Please use this identifier to cite or link to this item: http://ir.unikl.edu.my/jspui/handle/123456789/23613
metadata.conference.dc.title: Unifying the seeds auto-generation (SAGE) with knee cartilage segmentation framework: data from the osteoarthritis initiative.
metadata.conference.dc.contributor.*: Hong-Seng Gan
Khairil Amir Sayuti
Muhammad Hanif Ramlee
Yeng-Seng Lee
Wan Mahani Hafizah Wan Mahmud
Ahmad Helmy Abdul Karim
metadata.conference.dc.subject: Automatic
Knee cartilage segmentation
Random walks
Seeds
metadata.conference.dc.date.issued: 11-Mar-2019
metadata.conference.dc.publisher: International journal of computer assisted radiology and surgery
metadata.conference.dc.description.abstract: Purpose Manual segmentation is sensitive to operator bias, while semiautomatic random walks segmentation offers an intuitive approach to understand the user knowledge at the expense of large amount of user input. In this paper, we propose a novel random walks seed auto-generation (SAGE) hybrid model that is robust to interobserver error and intensive user intervention. Methods Knee image is first oversegmented to produce homogeneous superpixels. Then, a ranking model is developed to rank the superpixels according to their affinities to standard priors, wherein background superpixels would have lower ranking values. Finally, seed labels are generated on the background superpixel using Fuzzy C-Means method. Results SAGE has achieved better interobserver DSCs of 0.94 ± 0.029 and 0.93 ± 0.035 in healthy and OA knee segmentation, respectively. Good segmentation performance has been reported in femoral (Healthy: 0.94 ± 0.036 and OA: 0.93 ± 0.034), tibial (Healthy: 0.91 ± 0.079 and OA: 0.88 ± 0.095) and patellar (Healthy: 0.88 ± 0.10 and OA: 0.84 ± 0.094) cartilage segmentation. Besides, SAGE has demonstrated greater mean readers’ time of 80 ± 19 s and 80 ± 27 s in healthy and OA knee segmentation, respectively. Conclusions SAGE enhances the efficiency of segmentation process and attains satisfactory segmentation performance compared to manual and random walks segmentation. Future works should validate SAGE on progressive image data cohort using OA biomarkers.
metadata.conference.dc.identifier.uri: 10.1007/s11548-019-01936-y
http://ir.unikl.edu.my/jspui/handle/123456789/23613
metadata.conference.dc.identifier.issn: 1861-6410
1861-6429
Appears in Collections:Journal Articles



Items in UniKL IR are protected by copyright, with all rights reserved, unless otherwise indicated.