Meeting Banner
Abstract #2905

A Time efficient IVIM analysis method using fuzzy clustering algorithm

Kaining Shi 1 , He Wang 2 , Guang Cao 3 , Ying Qi 4 , and Xiaoming Wang 4

1 Imaging Systems Clinical Science, Philips Healthcare (China), Beijing, China, 2 Philips Research (China), Shanghai, China, 3 Imaging Systems Clinical Science, Philips Healthcare (China), Hongkong, China, 4 Radiology Department, Shengjing Hospital of China Medical University, Shenyang, Liaoning, China

The nonlinear bi-exponential curve-fitting in the Intravoxel Incoherent Motion (IVIM) model is sensitive to noise and time-consuming. In this work, fussy clustering technique is used to improve the reliability of curve-fitting and reduce the total calculation time.16 b-values DWI data of 2 PRES patients and 2 volunteers was processed by the fussy clustering analysis method. The new algorithm achieved brain segmentation successfully and generated similar parameters as the pixel-by-pixel approach, with 1.3-3.3% time cost and 11.4~79.0% curve-fit residual.

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

Join Here