Keno Bressem

Llama3-70B performs on par with GPT-4-Turbo on answering USMLE questions

The United States Medical Licensing Examination (USMLE) is a rigorous, multi-step assessment that all medical students…
Prostate158: Data and AI Models for Prostate Cancer Segmentation

We released Prostate158, a large, publicly available dataset of 158 expert-annotated biparametric 3T prostate MRIs. This…
Deep Learning for Automated Detection of Sacroiliitis on Biparametric MRI

Our team developed a deep learning pipeline for the automated detection of active inflammatory and structural…
LongHealth: Benchmarking LLMs on Lengthy Clinical Documents

In this preprint, our team introduces the LongHealth benchmark, a novel dataset designed to assess the…
GPT-4 for Structured Reporting

Our team investigated the feasibility of using GPT-4, a cutting-edge natural language processing model, to automate…
medBERT.de: a German Medical BERT Model

Our team developed medBERT.de, a comprehensive German BERT model specifically designed for the medical domain. We…

Llama3-70B performs on par with GPT-4-Turbo on answering USMLE questions