Conference proceeding
Surf-CDM: Score-Based Surface Cold-Diffusion Model for Medical Image Segmentation
2024 IEEE International Symposium on Biomedical Imaging (ISBI), pp.1-5
05/27/2024
DOI: 10.1109/ISBI56570.2024.10635329
Abstract
Diffusion models have shown impressive performance for image generation, often times outperforming other generative models. Since their introduction, researchers have extended the powerful noise-to-image denoising pipeline to discriminative tasks, including image segmentation. In this work we propose a conditional score-based generative modeling framework for medical image segmentation which relies on a parametric surface representation for the segmentation masks. Moreover, we adapted an extended variant of the diffusion technique known as the "cold-diffusion" where the diffusion model can be constructed with deterministic perturbations instead of Gaussian noise, which facilitates significantly faster convergence in the reverse diffusion. We evaluated our method on an echocardiogram video dataset (2230 echo image frames) and compared its performance to the most popular and widely used image segmentation models. Our proposed model not only outperformed the compared methods in terms of segmentation accuracy, but also showed potential in estimating segmentation uncertainties for further downstream analyses due to its inherent generative nature.
Details
- Title: Subtitle
- Surf-CDM: Score-Based Surface Cold-Diffusion Model for Medical Image Segmentation
- Creators
- Fahim Ahmed Zaman - University of IowaMathews Jacob - University of IowaAmanda Chang - University of IowaKan Liu - University of Iowa, Cardiovascular MedicineMilan Sonka - University of IowaXiaodong Wu - University of Iowa
- Resource Type
- Conference proceeding
- Publication Details
- 2024 IEEE International Symposium on Biomedical Imaging (ISBI), pp.1-5
- DOI
- 10.1109/ISBI56570.2024.10635329
- eISSN
- 1945-8452
- Publisher
- IEEE
- Language
- English
- Date published
- 05/27/2024
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Iowa Technology Institute; Iowa Neuroscience Institute; Cardiovascular Medicine; Radiation Oncology; The Iowa Institute for Biomedical Imaging; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Internal Medicine; Ophthalmology and Visual Sciences
- Record Identifier
- 9984699054302771
Metrics
53 Record Views