A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations
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 imag...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-025-04760-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849774674799493120 |
|---|---|
| author | Zhangnan Zhong Li Huang Shi-Ting Feng Haiwei Lin Xinyue Wang Baolan Lu Kangyang Cao Xuehua Li Bingsheng Huang |
| author_facet | Zhangnan Zhong Li Huang Shi-Ting Feng Haiwei Lin Xinyue Wang Baolan Lu Kangyang Cao Xuehua Li Bingsheng Huang |
| author_sort | Zhangnan Zhong |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-484ed26552ee4c9a8113e551f98eb269 |
| institution | DOAJ |
| issn | 2052-4463 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj-art-484ed26552ee4c9a8113e551f98eb2692025-08-20T03:01:38ZengNature PortfolioScientific Data2052-44632025-03-011211710.1038/s41597-025-04760-zA comprehensive dataset of magnetic resonance enterography images with intestinal segment annotationsZhangnan Zhong0Li Huang1Shi-Ting Feng2Haiwei Lin3Xinyue Wang4Baolan Lu5Kangyang Cao6Xuehua Li7Bingsheng Huang8Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen UniversityDepartment of Radiology, The First Affiliated Hospital, Sun Yat-Sen UniversityDepartment of Radiology, The First Affiliated Hospital, Sun Yat-Sen UniversityMedical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen UniversityDepartment of Radiology, The First Affiliated Hospital, Sun Yat-Sen UniversityDepartment of Radiology, The First Affiliated Hospital, Sun Yat-Sen UniversityMedical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen UniversityDepartment of Radiology, The First Affiliated Hospital, Sun Yat-Sen UniversityMedical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen UniversityAbstract 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.https://doi.org/10.1038/s41597-025-04760-z |
| spellingShingle | Zhangnan Zhong Li Huang Shi-Ting Feng Haiwei Lin Xinyue Wang Baolan Lu Kangyang Cao Xuehua Li Bingsheng Huang A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations Scientific Data |
| title | A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations |
| title_full | A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations |
| title_fullStr | A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations |
| title_full_unstemmed | A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations |
| title_short | A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations |
| title_sort | comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations |
| url | https://doi.org/10.1038/s41597-025-04760-z |
| work_keys_str_mv | AT zhangnanzhong acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT lihuang acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT shitingfeng acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT haiweilin acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT xinyuewang acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT baolanlu acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT kangyangcao acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT xuehuali acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT bingshenghuang acomprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT zhangnanzhong comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT lihuang comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT shitingfeng comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT haiweilin comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT xinyuewang comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT baolanlu comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT kangyangcao comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT xuehuali comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations AT bingshenghuang comprehensivedatasetofmagneticresonanceenterographyimageswithintestinalsegmentannotations |