UW-Madison GI Tract Image Segmentation
Projects
ML Marathon
MLM24
Image segmentation
Computer vision
Deep learning
U-Net
Medical imaging
Image data
UW-Madison
The UW-Madison GI Tract Image Segmentation challenge was featured in the 2024 Machine Learning Marathon (MLM24). Originally a major Kaggle competition (1,500+ teams), this challenge asks participants to automatically segment the stomach and intestines on MRI scans taken during radiation treatment for cancer patients.
Challenge design
- Task: Segment the stomach, small bowel, and large bowel in MRI scans of cancer patients undergoing radiation therapy.
- Domain: Medical imaging – accurate organ segmentation can speed up cancer treatment by enabling faster radiation planning on MR-Linac systems.
- Data: Serial MRI scans from real cancer patients who underwent 1-5 scans on different days during treatment.
Links
- Kaggle challenge: UW-Madison GI Tract Image Segmentation
- Dataset: UW-Madison GI Tract Image Segmentation Dataset
Questions
If you have any lingering questions about this project, please feel free to post to the Nexus Q&A on GitHub. We will improve materials on this website as additional questions come in.