TY - GEN
T1 - Analysis of parameters' effects in semi-automated knee cartilage segmentation model
T2 - 2nd International Conference on Mathematics, Engineering and Industrial Applications 2016, ICOMEIA 2016
AU - Gan, Hong Seng
AU - Karim, Ahmad Helmy Abdul
AU - Sayuti, Khairil Amir
AU - Tan, Tian Swee
AU - Kadir, Mohammed Rafiq Abdul
N1 - Publisher Copyright:
© 2016 Author(s).
PY - 2016/10/24
Y1 - 2016/10/24
N2 - Unlike automated segmentation, the accuracy of semi-automated segmentation is affected by pertinent parameters such as observer, type of methods and type of cartilage. In this paper, we investigated the effect of these parameters on segmentation results. Based on Dice similarity index obtained from fifteen normal and ten diseased magnetic resonance images, a parameter estimation model was constructed to study the impact of each parameter. Then, we conducted deviance test to verify the effect's significance. Our result showed that implementation of the proposed segmentation model would introduce positive effect (+0.12) on reproducibility compared to conventional random walks model. Furthermore, we have found intriguing results indicating cartilage normality has diminished effect on reproducibility and tibial cartilage's result could be influenced by external factors as well. Lastly, our findings highlighted on the necessity of refinement for semi-automated segmentation.
AB - Unlike automated segmentation, the accuracy of semi-automated segmentation is affected by pertinent parameters such as observer, type of methods and type of cartilage. In this paper, we investigated the effect of these parameters on segmentation results. Based on Dice similarity index obtained from fifteen normal and ten diseased magnetic resonance images, a parameter estimation model was constructed to study the impact of each parameter. Then, we conducted deviance test to verify the effect's significance. Our result showed that implementation of the proposed segmentation model would introduce positive effect (+0.12) on reproducibility compared to conventional random walks model. Furthermore, we have found intriguing results indicating cartilage normality has diminished effect on reproducibility and tibial cartilage's result could be influenced by external factors as well. Lastly, our findings highlighted on the necessity of refinement for semi-automated segmentation.
UR - http://www.scopus.com/inward/record.url?scp=84997285878&partnerID=8YFLogxK
U2 - 10.1063/1.4965172
DO - 10.1063/1.4965172
M3 - Conference Proceeding
AN - SCOPUS:84997285878
T3 - AIP Conference Proceedings
BT - International Conference on Mathematics, Engineering and Industrial Applications 2016, ICOMEIA 2016
A2 - Khazali, Khairul Anwar Mohamad
A2 - Daud, Wan Suhana Wan
A2 - Amin, Nor Azrita Mohd
A2 - Zaimi, Wan Mohd Khairy Adly Wan
A2 - Yusuf, Yusmye Nur Abu
A2 - Abdullah, Nooraihan
A2 - Aziz, Nurul Huda Abdul
A2 - Rusli, Nursalasawati
A2 - Masnan, Maz Jamilah
A2 - Yahya, Zainab
PB - American Institute of Physics Inc.
Y2 - 10 August 2016 through 12 August 2016
ER -