MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs

Abstract

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 .

arXiv comment1st Conference on Medical Imaging with Deep Learning (MIDL 2018)

Cited by in corpus (26)

• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
• Contrastive Learning of Medical Visual Representations from Paired Images and Text
• Transformers in Healthcare: A Survey
• Comparison of fine-tuning strategies for transfer learning in medical image classification
• Targeted transfer learning to improve performance in small medical physics datasets
• Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System
• COVID-MobileXpert: On-Device COVID-19 Patient Triage and Follow-up using Chest X-rays
• CheXpedition: Investigating Generalization Challenges for Translation of Chest X-Ray Algorithms to the Clinical Setting
• PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentation
• MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
• Treatment Learning Causal Transformer for Noisy Image Classification
• Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations
• The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning
• IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning
• MRI Pulse Sequence Integration for Deep-Learning Based Brain Metastasis Segmentation
• Automating Abnormality Detection in Musculoskeletal Radiographs through Deep Learning
• Anomaly Detection on X-Rays Using Self-Supervised Aggregation Learning
• Probabilistic Neighbourhood Component Analysis: Sample Efficient Uncertainty Estimation in Deep Learning
• Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives
• Adversarial Policy Gradient for Deep Learning Image Augmentation
• Medical Datasets Collections for Artificial Intelligence-based Medical Image Analysis
• A Practical Framework for ROI Detection in Medical Images -- a case study for hip detection in anteroposterior pelvic radiographs
• Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models
• Classification of COVID-19 from CXR Images in a 15-class Scenario: an Attempt to Avoid Bias in the System
• Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning