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

TY - CHAP

T1 - Hessian-assisted supervoxel

T2 - Medical Imaging 2017: Computer-Aided Diagnosis

AU - Oda, Hirohisa

AU - Bhatia, Kanwal K.

AU - Oda, Masahiro

AU - Kitasaka, Takayuki

AU - Iwano, Shingo

AU - Homma, Hirotoshi

AU - Takabatake, Hirotsugu

AU - Mori, Masaki

AU - Natori, Hiroshi

AU - Schnabel, Julia A.

AU - Mori, Kensaku

PY - 2017

Y1 - 2017

N2 - 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.

AB - 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.

KW - Clustering

KW - Computer aided detection

KW - Feature extraction

UR - http://www.scopus.com/inward/record.url?scp=85020307663&partnerID=8YFLogxK

U2 - 10.1117/12.2254782

DO - 10.1117/12.2254782

M3 - Other chapter contribution

AN - SCOPUS:85020307663

VL - 10134

BT - Medical Imaging 2017: Computer-Aided Diagnosis

PB - SPIE

Y2 - 13 February 2017 through 16 February 2017

ER -