Abstract #1376

Semi-automatic segmentation of medulloblastoma using active contour method

Ka Hei Lok¹, Lin Shi^2,3, Queenie Chan⁴, and Defeng Wang^5,6

¹Department of Imaging and Intenvntional Radiology, The Chinese University of Hong Kong, Sha Tin, Hong Kong, ²Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Sha Tin, Hong Kong, ³Chow Yuk Ho Technology Centre for Innovative Medicine, The Chinese University of Hong Kong, Sha Tin, Hong Kong, ⁴Philips Healthcare, Hong Kong, Hong Kong, ⁵Research Center for Medical Image Computing, Department of Imaging and Intenvntional Radiology, The Chinese University of Hong Kong, Sha Tin, Hong Kong, ⁶Shenzhen Research Institute, The Chinese University of Hong Kong, Shenzhen, China, People's Republic of

Brain tumours are the second commonest form of childhood malignancy while medulloblastoma is the most common brain tumor in children. Accurate Segmentation of medulloblastoma is necessary for maximum tumor surgical removal. We proposed a novel method to segment medulloblastoma by modifying signed pressure function (SPF) function in Gaussians Filtering Regularized Level Set (SBGRLS) method. Quantitative validation is performed in this project. The method is proved to be clinical-oriented which is fast, robust, accurate with minimal user interaction.

This abstract and the presentation materials are available to members only; a login is required.

Join Here