A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model
International Journal of Computer Vision
Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations (Applied Mathematical Sciences)
| Hi-index | 0.00 |
The temporomandibular joint is one of the most complicated joints in the human body. Diagnosing its disorders is difficult because the pain is mistakenly taken for toothache, pain in the jaw bones, etc. The paper deals with a post-processing tomographic examination of temporomandibular joint. An interesting post-processing method was used to increase the contrast related to relaxation time T2. Both increasing the contrast and enbancing the arthritic region were realized by processing two MR images in different echo-times. The enhancement rate is realized on the basis of subjective MR image evaluation by the surgeon. Magnetic resonance images (MRIs) are of very low resolution and contrast. An appropriate algorithm has been found, which consists of preprocessing the image by a smoothing filter, focusing, and four-phase level set segmentation. This method segments the image on the basis of the intensity of respective regions and is thus suitable to be applied to the above MR images, in which no sharp edges occur.