13 citations · 22 across the 8 of their papers we have counts for
5 papers · 1 filter
Abnormality-Driven Representation Learning for Radiology Imaging
Marta Ligero, Tim Lenz, Georg Wölflein +3
To date, the most common approach for radiology deep learning pipelines is the use of end-to-end 3D networks based on models pre-trained on other tasks, followed by fine-tuning on…
Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning
Tim Lenz, Peter Neidlinger, Marta Ligero +3
Representation learning of pathology whole-slide images (WSIs) has primarily relied on weak supervision with Multiple Instance Learning (MIL). This approach leads to slide represen…
Benchmarking foundation models as feature extractors for weakly-supervised computational pathology
Peter Neidlinger, Omar S. M. El Nahhas, Hannah Sophie Muti +13
Advancements in artificial intelligence have driven the development of numerous pathology foundation models capable of extracting clinically relevant information. However, there is…
Reducing self-supervised learning complexity improves weakly-supervised classification performance in computational pathology
Tim Lenz, Omar S. M. El Nahhas, Marta Ligero +1
Deep Learning models have been successfully utilized to extract clinically actionable insights from routinely available histology data. Generally, these models require annotations…
Joint multi-task learning improves weakly-supervised biomarker prediction in computational pathology
Omar S. M. El Nahhas, Georg Wölflein, Marta Ligero +5
Deep Learning (DL) can predict biomarkers directly from digitized cancer histology in a weakly-supervised setting. Recently, the prediction of continuous biomarkers through regress…