Abstract #0015

Radiomics-based CEST image analysis for improved performance of brain tumor grading

Jibin Tang¹, Hongxi Zhang², Zhipeng Shen³, Wenqi Wang¹, Xingwang Yong¹, Junjie Wen¹, Xinchun Chen², Fengyu Tian², Weibo Chen⁴, Dan Wu¹, and Yi Zhang¹

¹Key Laboratory for Biomedical Engineering of Ministry of Education, Department of Biomedical Engineering, College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou, Zhejiang, China, ²Department of Radiology, Children’s Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China, ³Department of Neurosurgery, Children’s Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China, ⁴Philips Healthcare, Shanghai, China

CEST imaging can detect proteins and metabolites in vivo and has been successfully applied to brain tumor grading. In this work, we implemented a radiomic analysis of the APTw images, which were acquired from 40 patients with 20 confirmed high-grade brain tumors and 20 confirmed low-grade tumors. We established predictive models, assessed their performance, and compared them with conventional average APTw image intensities. The average sensitivity and AUC of the selected radiomic feature models for tumor grading were significantly higher than that of conventional mean APTw signals, demonstrating the advantage of radiomics for diagnosing brain tumors.

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

Join Here