# MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI

arXiv: https://arxiv.org/abs/2604.11762 · HTML: https://mlsanity.com/paper/2604.11762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [Learning a Variational Network for Reconstruction of Accelerated MRI Data](https://mlsanity.com/paper/1704.00447/) (2017)
- [Score-based diffusion models for accelerated MRI](https://mlsanity.com/paper/2110.05243/) (2021)
- [End-to-End Variational Networks for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2004.06688/) (2020)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1802.01221/) (2018)
- [Deep learning for undersampled MRI reconstruction](https://mlsanity.com/paper/1709.02576/) (2017)
- [Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT](https://mlsanity.com/paper/1708.08333/) (2017)
- [Measuring Robustness in Deep Learning Based Compressive Sensing](https://mlsanity.com/paper/2102.06103/) (2021)
- [OCMR (v1.0)--Open-Access Multi-Coil k-Space Dataset for Cardiovascular Magnetic Resonance Imaging](https://mlsanity.com/paper/2008.03410/) (2020)
- [HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction](https://mlsanity.com/paper/2203.08213/) (2022)
- [i-RIM applied to the fastMRI challenge](https://mlsanity.com/paper/1910.08952/) (2019)
- [Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data](https://mlsanity.com/paper/2312.10271/) (2023)
- [Sigma-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction](https://mlsanity.com/paper/1912.09278/) (2019)
- [fastMRI Breast: A publicly available radial k-space dataset of breast dynamic contrast-enhanced MRI](https://mlsanity.com/paper/2406.05270/) (2024)
- [Improving Deep Learning for Accelerated MRI With Data Filtering](https://mlsanity.com/paper/2508.13822/) (2025)

## Abstract (arXiv)

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 3,150 volumes and 89,830 slices, including a 3,096-volume 1.5~T core dataset and a 54-volume 0.55~T low-field set. 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), numbers of acquisition coils, and field strengths. Using accelerated reconstruction as a testbed, we study scaling, robustness, and data selection under realistic MSK distribution shifts. Across E2E-VarNet, U-Net, and ViT baselines, mixed-anatomy training improves over anatomy-specific training, showing that the benefit of anatomical diversity is not architecture-specific. Zero-shot experiments on the 0.55~T low-field set highlight that using more training data improves average reconstruction under field-strength shift. Controlled subset experiments further suggest that these gains come from transferable cross-anatomy structure, rather than anatomy or contrast matching alone.