5 papers
EndoExtract: Co-Designing Structured Text Extraction from Endometriosis Ultrasound Reports
Haiyi Li, Yiyang Zhao, Yutong Li +5
Endometriosis ultrasound reports are often unstructured free-text documents that require manual abstraction for downstream tasks such as analytics, machine learning model training,…
Who Fails Where? LLM and Human Error Patterns in Endometriosis Ultrasound Report Extraction
Haiyi Li, Yutong Li, Yiheng Chi +7
In this study, we evaluate a locally-deployed large-language model (LLM) to convert unstructured endometriosis transvaginal ultrasound (eTVUS) scan reports into structured data for…
Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data
Hu Wang, Salma Hassan, Yuyuan Liu +12
In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this…
Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality
Hu Wang, Congbo Ma, Jianpeng Zhang +4
The problem of missing modalities is both critical and non-trivial to be handled in multi-modal models. It is common for multi-modal tasks that certain modalities contribute more c…
Human-AI Collaborative Multi-modal Multi-rater Learning for Endometriosis Diagnosis
Hu Wang, David Butler, Yuan Zhang +5
Endometriosis, affecting about 10% of individuals assigned female at birth, is challenging to diagnose and manage. Diagnosis typically involves the identification of various signs…