Robust retinal blood vessel segmentation using a patch-based statistical adaptive multi-scale line detector

TY - JOUR

T1 - Robust retinal blood vessel segmentation using a patch-based statistical adaptive multi-scale line detector

AU - Iqbal, Shahzaib

AU - Naveed, Khuram

AU - Naqvi, Syed S.

AU - Naveed, Asim

AU - Khan, Tariq M.

N1 - Publisher Copyright: © 2023 Elsevier Inc.

PY - 2023/7

Y1 - 2023/7

N2 - The diagnosis of diseases using the retinal vasculature has long been a focus of medical research. Segmenting the vessels from retinal images is still a difficult task because of the variability in retinal vascular thickness and the inhomogeneity of image intensity. In this research work, a two-stage retinal vessel segmentation method is proposed. At the first stage, the large vessels are segmented by using multi-scale line detection by suppressing the small vessels through non-local mean filtering. At the second stage, the image is enhanced through noise suppression attributed largely to the block-matching 3-D filtering inside the nonsubsampled contourlet transform. Then a patch-based multi-scale line detector with adaptive statistical thresholding is used. Finally, both large and small vessels are combined to reconstruct the final vessel segmented image. The proposed method is evaluated on two publicly available databases and achieves an average sensitivity of 82.61%, and 81.67% on the DRIVE and STARE datasets respectively. The proposed method outperforms other state-of-the-art methods and has proven to be effective in boosting the sensitivity of retinal vessel segmentation.

AB - The diagnosis of diseases using the retinal vasculature has long been a focus of medical research. Segmenting the vessels from retinal images is still a difficult task because of the variability in retinal vascular thickness and the inhomogeneity of image intensity. In this research work, a two-stage retinal vessel segmentation method is proposed. At the first stage, the large vessels are segmented by using multi-scale line detection by suppressing the small vessels through non-local mean filtering. At the second stage, the image is enhanced through noise suppression attributed largely to the block-matching 3-D filtering inside the nonsubsampled contourlet transform. Then a patch-based multi-scale line detector with adaptive statistical thresholding is used. Finally, both large and small vessels are combined to reconstruct the final vessel segmented image. The proposed method is evaluated on two publicly available databases and achieves an average sensitivity of 82.61%, and 81.67% on the DRIVE and STARE datasets respectively. The proposed method outperforms other state-of-the-art methods and has proven to be effective in boosting the sensitivity of retinal vessel segmentation.

KW - Digital Image processing

KW - Multiscale line detector

KW - Retinal vessel extraction

KW - Statistical adaptive thresholding

U2 - 10.1016/j.dsp.2023.104075

DO - 10.1016/j.dsp.2023.104075

M3 - Journal article

AN - SCOPUS:85159358243

SN - 1051-2004

VL - 139

JO - Digital Signal Processing: A Review Journal

JF - Digital Signal Processing: A Review Journal

M1 - 104075

ER -