MORE: Multi-Organ Medical Image REconstruction Dataset

2025-10-30

AI Summary

Existing deep learning–based CT reconstruction methods exhibit poor generalizability to unseen anatomical structures and lesion types, primarily due to the absence of comprehensive, multi-organ, multi-lesion benchmark datasets. Method: We introduce the first publicly available multi-organ CT reconstruction dataset, covering nine anatomical regions and fifteen lesion types, enabling cross-structure and cross-lesion generalization modeling and evaluation. Leveraging this dataset, we jointly optimize model-based and deep learning reconstruction paradigms, trained and validated on large-scale heterogeneous clinical data. Results: Our method achieves an average PSNR improvement of 2.1 dB on unseen anatomical structures and demonstrates significantly superior transfer performance to novel lesion types compared to single-task baselines. This work establishes a critical data foundation and methodological framework for robust medical image reconstruction.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

CT reconstruction provides radiologists with images for diagnosis and treatment, yet current deep learning methods are typically limited to specific anatomies and datasets, hindering generalization ability to unseen anatomies and lesions. To address this, we introduce the Multi-Organ medical image REconstruction (MORE) dataset, comprising CT scans across 9 diverse anatomies with 15 lesion types. This dataset serves two key purposes: (1) enabling robust training of deep learning models on extensive, heterogeneous data, and (2) facilitating rigorous evaluation of model generalization for CT reconstruction. We further establish a strong baseline solution that outperforms prior approaches under these challenging conditions. Our results demonstrate that: (1) a comprehensive dataset helps improve the generalization capability of models, and (2) optimization-based methods offer enhanced robustness for unseen anatomies. The MORE dataset is freely accessible under CC-BY-NC 4.0 at our project page https://more-med.github.io/

Problem

• Addressing limited generalization in CT reconstruction models
• Providing multi-organ dataset with diverse anatomies and lesions
• Establishing robust baseline for medical image reconstruction evaluation

Innovation

• Introduces multi-organ CT reconstruction dataset with diverse anatomies
• Establishes baseline solution outperforming prior reconstruction approaches
• Demonstrates optimization methods enhance robustness for unseen anatomies