6 papers
From Documents to Spans: Scalable Supervision for Evidence-Based ICD Coding with LLMs
Xu Zhang, Wenxin Ma, Chenxu Wu +5
International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis. Reliable coding r…
CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning
Wenxin Ma, Chenlong Wang, Ruisheng Yuan +6
Humans can look at a static scene and instantly predict what happens next -- will moving this object cause a collision? We call this ability Causal Spatial Reasoning. However, curr…
Histomorphology-Guided Prototypical Multi-Instance Learning for Breast Cancer WSI Classification
Baizhi Wang, Rui Yan, Wenxin Ma +6
Histomorphology is crucial in cancer diagnosis. However, existing whole slide image (WSI) classification methods struggle to effectively incorporate histomorphology information, li…
Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster
Fenghe Tang, Wenxin Ma, Zhiyang He +3
With the advancement of Large Language Model (LLM) for natural language processing, this paper presents an intriguing finding: a frozen pre-trained LLM layer can process visual tok…
MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification
Chunjiang Wang, Kun Zhang, Yandong Liu +3
The concept bottleneck model (CBM), as a technique improving interpretability via linking predictions to human-understandable concepts, makes high-risk and life-critical medical im…
A General Knowledge Injection Framework for ICD Coding
Xu Zhang, Kun Zhang, Wenxin Ma +4
ICD Coding aims to assign a wide range of medical codes to a medical text document, which is a popular and challenging task in the healthcare domain. To alleviate the problems of l…