Exploiting the Self-Organizing Map for Medical Image Segmentation

Author(s):  
Ping-Lin Chang ◽  
Wei-Guang Teng

2014 ◽  
Vol 6 (1) ◽  
pp. 7-13
Author(s):  
Khoirul Umam ◽  
Fidi Wincoko Putro ◽  
Gulpi Qorik Oktagalu Pratamasunu

Segmentation on medical image requires good quality due to affect the interpretation and diagnosis of medical experts. On medical image segmentation, there is merging phase to increase the quality of the segmentation result. However, stopping criteria on merging phase was determined manually by medical experts. It implied the subjectivity of segmentation result. To increase the objectivity of segmentation result, a method to automate merging phase on medical image segmentation is required. Therefore, we propose a novel method on medical image segmentation which combine two-stage SOM and T-cluster method. Experiments were performed on dental panoramic as medical image sample and evaluated by using segmentation quality formula. Experiments show that the proposed method can perform segmentation on dental panoramic image automatically and objectively with the best average of segmentation quality value is 4,40. Index Terms—dental panoramic image, image segmentation, medical image, Self-Organizing Map, T-cluster





2019 ◽  
Vol 31 (6) ◽  
pp. 1007 ◽  
Author(s):  
Haiou Wang ◽  
Hui Liu ◽  
Qiang Guo ◽  
Kai Deng ◽  
Caiming Zhang


Sign in / Sign up

Export Citation Format

Share Document