Related Experiment Video
Updated: Sep 19, 2025
07:43
In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
Published on: July 2, 2021
3.2K
HVAngleEst: A Dataset for End-to-end Automated Hallux Valgus Angle Measurement from X-Ray Images
Qiong Wang1, Dongdong Ji1, Junhu Wang1
1Foot and Ankle Surgery Department, Honghui Hospital, Xi'an Jiaotong University, No. 76 Nanguo Road, Xi' an, 710054, People's Republic of China.
Scientific Data
|May 30, 2025
Summary
Accurate hallux valgus angle (HVA) estimation is crucial for diagnosis and treatment. This study introduces HVAngleEst, a large, open-access dataset enabling automated HVA measurement, reducing manual effort and bias.
Area of Science:
- Orthopedics
- Medical Imaging
- Computer Vision
Background:
- Accurate hallux valgus angle (HVA) and intermetatarsal angle (IMA) measurement is vital for diagnosing hallux valgus.
- Current manual methods are time-consuming, labor-intensive, and prone to evaluator bias.
- Deep learning for HVA estimation requires large, well-annotated datasets, which are currently lacking.
Purpose of the Study:
- To introduce HVAngleEst, the first large-scale, open-access dataset for hallux valgus angle estimation.
- To facilitate the development of effective deep learning algorithms for automated HVA and IMA measurement.
- To enable fully automated, end-to-end hallux valgus diagnosis and treatment planning.
Main Methods:
- Developed HVAngleEst, a dataset of 1,382 X-ray images from 1,150 patients.
- Included comprehensive annotations: foot localization, HVA, IMA, and line segments for each phalanx.
- Designed for fully automated, end-to-end hallux valgus angle estimation.
Main Results:
- HVAngleEst is the first large-scale, open-access dataset for HVA estimation.
- The dataset enables automated measurement, significantly reducing manual labor.
- Eliminates evaluator bias inherent in manual measurement techniques.
Conclusions:
- HVAngleEst addresses the critical need for large, annotated datasets in hallux valgus research.
- This dataset will accelerate the development of AI-driven diagnostic tools for hallux valgus.
- Facilitates more accurate, efficient, and objective clinical assessment of hallux valgus.
