TY - JOUR
T1 - Bone segmentation in metacarpophalangeal MR data
AU - Kubassova, Olga
AU - Boyle, Roger D.
AU - Pyatnizkiy, Mike
N1 - Funding Information:
We gratefully acknowledge the advice and supervisory support of Dr. E. Berry and Dr. S. F. Tanner [Medical Physics, University of Leeds]. Dr. Tanner is further thanked for providing medical data and evaluation thereof. O. Kubassova acknowledges with thanks the UK Research Councils for financial support via a Dorothy Hodgkin Award.
Funding Information:
O. Kubassova acknowledges with thanks the UK Research Councils for financial support via a Dorothy Hodgkin Award.
PY - 2005
Y1 - 2005
N2 - A robust, efficient segmentation algorithm for automatic segmentation of MR images of the metacarpophalangeal joint is presented. A preliminary segmentation detects bones in MR scans and uses histogram analysis, morphological operations and knowledge based rules to classify various tissues in the joint. The second part of the algorithm improves the segmentation mask and refines boundaries of bones using minimization of a sum of square deviations, automatic signal segmentation into an optimum number of segments, graph theory, and statistical analysis. The algorithm has been tested on 9 MR patient studies and detects 97% of all existing bones correctly with an average exceeding 80% mutual overlap between ground truth and detected regions
AB - A robust, efficient segmentation algorithm for automatic segmentation of MR images of the metacarpophalangeal joint is presented. A preliminary segmentation detects bones in MR scans and uses histogram analysis, morphological operations and knowledge based rules to classify various tissues in the joint. The second part of the algorithm improves the segmentation mask and refines boundaries of bones using minimization of a sum of square deviations, automatic signal segmentation into an optimum number of segments, graph theory, and statistical analysis. The algorithm has been tested on 9 MR patient studies and detects 97% of all existing bones correctly with an average exceeding 80% mutual overlap between ground truth and detected regions
UR - https://www.scopus.com/pages/publications/27244441684
U2 - 10.1007/11552499_80
DO - 10.1007/11552499_80
M3 - Article
AN - SCOPUS:27244441684
SN - 0302-9743
VL - 3687
SP - 726
EP - 735
JO - Lecture Notes in Computer Science
JF - Lecture Notes in Computer Science
IS - PART II
T2 - Third International Conference on Advances in Patten Recognition, ICAPR 2005
Y2 - 22 August 2005 through 25 August 2005
ER -