MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI
2026-04-13 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors created MosaicMRI, a large and varied dataset of musculoskeletal MRI scans, to help improve and test deep learning models beyond the typical brain and knee images. They showed that training models on mixed body parts works better, especially when there isn’t much data for each part. Their experiments also found that some body parts’ images allow models to learn general features that apply across different anatomies. Finally, they discovered that a model’s performance when tested on new body parts depends on how much training data it has and specific scanning methods used.
MRIDeep LearningMusculoskeletal ImagingDatasetImage ReconstructionVarNetCross-Anatomy GeneralizationDomain ShiftImaging ContrastsModel Scaling
Authors
Paula Arguello, Berk Tinaz, Mohammad Shahab Sepehri, Maryam Soltanolkotabi, Mahdi Soltanolkotabi
Abstract
Deep learning underpins a wide range of applications in MRI, including reconstruction, artifact removal, and segmentation. However, progress has been driven largely by public datasets focused on brain and knee imaging, shaping how models are trained and evaluated. As a result, careful studies of the reliability of these models across diverse anatomical settings remain limited. In this work, we introduce MosaicMRI, a large and diverse collection of fully sampled raw musculoskeletal (MSK) MR measurements designed for training and evaluating machine-learning-based methods. MosaicMRI is the largest open-source raw MSK MRI dataset to date, comprising 2,671 volumes and 80,156 slices. The dataset offers substantial diversity in volume orientation (e.g., axial, sagittal), imaging contrasts (e.g., PD, T1, T2), anatomies (e.g., spine, knee, hip, ankle, and others), and numbers of acquisition coils. Using VarNet as a baseline for accelerated reconstruction task, we perform a comprehensive set of experiments to study scaling behavior with respect to both model capacity and dataset size. Interestingly, models trained on the combined anatomies significantly outperform anatomy-specific models in low-sample regimes, highlighting the benefits of anatomical diversity and the presence of exploitable cross-anatomical correlations. We further evaluate robustness and cross-anatomy generalization by training models on one anatomy (e.g., spine) and testing them on another (e.g., knee). Notably, we identify groups of body parts (e.g., foot and elbow) that generalize well with each other, and highlight that performance under domain shifts depends on both training set size, anatomy, and protocol-specific factors.