Paper Info
Title
Segmentation of humeral head from MR slices
Abstract
The purpose of this study is to segment the humeral head from two dimentional proton dansity(PD) magnetic resonance images (MRI) of shoulder. MRI studies of patients presenting with shoulder pain may demonstrate bone marrow edema and different degrees of contour changes. Computerised tomography(CT) and T1 weighted MR images demonstrate bone margins better. T2 or PD weighted images are poor in determining exact images of bone margins, instead they give better detection of edema and thus pathology. However PD weighted slices have a higher noise to signal ratio than other modalities. Moreover soft tissues in close proximity to humeral head which have the similar intensity with bone make the segmentation of bony humeral head a challenging problem in PD weighted images. In this study we used a new data set which consists of PD weighted axial images of 33 shoulder MRI examinations of 33 randomly selected patients. We used specle reducing anisotropic diffusion(SRAD) method to decrease noise in PD weigted images. Secondly using Hough transform the round shaped humeral head was located roughly, afterwards for a more successful segmentation we applied active contour without edge (ACWE) method. Success of these methods is determined by comparing our results with manual segmentaion results of an expert and evaluated by Sorensen-Dice metric. The average value of measure over the entire database is found to be 90% by ACWE method. Application of ACWE method on PD weighted images provided higly successfull results for segmentation of bony structures. There is no other study to de determine bone contours in PD images in the literature.
Year
DOI
Venue
2014
10.1109/SIU.2014.6830500
Signal Processing and Communications Applications Conference
Keywords
Field
DocType
Hough transforms,biomedical MRI,bone,computerised tomography,image segmentation,medical image processing,ACWE method,CT,Hough transform,PD MR slice segmentation,PD weighted axial images,PD weighted slices,SRAD method,Sorensen-dice metric,T1 weighted MR images,T2 weighted images,active contour without edge method,bone margin images,bone marrow edema,computerised tomography,contour changes degrees,edema detection,humeral head segmentation,noise to signal ratio,pathology detection,shoulder MRI examinations,soft tissues,specle reducing anisotropic diffusion method,two dimensional proton density magnetic resonance images,Active Contours without edge,Segmentation,Shoulder MRI,Specle reducing anisotropic diffusion
Active contour model,Anisotropic diffusion,Computer vision,Segmentation,Computer science,Hough transform,Image segmentation,Tomography,Artificial intelligence,Soft tissue,Magnetic resonance imaging
Conference
ISSN
Citations 
PageRank 
2165-0608
0
0.34
References 
Authors
7
3
Name
Order
Citations
PageRank
Aysun Sezer153.51
Hasan Basri Sezer252.50
Songul Albayrak3286.86