RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis

2025-07-07

AI Summary

Instance-level annotations are scarce in radiographic analysis of rheumatoid arthritis (RA) wrist X-rays, and bone erosion (BE) detection remains challenging due to subtle morphological changes and inter-reader variability. Method: We introduce RA-WristSeg, the first publicly available multi-task wrist X-ray dataset, curated from multi-center clinical imaging. It comprises 621 wrist radiographs, with pixel-level instance segmentation annotations for carpal bones on 443 images and standardized Sharp/van der Heijde (SvdH) BE scores on 548 images. Contribution/Results: RA-WristSeg uniquely integrates fine-grained anatomical segmentation with clinical radiological scoring, enabling unified tasks including BE detection, joint space assessment, and quantitative disease progression modeling. It is the first dataset to jointly provide carpal bone instance segmentation and standardized SvdH scoring—establishing a reproducible, scalable benchmark for computer-aided diagnosis and longitudinal monitoring of RA.

Technology Category

• Computer Vision: Segmentation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Rheumatoid arthritis (RA) is a common autoimmune disease that has been the focus of research in computer-aided diagnosis (CAD) and disease monitoring. In clinical settings, conventional radiography (CR) is widely used for the screening and evaluation of RA due to its low cost and accessibility. The wrist is a critical region for the diagnosis of RA. However, CAD research in this area remains limited, primarily due to the challenges in acquiring high-quality instance-level annotations. (i) The wrist comprises numerous small bones with narrow joint spaces, complex structures, and frequent overlaps, requiring detailed anatomical knowledge for accurate annotation. (ii) Disease progression in RA often leads to osteophyte, bone erosion (BE), and even bony ankylosis, which alter bone morphology and increase annotation difficulty, necessitating expertise in rheumatology. This work presents a multi-task dataset for wrist bone in CR, including two tasks: (i) wrist bone instance segmentation and (ii) Sharp/van der Heijde (SvdH) BE scoring, which is the first public resource for wrist bone instance segmentation. This dataset comprises 621 wrist conventional radiographs of 227 patients from four medical centers, with pixel-level instance segmentation annotations for 443 images and SvdH BE scores for 548 images. This dataset can potentially support a wide range of research tasks related to RA, including joint space narrowing (JSN) progression quantification, BE detection, bone deformity evaluation, and osteophyte detection. It may also be applied to other wrist-related tasks, such as carpal bone fracture localization. We hope this dataset will significantly lower the barrier to research on wrist RA and accelerate progress in CAD research within the RA-related domain.

Problem

• Lack of high-quality wrist bone instance segmentation datasets for RA diagnosis
• Difficulty in annotating wrist bones due to complex structures and disease effects
• Need for a multi-task dataset to support diverse RA-related research tasks

Innovation

• Multi-task dataset for wrist bone CR
• Includes instance segmentation and BE scoring
• First public wrist bone instance segmentation resource