MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI

• URL: http://arxiv.org/abs/2604.11762v1
• Date: Mon, 13 Apr 2026 17:36:01 GMT
• Title: MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI
• Abstract summary: We introduce MosaicMRI, a collection of fully sampled raw musculoskeletal (MSK) MR measurements for training and evaluating machine-learning-based methods.<n>We study scaling behavior with respect to both model capacity and dataset size.<n>Interestingly, models trained on the combined anatomies significantly outperform anatomy-specific models in low-sample regimes.
• Score: 20.01253907654978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Large-scale modality-invariant foundation models for brain MRI analysis: Application to lesion segmentation [0.4915052615294639]
  Large-scale foundation model pre-training can learn anatomical priors that improve few-shot performance in neuroimaging tasks.<n>Most SSL frameworks are tailored to natural images, and their adaptation to capture multi-modal MRI information remains underexplored.<n>This work proposes a modality-invariant representation learning setup and evaluates its effectiveness in stroke and epilepsy lesion segmentation.
  arXiv  Detail & Related papers  (2025-11-14T13:56:07Z)
• Clinical Utility of Foundation Segmentation Models in Musculoskeletal MRI: Biomarker Fidelity and Predictive Outcomes [0.0]
  We evaluate three widely used segmentation models (SAM, SAM2, MedSAM) across eleven musculoskeletal (MSK) MRI datasets.<n>Our framework assesses both zero-shot and finetuned performance, with attention to segmentation accuracy, generalizability across imaging protocols, and reliability of derived quantitative biomarkers.
  arXiv  Detail & Related papers  (2025-01-23T04:41:20Z)
• Enhanced MRI Representation via Cross-series Masking [48.09478307927716]
  Cross-Series Masking (CSM) Strategy for effectively learning MRI representation in a self-supervised manner.<n>Method achieves state-of-the-art performance on both public and in-house datasets.
  arXiv  Detail & Related papers  (2024-12-10T10:32:09Z)
• SegmentAnyBone: A Universal Model that Segments Any Bone at Any Location on MRI [13.912230325828943]
  We propose a versatile, publicly available deep-learning model for bone segmentation in MRI across multiple standard MRI locations. The proposed model can operate in two modes: fully automated segmentation and prompt-based segmentation. Our contributions include (1) collecting and annotating a new MRI dataset across various MRI protocols, encompassing over 300 annotated volumes and 8485 annotated slices across diverse anatomic regions.
  arXiv  Detail & Related papers  (2024-01-23T18:59:25Z)
• MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation [58.53672866662472]
  We introduce a modality-agnostic SAM adaptation framework, named as MA-SAM. Our method roots in the parameter-efficient fine-tuning strategy to update only a small portion of weight increments. By injecting a series of 3D adapters into the transformer blocks of the image encoder, our method enables the pre-trained 2D backbone to extract third-dimensional information from input data.
  arXiv  Detail & Related papers  (2023-09-16T02:41:53Z)
• Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRI [55.78588835407174]
  We propose a method that reformulates the generation task of diffusion models as a patch-based estimation of healthy brain anatomy. We evaluate our approach on data of tumors and multiple sclerosis lesions and demonstrate a relative improvement of 25.1% compared to existing baselines.
  arXiv  Detail & Related papers  (2023-03-07T09:40:22Z)
• Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels [54.58539616385138]
  We introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owN Anatomy (MONA) First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features.
  arXiv  Detail & Related papers  (2022-09-27T15:50:31Z)
• Seeking Common Ground While Reserving Differences: Multiple Anatomy Collaborative Framework for Undersampled MRI Reconstruction [49.16058553281751]
  We present a novel deep MRI reconstruction framework with both anatomy-shared and anatomy-specific parameterized learners. Experiments on brain, knee and cardiac MRI datasets demonstrate that three of these learners are able to enhance reconstruction performance via multiple anatomy collaborative learning.
  arXiv  Detail & Related papers  (2022-06-15T08:19:07Z)
• Universal Undersampled MRI Reconstruction [12.731566667990315]
  We propose a framework to learn a universal deep neural network for undersampled MRI reconstruction. Specifically, anatomy-specific instance normalization is proposed to compensate for statistical shift and allow easy generalization to new datasets. Experimental results show the proposed universal model can reconstruct both brain and knee images with high image quality.
  arXiv  Detail & Related papers  (2021-03-09T04:25:22Z)
• Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI [47.26574993639482]
  We show improved anomaly segmentation performance and the general capability to obtain much more crisp reconstructions of input data at native resolution. The modeling of the laplacian pyramid further enables the delineation and aggregation of lesions at multiple scales.
  arXiv  Detail & Related papers  (2020-06-23T09:20:42Z)
• Modeling Shared Responses in Neuroimaging Studies through MultiView ICA [94.31804763196116]
  Group studies involving large cohorts of subjects are important to draw general conclusions about brain functional organization. We propose a novel MultiView Independent Component Analysis model for group studies, where data from each subject are modeled as a linear combination of shared independent sources plus noise. We demonstrate the usefulness of our approach first on fMRI data, where our model demonstrates improved sensitivity in identifying common sources among subjects.
  arXiv  Detail & Related papers  (2020-06-11T17:29:53Z)
• Large-scale biometry with interpretable neural network regression on UK Biobank body MRI [1.3439502310822151]
  The UK Biobank study has successfully imaged more than 32,000 volunteer participants with magnetic resonance imaging (MRI) Despite its potential for research, this vast amount of data presents a challenge to established methods of evaluation. In this work, neural networks were trained for image-based regression to infer various biological metrics from the neck-to-knee body MRI automatically.
  arXiv  Detail & Related papers  (2020-02-17T09:47:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.