TY - GEN
T1 - 3D Gabor wavelet based vessel filtering of photoacoustic images
AU - Haq, Israr Ul
AU - Nagoaka, Ryo
AU - Makino, Takahiro
AU - Tabata, Takuya
AU - Saijo, Yoshifumi
N1 - Publisher Copyright:
© 2016 IEEE.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2016/10/13
Y1 - 2016/10/13
N2 - Filtering and segmentation of vasculature is an important issue in medical imaging. The visualization of vasculature is crucial for the early diagnosis and therapy in numerous medical applications. This paper investigates the use of Gabor wavelet to enhance the effect of vasculature while eliminating the noise due to size, sensitivity and aperture of the detector in 3D Optical Resolution Photoacoustic Microscopy (OR-PAM). A detailed multi-scale analysis of wavelet filtering and Hessian based method is analyzed for extracting vessels of different sizes since the blood vessels usually vary with in a range of radii. The proposed algorithm first enhances the vasculature in the image and then tubular structures are classified by eigenvalue decomposition of the local Hessian matrix at each voxel in the image. The algorithm is tested on non-invasive experiments, which shows appreciable results to enhance vasculature in photo-acoustic images.
AB - Filtering and segmentation of vasculature is an important issue in medical imaging. The visualization of vasculature is crucial for the early diagnosis and therapy in numerous medical applications. This paper investigates the use of Gabor wavelet to enhance the effect of vasculature while eliminating the noise due to size, sensitivity and aperture of the detector in 3D Optical Resolution Photoacoustic Microscopy (OR-PAM). A detailed multi-scale analysis of wavelet filtering and Hessian based method is analyzed for extracting vessels of different sizes since the blood vessels usually vary with in a range of radii. The proposed algorithm first enhances the vasculature in the image and then tubular structures are classified by eigenvalue decomposition of the local Hessian matrix at each voxel in the image. The algorithm is tested on non-invasive experiments, which shows appreciable results to enhance vasculature in photo-acoustic images.
UR - http://www.scopus.com/inward/record.url?scp=85009089773&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85009089773&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2016.7591576
DO - 10.1109/EMBC.2016.7591576
M3 - Conference contribution
C2 - 28269134
AN - SCOPUS:85009089773
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 3883
EP - 3886
BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
Y2 - 16 August 2016 through 20 August 2016
ER -