Title
Combining split-and-merge and multi-seed region growing algorithms for uterine fibroid segmentation in MRgFUS treatments
Abstract
Uterine fibroids are benign tumors that can affect female patients during reproductive years. Magnetic resonance-guided focused ultrasound (MRgFUS) represents a noninvasive approach that uses thermal ablation principles to treat symptomatic fibroids. During traditional treatment planning, uterus, fibroids, and surrounding organs at risk must be manually marked on MR images by an operator. After treatment, an operator must segment, again manually, treated areas to evaluate the non-perfused volume (NPV) inside the fibroids. Both pre- and post-treatment procedures are time-consuming and operator-dependent. This paper presents a novel method, based on an advanced direct region detection model, for fibroid segmentation in MR images to address MRgFUS post-treatment segmentation issues. An incremental procedure is proposed: split-and-merge algorithm results are employed as multiple seed-region selections by an adaptive region growing procedure. The proposed approach segments multiple fibroids with different pixel intensity, even in the same MR image. The method was evaluated using area-based and distance-based metrics and was compared with other similar works in the literature. Segmentation results, performed on 14 patients, demonstrated the effectiveness of the proposed approach showing a sensitivity of 84.05 %, a specificity of 92.84 %, and a speedup factor of 1.56× with respect to classic region growing implementations (average values).
Year
DOI
Venue
2016
10.1007/s11517-015-1404-6
Medical & Biological Engineering & Computing
Keywords
DocType
Volume
Automatic segmentation, Split-and-merge segmentation, Multi-seed adaptive region growing, MRgFUS treatments, Uterine fibroids
Journal
54
Issue
ISSN
Citations 
7
1741-0444
3
PageRank 
References 
Authors
0.41
14
7
Name
Order
Citations
PageRank
Leonardo Rundo1151.29
Carmelo Militello211211.68
Salvatore Vitabile344460.03
Carlo Casarino430.41
Giorgio Lo Russo5385.89
Massimo Midiri6152.00
Maria Carla Gilardi7589.92