to make pred…

cs.CV2024

On dataset transferability in medical image classification

Dovile Juodelyte, Enzo Ferrante, Yucheng Lu +3

Current transferability estimation methods designed for natural image datasets are often suboptimal in medical image classification. These methods primarily focus on estimating the…

cs.CV2025

Fairness and Robustness of CLIP-Based Models for Chest X-rays

Théo Sourget, David Restrepo, Céline Hudelot +3

Motivated by the strong performance of CLIP-based models in natural image-text domains, recent efforts have adapted these architectures to medical tasks, particularly in radiology,…

eess.IV2024

CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images

Nicolás Gaggion, Candelaria Mosquera, Lucas Mansilla +4

The development of successful artificial intelligence models for chest X-ray analysis relies on large, diverse datasets with high-quality annotations. While several databases of ch…

cs.CV2025

On the Risk of Misleading Reports: Diagnosing Textual Biases in Multimodal Clinical AI

David Restrepo, Ira Ktena, Maria Vakalopoulou +2

Clinical decision-making relies on the integrated analysis of medical images and the associated clinical reports. While Vision-Language Models (VLMs) can offer a unified framework…

cs.CV2020

Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoders

Agostina J Larrazabal, César Martínez, Ben Glocker +1

We introduce Post-DAE, a post-processing method based on denoising autoencoders (DAE) to improve the anatomical plausibility of arbitrary biomedical image segmentation algorithms.…

eess.IV2020

Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images

Julian Alberto Palladino, Diego Fernandez Slezak, Enzo Ferrante

Automatic segmentation of white matter hyperintensities in magnetic resonance images is of paramount clinical and research importance. Quantification of these lesions serve as a pr…

cs.CV2026

PVeRA: Probabilistic Vector-Based Random Matrix Adaptation

Leo Fillioux, Enzo Ferrante, Paul-Henry Cournède +2

Large foundation models have emerged in the last years and are pushing performance boundaries for a variety of tasks. Training or even finetuning such models demands vast datasets…

cs.CV2017

Slice-to-volume medical image registration: a survey

Enzo Ferrante, Nikos Paragios

During the last decades, the research community of medical imaging has witnessed continuous advances in image registration methods, which pushed the limits of the state-of-the-art…

cs.CV2017

Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation

Konstantinos Kamnitsas, Wenjia Bai, Enzo Ferrante +8

Deep learning approaches such as convolutional neural nets have consistently outperformed previous methods on challenging tasks such as dense, semantic segmentation. However, the v…

cs.CV2023

Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation

Agostina Larrazabal, Cesar Martinez, Jose Dolz +1

Modern deep neural networks achieved remarkable progress in medical image segmentation tasks. However, it has recently been observed that they tend to produce overconfident estimat…

cs.CV2016

Prior-based Coregistration and Cosegmentation

Mahsa Shakeri, Enzo Ferrante, Stavros Tsogkas +4

We propose a modular and scalable framework for dense coregistration and cosegmentation with two key characteristics: first, we substitute ground truth data with the semantic map o…

eess.IV2022

Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis

Nicolás Gaggion, Lucas Mansilla, Candelaria Mosquera +2

Anatomical segmentation is a fundamental task in medical image computing, generally tackled with fully convolutional neural networks which produce dense segmentation masks. These m…

cs.CV2018

Weakly-Supervised Learning of Metric Aggregations for Deformable Image Registration

Enzo Ferrante, Puneet K. Dokania, Rafael Marini Silva +1

Deformable registration has been one of the pillars of biomedical image computing. Conventional approaches refer to the definition of a similarity criterion that, once endowed with…

cs.CV2017

Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networks

Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante +4

Evaluating similarity between graphs is of major importance in several computer vision and pattern recognition problems, where graph representations are often used to model objects…

cs.CV2026

CheXmask-U: Quantifying uncertainty in landmark-based anatomical segmentation for X-ray images

Matias Cosarinsky, Nicolas Gaggion, Rodrigo Echeveste +1

In this work, we study uncertainty estimation for anatomical landmark-based segmentation on chest X-rays. Inspired by hybrid neural network architectures that combine standard imag…

eess.IV2019

Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders

Agostina J. Larrazabal, Cesar Martinez, Enzo Ferrante

Deep convolutional neural networks (CNN) proved to be highly accurate to perform anatomical segmentation of medical images. However, some of the most popular CNN architectures for…

eess.IV2020

Learning Deformable Registration of Medical Images with Anatomical Constraints

Lucas Mansilla, Diego H. Milone, Enzo Ferrante

Deformable image registration is a fundamental problem in the field of medical image analysis. During the last years, we have witnessed the advent of deep learning-based image regi…

cs.LG2025

BM-CL: Bias Mitigation through the lens of Continual Learning

Lucas Mansilla, Rodrigo Echeveste, Camila Gonzalez +2

Biases in machine learning pose significant challenges, particularly when models amplify disparities that affect disadvantaged groups. Traditional bias mitigation techniques often…

eess.IV2025

Towards Reliable WMH Segmentation under Domain Shift: An Application Study using Maximum Entropy Regularization to Improve Uncertainty Estimation

Franco Matzkin, Agostina Larrazabal, Diego H Milone +2

Accurate segmentation of white matter hyperintensities (WMH) is crucial for clinical decision-making, particularly in the context of multiple sclerosis. However, domain shifts, suc…

cs.CY2026

Implicit Bias in LLMs for Transgender Populations

Micaela Hirsch, Marina Elichiry, Blas Radi +6

Large language models (LLMs) have been shown to exhibit biases against LGBTQ+ populations. While safety training may lessen explicit expressions of bias, previous work has shown th…

cs.LG2026

Inference-Time Toxicity Mitigation in Protein Language Models

Manuel Fernández Burda, Santiago Aranguri, Iván Arcuschin Moreno +1

Protein language models (PLMs) are becoming practical tools for de novo protein design, yet their dual-use potential raises safety concerns. We show that domain adaptation to speci…

cs.CY2024

FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

Karim Lekadir, Aasa Feragen, Abdul Joseph Fofanah +117

Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. I…

eess.IV2023

Towards unraveling calibration biases in medical image analysis

María Agustina Ricci Lara, Candelaria Mosquera, Enzo Ferrante +1

In recent years the development of artificial intelligence (AI) systems for automated medical image analysis has gained enormous momentum. At the same time, a large body of work ha…

cs.CV2019

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

Spyridon Bakas, Mauricio Reyes, Andras Jakab +421

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritum…

cs.LG2024

Are demographically invariant models and representations in medical imaging fair?

Eike Petersen, Enzo Ferrante, Melanie Ganz +1

Medical imaging models have been shown to encode information about patient demographics such as age, race, and sex in their latent representation, raising concerns about their pote…

cs.CV2025

In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review

Amelia Jiménez-Sánchez, Natalia-Rozalia Avlona, Sarah de Boer +26

Datasets play a critical role in medical imaging research, yet issues such as label quality, shortcuts, and metadata are often overlooked. This lack of attention may harm the gener…

eess.IV2025

Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI

Nicolás Gaggion, Benjamin A. Matheson, Yan Xia +6

Cardiovascular magnetic resonance imaging is emerging as a crucial tool to examine cardiac morphology and function. Essential to this endeavour are anatomical 3D surface and volume…

cs.CV2024

Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging

Dovile Juodelyte, Yucheng Lu, Amelia Jiménez-Sánchez +3

Transfer learning has become an essential part of medical imaging classification algorithms, often leveraging ImageNet weights. The domain shift from natural to medical images has…

cs.LG2026

Remedying uncertainty representations in visual inference through Explaining-Away Variational Autoencoders

Josefina Catoni, Domonkos Martos, Ferenc Csikor +5

Optimal computations under uncertainty require an adequate probabilistic representation about beliefs. Deep generative models, and specifically Variational Autoencoders (VAEs), hav…

cs.LG2025

Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation

Estanislao Claucich, Sara Hooker, Diego H. Milone +2

Ensembling is commonly regarded as an effective way to improve the general performance of models in machine learning, while also increasing the robustness of predictions. When it c…

eess.IV2024

Deep vessel segmentation with joint multi-prior encoding

Amine Sadikine, Bogdan Badic, Enzo Ferrante +4

The precise delineation of blood vessels in medical images is critical for many clinical applications, including pathology detection and surgical planning. However, fully-automated…

cs.CV2022

Impact of class imbalance on chest x-ray classifiers: towards better evaluation practices for discrimination and calibration performance

Candelaria Mosquera, Luciana Ferrer, Diego Milone +2

This work aims to analyze standard evaluation practices adopted by the research community when assessing chest x-ray classifiers, particularly focusing on the impact of class imbal…

cs.CV2024

Fitting Skeletal Models via Graph-based Learning

Nicolás Gaggion, Enzo Ferrante, Beatriz Paniagua +1

Skeletonization is a popular shape analysis technique that models an object's interior as opposed to just its boundary. Fitting template-based skeletal models is a time-consuming p…

cs.CV2026

ChronoRoot 2.0: An Open AI-Powered Platform for 2D Temporal Plant Phenotyping

Nicolás Gaggion, Noelia A. Boccardo, Rodrigo Bonazzola +17

Plant developmental plasticity, particularly in root system architecture, is fundamental to understanding adaptability and agricultural sustainability. ChronoRoot 2.0 builds upon e…

cs.CV2023

Unsupervised bias discovery in medical image segmentation

Nicolás Gaggion, Rodrigo Echeveste, Lucas Mansilla +2

It has recently been shown that deep learning models for anatomical segmentation in medical images can exhibit biases against certain sub-populations defined in terms of protected…

cs.CV2019

Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets

Nicolas Roulet, Diego Fernandez Slezak, Enzo Ferrante

Brain lesion and anatomy segmentation in magnetic resonance images are fundamental tasks in neuroimaging research and clinical practice. Given enough training data, convolutional n…

eess.IV2025

Predicting risk of cardiovascular disease using retinal OCT imaging

Cynthia Maldonado-Garcia, Rodrigo Bonazzola, Enzo Ferrante +4

Cardiovascular diseases (CVD) are the leading cause of death globally. Non-invasive, cost-effective imaging techniques play a crucial role in early detection and prevention of CVD.…

q-bio.NC2021

Bridging physiological and perceptual views of autism by means of sampling-based Bayesian inference

Rodrigo Echeveste, Enzo Ferrante, Diego H. Milone +1

Theories for autism spectrum disorder (ASD) have been formulated at different levels: ranging from physiological observations to perceptual and behavioral descriptions. Understandi…

eess.IV2020

Cranial Implant Design via Virtual Craniectomy with Shape Priors

Franco Matzkin, Virginia Newcombe, Ben Glocker +1

Cranial implant design is a challenging task, whose accuracy is crucial in the context of cranioplasty procedures. This task is usually performed manually by experts using computer…

eess.IV2025

Performance Estimation for Supervised Medical Image Segmentation Models on Unlabeled Data Using UniverSeg

Jingchen Zou, Jianqiang Li, Gabriel Jimenez +5

The performance of medical image segmentation models is usually evaluated using metrics like the Dice score and Hausdorff distance, which compare predicted masks to ground truth an…

cs.CL2025

Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation

Israfel Salazar, Manuel Fernández Burda, Shayekh Bin Islam +42

The evaluation of vision-language models (VLMs) has mainly relied on English-language benchmarks, leaving significant gaps in both multilingual and multicultural coverage. While mu…

cs.CV2025

ViG-Bias: Visually Grounded Bias Discovery and Mitigation

Badr-Eddine Marani, Mohamed Hanini, Nihitha Malayarukil +3

The proliferation of machine learning models in critical decision making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons be…

cs.CV2024

Open Challenges on Fairness of Artificial Intelligence in Medical Imaging Applications

Enzo Ferrante, Rodrigo Echeveste

Recently, the research community of computerized medical imaging has started to discuss and address potential fairness issues that may emerge when developing and deploying AI syste…

eess.IV2021

Hybrid graph convolutional neural networks for landmark-based anatomical segmentation

Nicolás Gaggion, Lucas Mansilla, Diego Milone +1

In this work we address the problem of landmark-based segmentation for anatomical structures. We propose HybridGNet, an encoder-decoder neural architecture which combines standard…

cs.CV2017

Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation

Ozan Oktay, Enzo Ferrante, Konstantinos Kamnitsas +10

Incorporation of prior knowledge about organ shape and location is key to improve performance of image analysis approaches. In particular, priors can be useful in cases where image…

cs.CV2026

ConfIC-RCA: Statistically Grounded Efficient Estimation of Segmentation Quality

Matias Cosarinsky, Ramiro Billot, Lucas Mansilla +5

Assessing the quality of automatic image segmentation is crucial in clinical practice, but often very challenging due to the limited availability of ground truth annotations. Rever…

cs.CV2026

Medical Context Distorts Decisions in Clinical Vision Language Models

David Restrepo, Ira Ktena, Maria Vakalopoulou +2

Vision-language models (VLMs) are increasingly proposed for clinical decision support, yet their reliability in real-world scenarios that require integrating both visual and textua…

stat.ML2017

Spectral Graph Convolutions for Population-based Disease Prediction

Sarah Parisot, Sofia Ira Ktena, Enzo Ferrante +4

Exploiting the wealth of imaging and non-imaging information for disease prediction tasks requires models capable of representing, at the same time, individual features as well as…

q-bio.GN2023

Unsupervised ensemble-based phenotyping helps enhance the discoverability of genes related to heart morphology

Rodrigo Bonazzola, Enzo Ferrante, Nishant Ravikumar +5

Recent genome-wide association studies (GWAS) have been successful in identifying associations between genetic variants and simple cardiac parameters derived from cardiac magnetic…

cs.CL2025

Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation

Shivalika Singh, Angelika Romanou, Clémentine Fourrier +21

Cultural biases in multilingual datasets pose significant challenges for their effectiveness as global benchmarks. These biases stem not only from differences in language but also…

eess.IV2020

Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy

Franco Matzkin, Virginia Newcombe, Susan Stevenson +6

Decompressive craniectomy (DC) is a common surgical procedure consisting of the removal of a portion of the skull that is performed after incidents such as stroke, traumatic brain…

cs.CV2016

Sub-cortical brain structure segmentation using F-CNN's

Mahsa Shakeri, Stavros Tsogkas, Enzo Ferrante +4

In this paper we propose a deep learning approach for segmenting sub-cortical structures of the human brain in Magnetic Resonance (MR) image data. We draw inspiration from a state-…

cs.CL2024

SignAttention: On the Interpretability of Transformer Models for Sign Language Translation

Pedro Alejandro Dal Bianco, Oscar Agustín Stanchi, Facundo Manuel Quiroga +2

This paper presents the first comprehensive interpretability analysis of a Transformer-based Sign Language Translation (SLT) model, focusing on the translation from video-based Gre…

eess.IV2024

Supervision by Denoising for Medical Image Segmentation

Sean I. Young, Adrian V. Dalca, Enzo Ferrante +4

Learning-based image reconstruction models, such as those based on the U-Net, require a large set of labeled images if good generalization is to be guaranteed. In some imaging doma…

eess.IV2022

Multi-center anatomical segmentation with heterogeneous labels via landmark-based models

Nicolás Gaggion, Maria Vakalopoulou, Diego H. Milone +1

Learning anatomical segmentation from heterogeneous labels in multi-center datasets is a common situation encountered in clinical scenarios, where certain anatomical structures are…

eess.IV2021

Orthogonal Ensemble Networks for Biomedical Image Segmentation

Agostina J. Larrazabal, César Martínez, Jose Dolz +1

Despite the astonishing performance of deep-learning based approaches for visual tasks such as semantic segmentation, they are known to produce miscalibrated predictions, which cou…

cs.CV2018

Left ventricle quantification through spatio-temporal CNNs

Alejandro Debus, Enzo Ferrante

Cardiovascular diseases are among the leading causes of death globally. Cardiac left ventricle (LV) quantification is known to be one of the most important tasks for the identifica…

cs.CV2017

Arabidopsis roots segmentation based on morphological operations and CRFs

José Ignacio Orlando, Hugo Luis Manterola, Enzo Ferrante +1

Arabidopsis thaliana is a plant species widely utilized by scientists to estimate the impact of genetic differences in root morphological features. For this purpose, images of this…