Meeting Banner
Abstract #1400

Using texture analysis based on T2WI, DWI and delayed T1-enhanced imaging to differentiate benign and malignant soft tissue tumors

Nan Sun1, Cuiping Ren1, Ying Li1, Jingliang Cheng1, and Zhizheng Zhuo2

1Dept. of MRI, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China, 2Philips Healthcare, Beijing, China

With the popularity of magnetic resonance technology in recent years, the detection rate of soft tissue tumors has been greatly improved. The soft tissue tumors in MR images show various signal intensity distribution in different modalities. This work investigated and evaluated the role of texture analysis on T2WI, DWI and delayed T1-enhanced images to characterize the soft tissue tumors, and then evaluate the textures by support vector machine classifiers (SVM) to differentiate benign and malignant soft tissue tumors. Results showed that the application of texture analysis in T2WI, DWI and T1-enhanced imaging is helpful to distinguish benign and malignant soft tissue tumors by SVM.

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

Join Here