MORE: Multi-Organ Medical Image REconstruction Dataset

TL;DR

The paper introduces the MORE dataset, a comprehensive collection of multi-organ CT scans with diverse anatomies and lesions, aimed at improving deep learning model generalization and robustness in medical image reconstruction.

Contribution

It provides a large, diverse dataset for training and evaluating CT reconstruction models, and establishes a baseline that outperforms previous methods under challenging conditions.

Findings

A diverse dataset enhances model generalization.

Optimization-based methods improve robustness for unseen anatomies.

Baseline models outperform prior approaches.

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/