Related Experiment Video
Updated: May 23, 2025
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
Published on: June 21, 2024
A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations
Zhangnan Zhong1,2, Li Huang3, Shi-Ting Feng3
1Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, 518060, China.
Abstract:
Inflammatory bowel disease (IBD) is a recurrent bowel disease that usually requires magnetic resonance enterography (MRE) for diagnosis and monitoring. However, recognition of bowel segments from MRE images by a radiologist is challenging and time-consuming. Deep learning-based medical image segmentation has shown the potential to reduce manual effort and provide automated tools to assist in disease management; however, it requires a large-scale fine-annotated dataset for training. To address this gap, we collected MRE data, including half-Fourier acquisition single-shot turbo spin-echo(HASTE) sequences with coronal orientation, from 114 patients with IBD, who received 1600-2000 mL of 2.5% mannitol. The bowel images per patient were contoured and annotated into ten segments (stomach, duodenum, small intestine, appendix, cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum), with fine pixel-level annotations labeled by experienced radiologists. Furthermore, we validated the efficiency of several state-of-the-art segmentation methods using this dataset. This study established a high-quality, publicly available whole-bowel segment MR dataset with benchmark results and laid the groundwork for AI research on IBD.
Insights
Researchers created a new dataset of whole-bowel MRI scans for Inflammatory Bowel Disease (IBD) patients. This resource aids in developing AI tools for faster, automated diagnosis and monitoring of IBD using magnetic resonance enterography.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Gastroenterology
Background:
- Inflammatory Bowel Disease (IBD) diagnosis and monitoring rely on Magnetic Resonance Enterography (MRE).
- Manual segmentation of bowel segments in MRE is labor-intensive and challenging for radiologists.
- Deep learning for medical image segmentation requires large, annotated datasets, which are currently lacking for IBD MRE.
Purpose of the Study:
- To address the need for a comprehensive dataset for AI development in IBD.
- To create a high-quality, publicly available dataset of annotated whole-bowel MRE images.
- To establish benchmark results for state-of-the-art segmentation methods on this new dataset.
Main Methods:
- Collected MRE data (coronal HASTE sequences) from 114 IBD patients who ingested 2.5% mannitol.
- Annotated 1600-2000 mL bowel images per patient into ten distinct segments with pixel-level precision.
- Radiologists meticulously labeled the contours of each bowel segment.
Main Results:
- Established a novel, high-quality dataset of whole-bowel MR images specifically for IBD.
- The dataset includes fine pixel-level annotations for ten bowel segments.
- Validated the performance of several leading AI segmentation techniques on the dataset.
Conclusions:
- The developed dataset provides a crucial resource for advancing AI research in IBD.
- This work facilitates the development of automated tools for MRE analysis in IBD.
- The dataset and benchmark results pave the way for improved IBD diagnosis and management.
Related Concept Videos
01:26Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
01:24Magnetic Resonance Imaging