42 citations · 77 across the 15 of their papers we have counts for
16 papers
Symbal: Detecting Systematic Misalignments in Model-Generated Captions
Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier +2
Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs. Our work focuses on a class of captioning…
CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography
Eva Prakash, Yunhe Gao, Chong Wang +10
Chest radiograph interpretation requires temporal reasoning over prior and current studies, yet most vision-language models are trained on static image-report pairs and lack explic…
A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation
Yabin Zhang, Chong Wang, Yunhe Gao +19
Chest X-rays (CXRs) are among the most frequently performed imaging examinations worldwide, yet rising imaging volumes increase radiologist workload and the risk of diagnostic erro…
Clinician input steers AI toward accurate and harmful recommendations
Ivan Lopez, Selin S. Everett, Bryan J. Bunning +10
Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior during clinical interactions. Using 61 cur…
Gradient-Stable Attention Heads Signal LLM Correctness
Sophie Ostmeier, Brian Axelrod, Maya Varma +6
Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evaluation is expensive, and LLM-as-ju…
TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier +2
Vision-language models (VLMs) have made great strides in addressing temporal understanding tasks, which involve characterizing visual changes across a sequence of images. However,…
From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis
Clemence Mottez, Louisa Fay, Maya Varma +2
Deep learning models have shown promise in improving diagnostic accuracy from chest X-rays, but they also risk perpetuating healthcare disparities when performance varies across de…
Structuring Radiology Reports: Challenging LLMs with Lightweight Models
Johannes Moll, Louisa Fay, Asfandyar Azhar +5
Radiology reports are critical for clinical decision-making but often lack a standardized format, limiting both human interpretability and machine learning (ML) applications. While…
MedVAL: Toward Expert-Level Medical Text Validation with Language Models
Asad Aali, Vasiliki Bikia, Maya Varma +24
With the growing use of language models (LMs) in clinical environments, there is an immediate need to evaluate the accuracy and safety of LM-generated medical text. Currently, such…
MIRIAD: Augmenting LLMs with millions of medical query-response pairs
Qinyue Zheng, Salman Abdullah, Sam Rawal +7
LLMs are bound to transform healthcare with advanced decision support and flexible chat assistants. However, LLMs are prone to generate inaccurate medical content. To ground LLMs i…
Automated Structured Radiology Report Generation
Jean-Benoit Delbrouck, Justin Xu, Johannes Moll +11
Automated radiology report generation from chest X-ray (CXR) images has the potential to improve clinical efficiency and reduce radiologists' workload. However, most datasets, incl…
MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders
Maya Varma, Ashwin Kumar, Rogier van der Sluijs +7
Medical images are acquired at high resolutions with large fields of view in order to capture fine-grained features necessary for clinical decision-making. Consequently, training d…
CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback
Dennis Hein, Zhihong Chen, Sophie Ostmeier +8
Radiologists play a crucial role in translating medical images into actionable reports. However, the field faces staffing shortages and increasing workloads. While automated approa…
LieRE: Lie Rotational Positional Encodings
Sophie Ostmeier, Brian Axelrod, Maya Varma +3
Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that e…
Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset
Louis Blankemeier, Ashwin Kumar, Joseph Paul Cohen +37
The large volume of abdominal computed tomography (CT) scans coupled with the shortage of radiologists have intensified the need for automated medical image analysis tools. Previou…
GREEN: Generative Radiology Report Evaluation and Error Notation
Sophie Ostmeier, Justin Xu, Zhihong Chen +8
Evaluating radiology reports is a challenging problem as factual correctness is extremely important due to the need for accurate medical communication about medical images. Existin…