activity
20212024
most citedUnsupervised Pathology Detection: A Deep Dive Into the State of the Art

30 citations · 90 across the 14 of their papers we have counts for

collaborators

15 papers

cs.CL2024★ 1 cited

Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings

Andrea Posada, Daniel Rueckert, Felix Meissen +1

Since the Transformer architecture emerged, language model development has grown, driven by their promising potential. Releasing these models into production requires properly unde…

cs.CV2024★ 6 cited

Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI Pooling

Philip Müller, Felix Meissen, Georgios Kaissis +1

Weakly supervised object detection (WSup-OD) increases the usefulness and interpretability of image classification algorithms without requiring additional supervision. The successe…

cs.CV2023

How Low Can You Go? Surfacing Prototypical In-Distribution Samples for Unsupervised Anomaly Detection

Felix Meissen, Johannes Getzner, Alexander Ziller +4

Unsupervised anomaly detection (UAD) alleviates large labeling efforts by training exclusively on unlabeled in-distribution data and detecting outliers as anomalies. Generally, the…

cs.LG2023

(Predictable) Performance Bias in Unsupervised Anomaly Detection

Felix Meissen, Svenja Breuer, Moritz Knolle +5

Background: With the ever-increasing amount of medical imaging data, the demand for algorithms to assist clinicians has amplified. Unsupervised anomaly detection (UAD) models promi…

cs.CV2023★ 1 cited

Anatomy-Driven Pathology Detection on Chest X-rays

Philip Müller, Felix Meissen, Johannes Brandt +2

Pathology detection and delineation enables the automatic interpretation of medical scans such as chest X-rays while providing a high level of explainability to support radiologist…

eess.IV2023★ 12 cited

The Brain Tumor Segmentation (BraTS) Challenge 2023: Brain MR Image Synthesis for Tumor Segmentation (BraSyn)

Hongwei Bran Li, Gian Marco Conte, Qingqiao Hu +62

Automated brain tumor segmentation methods have become well-established and reached performance levels offering clear clinical utility. These methods typically rely on four input m…