papers

Publications (14)

eess.IV2025

From Explainable to Explained AI: Ideas for Falsifying and Quantifying Explanations

Yoni Schirris, Eric Marcus, Jonas Teuwen +2

Explaining deep learning models is essential for clinical integration of medical image analysis systems. A good explanation highlights if a model depends on spurious features that…

cs.CV2025

TAP-CT: 3D Task-Agnostic Pretraining of Computed Tomography Foundation Models

Tim Veenboer, George Yiasemis, Eric Marcus +4

Existing foundation models (FMs) in the medical domain often require extensive fine-tuning or rely on training resource-intensive decoders, while many existing encoders are pretrai…

cs.LG2023

Constrained Empirical Risk Minimization: Theory and Practice

Eric Marcus, Ray Sheombarsing, Jan-Jakob Sonke +1

Deep Neural Networks (DNNs) are widely used for their ability to effectively approximate large classes of functions. This flexibility, however, makes the strict enforcement of cons…

cs.LG2025

Current Pathology Foundation Models are unrobust to Medical Center Differences

Edwin D. de Jong, Eric Marcus, Jonas Teuwen

Pathology Foundation Models (FMs) hold great promise for healthcare. Before they can be used in clinical practice, it is essential to ensure they are robust to variations between m…

eess.IV2024

Ordinal Learning: Longitudinal Attention Alignment Model for Predicting Time to Future Breast Cancer Events from Mammograms

Xin Wang, Tao Tan, Yuan Gao +9

Precision breast cancer (BC) risk assessment is crucial for developing individualized screening and prevention. Despite the promising potential of recent mammogram (MG) based deep…

cs.AI2024

Problems in AI, their roots in philosophy, and implications for science and society

Max Velthoven, Eric Marcus

Artificial Intelligence (AI) is one of today's most relevant emergent technologies. In view thereof, this paper proposes that more attention should be paid to the philosophical asp…

hep-ph2018

Charge-dependent Flow Induced by Magnetic and Electric Fields in Heavy Ion Collisions

Umut Gürsoy, Dmitri Kharzeev, Eric Marcus +2

We investigate the charge-dependent flow induced by magnetic and electric fields in heavy ion collisions. We simulate the evolution of the expanding cooling droplet of strongly cou…

cs.CV2023

Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms

Joren Brunekreef, Eric Marcus, Ray Sheombarsing +2

Image segmentation algorithms can be understood as a collection of pixel classifiers, for which the outcomes of nearby pixels are correlated. Classifier models can be calibrated us…

hep-th2020

Black holes in string theory with duality twists

Chris Hull, Eric Marcus, Koen Stemerdink +1

We consider 5D supersymmetric black holes in string theory compactifications that partially break supersymmetry. We compactify type IIB on and then further compactify on a ci…

eess.IV2024

Nodule detection and generation on chest X-rays: NODE21 Challenge

Ecem Sogancioglu, Bram van Ginneken, Finn Behrendt +16

Pulmonary nodules may be an early manifestation of lung cancer, the leading cause of cancer-related deaths among both men and women. Numerous studies have established that deep lea…

eess.IV2025

Foundation Models in Medical Imaging: A Review and Outlook

Vivien van Veldhuizen, Vanessa Botha, Chunyao Lu +10

Foundation models (FMs) are changing the way medical images are analyzed by learning from large collections of unlabeled data. Instead of relying on manually annotated examples, FM…

eess.IV2025

Towards Robust Foundation Models for Digital Pathology

Jonah Kömen, Edwin D. de Jong, Julius Hense +9

Biomedical Foundation Models (FMs) are rapidly transforming AI-enabled healthcare research and entering clinical validation. However, their susceptibility to learning non-biologica…

hep-th2020

The Near-Horizon Geometry of Supersymmetric Rotating AdS Black Holes in M-theory

Christopher Couzens, Eric Marcus, Koen Stemerdink +1

We classify the necessary and sufficient conditions to obtain the near-horizon geometry of extremal supersymmetric rotating black holes embedded in 11d supergravity. Such rotating…

hep-th2018

A new class of SYK-like models with maximal chaos

Eric Marcus, Stefan Vandoren

We investigate a model closely related to both the original Sachdev-Ye-Kitaev (SYK) model and the supersymmetric SYK model. It consists of real Majorana fermion…