The medical data science group carries out research at the intersection of machine learning and medicine with the ultimate goal of improving diagnosis and treatment outcome to the benefit of the care and wellbeing of patients. As medical and health data is heterogenous and multimodal, our research deals with the advancement of machine learning models and methodologies to address the specific challenges of the medical domain. Specifically, we work in the areas of multimodal data integration, structure detection, and trustworthy (or transparent) models. The challenge lies not only in developing fast, robust and reliable systems but also in systems that are easy to interpret and usable in clinical practice.
New Timeline Documents 30+ Years of Promoting Women in Computer Science at D-INFK
The Department of Computer Science (D-INFK) at ETH Zurich has published a new historical timeline documenting the development of its women’s promotion…
Dr Ece Özkan Elsen appointed as BRCCH Professor of Paediatric Digital Health Data Analysis
We are excited to announce that Dr. Ece Ozkan Elsen, currently an Established Researcher in our group, will be transitioning to her new role as…
MDS at NeurIPS 2024
Several members of the MDS group attended NeurIPS 2024. Congratulations to everyone who presented work at the main conference and workshops!
General movements (GMs) are spontaneous, coordinated body movements in infants that offer valuable insights into the developing nervous system. Assessed through the Prechtl GM Assessment (GMA), GMs are reliable predictors for neurodevelopmental disorders. However, GMA requires specifically trained clinicians, who are limited in number. To scale up newborn screening, there is a need for an algorithm that can automatically classify GMs from infant video recordings. This data poses challenges, including variability in recording length, device type, and setting, with each video coarsely annotated for overall movement quality. In this work, we introduce a tool for extracting features from these recordings and explore various machine learning techniques for automated GM classification.
AuthorsDaphne Chopard*, Sonia Laguna*, Kieran Chin-Cheong*, Annika Dietz, Anna Badura, Sven Wellmann, Julia E Vogt* denotes shared first authorship
SubmittedProceedings of Machine Learning Research - Machine Learning for Healthcare 2025, previous version in ICLR 2025 (Best Paper Award - Oral) Workshop AI4CHL
Date15.08.2025
Building generalizable medical AI systems requires pretraining strategies that are data-efficient and domain-aware. Unlike internet-scale corpora, clinical datasets such as MIMIC-CXR offer limited image counts and scarce annotations, but exhibit rich internal structure through multi-view imaging. We propose a self-supervised framework that leverages the inherent structure of medical datasets. Specifically, we treat paired chest X-rays (i.e., frontal and lateral views) as natural positive pairs, learning to reconstruct each view from sparse patches while aligning their latent embeddings. Our method requires no textual supervision and produces informative representations. Evaluated on MIMIC-CXR, we show strong performance compared to supervised objectives and baselines being trained without leveraging structure. This work provides a lightweight, modality-agnostic blueprint for domain-specific pretraining where data is structured but scarce.
AuthorsAndrea Agostini*, Sonia Laguna*, Alain Ryser*, Samuel Ruiperez-Campillo*, Moritz Vandenhirtz, Nicolas Deperrois, Farhad Nooralahzadeh, Michael Krauthammer, Thomas M Sutter†, Julia E Vogt†* denotes shared first authorship, † denotes shared last authorship
SubmittedInternational Conference of Machine Learning (ICML) 2025 Workshop on FM4LS
Date15.07.2025
We introduce Concept Bottleneck Reward Models (CB-RM), a reward modeling framework that enables interpretable preference learning through selective concept annotation. Unlike standard RLHF methods that rely on opaque reward functions, CB-RM decomposes reward prediction into human-interpretable concepts. To make this framework efficient in low-supervision settings, we formalize an active learning strategy that dynamically acquires the most informative concept labels. We propose an acquisition function based on Expected Information Gain and show that it significantly accelerates concept learning without compromising preference accuracy. Evaluated on the UltraFeedback dataset, our method outperforms baselines in interpretability and sample efficiency, marking a step towards more transparent, auditable, and human-aligned reward models.
AuthorsSonia Laguna, Katarzyna Kobalczyk, Julia E Vogt, Mihaela Van der Schaar
SubmittedInternational Conference on Machine Learning (ICML) 2025 Workshop on PRAL
Date12.07.2025
Purpose Speed-of-sound (SoS) is a biomechanical characteristic of tissue, and its imaging can provide a promising biomarker for diagnosis. Reconstructing SoS images from ultrasound acquisitions can be cast as a limited-angle computed-tomography problem, with variational networks being a promising model-based deep learning solution. Some acquired data frames may, however, get corrupted by noise due to, e.g., motion, lack of contact, and acoustic shadows, which in turn negatively affects the resulting SoS reconstructions. Methods We propose to use the uncertainty in SoS reconstructions to attribute trust to each individual acquired frame. Given multiple acquisitions, we then use an uncertainty-based automatic selection among these retrospectively, to improve diagnostic decisions. We investigate uncertainty estimation based on Monte Carlo Dropout and Bayesian Variational Inference. Results We assess our automatic frame selection method for differential diagnosis of breast cancer, distinguishing between benign fibroadenoma and malignant carcinoma. We evaluate 21 lesions classified as BI-RADS 4, which represents suspicious cases for probable malignancy. The most trustworthy frame among four acquisitions of each lesion was identified using uncertainty-based criteria. Selecting a frame informed by uncertainty achieved an area under curve of 76% and 80% for Monte Carlo Dropout and Bayesian Variational Inference, respectively, superior to any uncertainty-uninformed baselines with the best one achieving 64%. Conclusion A novel use of uncertainty estimation is proposed for selecting one of multiple data acquisitions for further processing and decision making.
AuthorsSonia Laguna, Lin Zhang, Can Deniz Bezek, Monika Farkas, Dieter Schweizer, Rahel A. Kubik-Huch, Orcun Goksel
SubmittedInternational Journal of Computer Assisted Radiology and Surgery
Date10.06.2025
Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenarios. To address data scarcity, we propose an end-to-end system for synthetic data generation for scalable, high-quality, and customizable 3D indoor scenes. By integrating and adapting text-to-image and multi-view diffusion models with Neural Radiance Field-based meshing, this system generates highfidelity 3D object assets from text prompts and incorporates them into pre-defined floor plans using a rendering tool. By introducing novel loss functions and training strategies into existing methods, the system supports on-demand scene generation, aiming to alleviate the scarcity of current available data, generally manually crafted by artists. This system advances the role of synthetic data in addressing machine learning training limitations, enabling more robust and generalizable models for real-world applications.
AuthorsSonia Laguna, Alberto Garcia-Garcia, Marie-Julie Rakotosaona, Stylianos Moschoglou, Leonhard Helminger, Sergio Orts-Escolano
SubmittedInternational Conference on Learning Representations (ICLR) 2025 Workshop SynthData
Date17.04.2025