Hessian-assisted supervoxel: Structure-oriented voxel clustering and application to mediastinal lymph node detection from CT volumes

Oda H, Bhatia KK, Oda M, Kitasaka T, Iwano S, Homma H, Takabatake H, Mori M, Natori H, Schnabel JA, Mori K (2017)

Publication Type: Conference contribution

Publication year: 2017

Journal

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

Publisher: SPIE

Book Volume: 10134

Conference Proceedings Title: Progress in Biomedical Optics and Imaging - Proceedings of SPIE

Event location: Orlando, FL, USA

ISBN: 9781510607132

DOI: 10.1117/12.2254782

Abstract

In this paper, we propose a novel supervoxel segmentation method designed for mediastinal lymph node by embedding Hessian-based feature extraction. Starting from a popular supervoxel segmentation method, SLIC, which computes supervoxels by minimising differences of intensity and distance, we overcome this method's limitation of merging neighboring regions with similar intensity by introducing Hessian-based feature analysis into the supervoxel formation. We call this structure-oriented voxel clustering, which allows more accurate division into distinct regions having blob-, line- or sheet-like structures. This way, different tissue types in chest CT volumes can be segmented individually, even if neighboring tissues have similar intensity or are of non- spherical extent. We demonstrate the performance of the Hessian-assisted supervoxel technique by applying it to mediastinal lymph node detection in 47 chest CT volumes, resulting in false positive reductions from lymph node candidate regions. 89 % of lymph nodes whose short axis is at least 10 mm could be detected with 5.9 false positives per case using our method, compared to our previous method having 83 % of detection rate with 6.4 false positives per case.

Involved external institutions

Nagoya University / 名古屋大学 JP Japan (JP) King’s College London GB United Kingdom (GB) Aichi Institute of Technology (AIT) / 愛知工業大学 JP Japan (JP) Sapporo-Kosei General Hospital / JA北海道厚生連札幌厚生病院 JP Japan (JP)

How to cite

APA:

Oda, H., Bhatia, K.K., Oda, M., Kitasaka, T., Iwano, S., Homma, H.,... Mori, K. (2017). Hessian-assisted supervoxel: Structure-oriented voxel clustering and application to mediastinal lymph node detection from CT volumes. In Nicholas A. Petrick, Samuel G. Armato (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Orlando, FL, USA: SPIE.

MLA:

Oda, Hirosha, et al. "Hessian-assisted supervoxel: Structure-oriented voxel clustering and application to mediastinal lymph node detection from CT volumes." Proceedings of the Medical Imaging 2017: Computer-Aided Diagnosis, Orlando, FL, USA Ed. Nicholas A. Petrick, Samuel G. Armato, SPIE, 2017.

BibTeX: Download