Related Experiment Video
Updated: May 24, 2026
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Fully Automated Colon Delineation and Volume Estimation in T2-Weighted MRI with a 2D U-Net
Maciej Plocharski1, Gry B Hvaas1, Maria G Møller1
1Department of Health Science and Technology, Aalborg University, Aalborg, Denmark.
Studies in Health Technology and Informatics
|May 23, 2026
Summary
Artificial intelligence enables objective colon evaluation using MRI scans. This automated method accurately segments the colon, aiding in gastrointestinal disease assessment without radiation exposure.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Gastroenterology
Background:
- Accurate colon segmentation is crucial for assessing gastrointestinal diseases like chronic constipation.
- Manual segmentation is time-consuming and subject to significant interobserver variability.
- Objective and efficient colon evaluation methods are needed.
Purpose of the Study:
- To develop an automated colon segmentation method using T2-weighted MRI.
- To evaluate the accuracy and reliability of the proposed AI-based segmentation technique.
- To provide a non-invasive, radiation-free tool for colon physiology assessment.
Main Methods:
- Utilized a neural network based on the 2D U-Net architecture.
- Trained and validated the network on 297 T2-weighted MRI scans from 72 healthy subjects.
- Compared automated segmentation results against ground truth data.
Main Results:
- Achieved a Dice Similarity Coefficient (DSC) of 0.82 ± 0.04, indicating high accuracy.
- Demonstrated significant correlation between estimated and ground truth colonic volumes (p<0.001).
- Showed no tendency for over- or underestimation of colonic volumes.
Conclusions:
- This study presents the first fully automated colon segmentation method using MRI data.
- The AI-driven approach offers an objective, accurate, and fast alternative to manual segmentation.
- This technique facilitates colon evaluation without radiation exposure or physiological disturbance.