# MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs

arXiv: https://arxiv.org/abs/1712.06957 · HTML: https://mlsanity.com/paper/1712.06957/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2017.

## Built on by (most cited first, 20 of 20)

- [Adaptive Consistency Regularization for Semi-Supervised Transfer Learning](https://mlsanity.com/paper/2103.02193/) (2021)
- [Fr'echet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets](https://mlsanity.com/paper/2412.01496/) (2024)
- [Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm](https://mlsanity.com/paper/2304.05071/) (2023)
- [A Survey of Medical Vision-and-Language Applications and Their Techniques](https://mlsanity.com/paper/2411.12195/) (2024)
- [DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?](https://mlsanity.com/paper/2505.24173/) (2025)
- [False Promises in Medical Imaging AI? Assessing Validity of Outperformance Claims](https://mlsanity.com/paper/2505.04720/) (2025)
- [Towards Inadequately Pre-trained Models in Transfer Learning](https://mlsanity.com/paper/2203.04668/) (2022)
- [LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions](https://mlsanity.com/paper/2411.16760/) (2024)
- [Deployment of Image Analysis Algorithms under Prevalence Shifts](https://mlsanity.com/paper/2303.12540/) (2023)
- [Dynamically Scaled Temperature in Self-Supervised Contrastive Learning](https://mlsanity.com/paper/2308.01140/) (2023)
- [Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographs](https://mlsanity.com/paper/2403.19107/) (2024)
- [Outlier Detection in Large Radiological Datasets using UMAP](https://mlsanity.com/paper/2407.21263/) (2024)
- [Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AI](https://mlsanity.com/paper/2412.08763/) (2024)
- [Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development](https://mlsanity.com/paper/2603.27460/) (2026)
- [Global Context Modeling in YOLOv8 for Pediatric Wrist Fracture Detection](https://mlsanity.com/paper/2407.03163/) (2024)
- [Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images](https://mlsanity.com/paper/2410.01031/) (2024)
- [A novel approach towards the classification of Bone Fracture from Musculoskeletal Radiography images using Attention Based Transfer Learning](https://mlsanity.com/paper/2410.14833/) (2024)
- [SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification](https://mlsanity.com/paper/2510.02109/) (2025)
- [Google-MedGemma Based Abnormality Detection in Musculoskeletal radiographs](https://mlsanity.com/paper/2511.05600/) (2025)
- [QuPID: Quantum Parameter-Efficient Input-Dependent Retrieval Adaptation for Medical RAG](https://mlsanity.com/paper/2609.33351/) (2026)

## Abstract (arXiv)

We introduce MURA, a large dataset of musculoskeletal radiographs containing 40,561 images from 14,863 studies, where each study is manually labeled by radiologists as either normal or abnormal. To evaluate models robustly and to get an estimate of radiologist performance, we collect additional labels from six board-certified Stanford radiologists on the test set, consisting of 207 musculoskeletal studies. On this test set, the majority vote of a group of three radiologists serves as gold standard. We train a 169-layer DenseNet baseline model to detect and localize abnormalities. Our model achieves an AUROC of 0.929, with an operating point of 0.815 sensitivity and 0.887 specificity. We compare our model and radiologists on the Cohen's kappa statistic, which expresses the agreement of our model and of each radiologist with the gold standard. Model performance is comparable to the best radiologist performance in detecting abnormalities on finger and wrist studies. However, model performance is lower than best radiologist performance in detecting abnormalities on elbow, forearm, hand, humerus, and shoulder studies. We believe that the task is a good challenge for future research. To encourage advances, we have made our dataset freely available at https://stanfordmlgroup.github.io/competitions/mura .