Interactive GPU Active Contours for Segmenting Inhomogeneous Objects

Willcocks, Chris G.; Jackson, Philip T.G.; Nelson, Carl J.; Nasrulloh, Amar; Obara, Boguslaw

Abstract

We present a segmentation software package primarily targeting medical and biological applications, with a high level of visual feedback and several usability enhancements over existing packages. Specifically, we provide a substantially faster GPU implementation of the local Gaussian distribution fitting energy model, which can segment inhomogeneous objects with poorly defined boundaries as often encountered in biomedical images. We also provide interactive brushes to guide the segmentation process in a semiautomated framework. The speed of our implementation allows us to visualize the active surface in real time with a built-in ray tracer, where users may halt evolution at any time step to correct implausible segmentation by painting new blocking regions or new seeds. Quantitative and qualitative validation is presented, demonstrating the practical efficacy of our interactive elements for a variety of real-world datasets.

Citation

Willcocks, C. G., Jackson, P. T., Nelson, C. J., Nasrulloh, A., & Obara, B. (2019). Interactive GPU Active Contours for Segmenting Inhomogeneous Objects. Journal of Real-Time Image Processing, 16(6), 2305-2318. https://doi.org/10.1007/s11554-017-0740-1

• Journal Article Type: Article
• Acceptance Date: Nov 27, 2017
• Online Publication Date: Dec 26, 2017
• Publication Date: Dec 31, 2019
• Deposit Date: May 30, 2017
• Publicly Available Date: Nov 28, 2017
• Journal: Journal of Real-Time Image Processing
• Print ISSN: 1861-8200
• Electronic ISSN: 1861-8219
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 16
• Issue: 6
• Pages: 2305-2318
• DOI: https://doi.org/10.1007/s11554-017-0740-1
• Public URL: https://durham-repository.worktribe.com/output/1385997