GrowCut-based fast tumor segmentation for 3D magnetic resonance images

Toshihiko Yamasaki; Tsuhan Chen; Masakazu Yagi; Toshinori Hirai; Ryuji Murakami

doi:10.1117/12.911649

Translator Disclaimer

14 February 2012 GrowCut-based fast tumor segmentation for 3D magnetic resonance images

Toshihiko Yamasaki, Tsuhan Chen, Masakazu Yagi, Toshinori Hirai, Ryuji Murakami

Author Affiliations +

Proceedings Volume 8314, Medical Imaging 2012: Image Processing; 831434 (2012) https://doi.org/10.1117/12.911649
Event: SPIE Medical Imaging, 2012, San Diego, California, United States

Abstract

This paper presents a very fast segmentation algorithm based on the region-growing-based segmentation called GrowCut for 3D medical image slices. By the combination of four contributions such as hierarchical segmentation, voxel value quantization, skipping method, and parallelization, the computational time is drastically reduced from 507 seconds to 9.2-14.6 seconds on average for tumor segmentation of 256 x 256 x 200 MRIs.

Citation Download Citation

Toshihiko Yamasaki, Tsuhan Chen, Masakazu Yagi, Toshinori Hirai, and Ryuji Murakami "GrowCut-based fast tumor segmentation for 3D magnetic resonance images", Proc. SPIE 8314, Medical Imaging 2012: Image Processing, 831434 (14 February 2012); https://doi.org/10.1117/12.911649

ACCESS THE FULL ARTICLE