Meeting Banner
Abstract #1858

A Convolutional Neural Network for Accelerating the Computation of the Extended Tofts Model in DCE-MRI

Ke Fang1, Zejun Wang2,3, Zhaoqing Li2,3, Bao Wang4, Guangxu Han2,3, Zhaowei Cheng1, Zhihong Chen1, Chuanjin Lan5, Yi Zhang6, Peng Zhao7, Xinyu Jin1, Yingchao Liu8, and Ruiliang Bai2,3
1College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, China, 2Department of Physical Medicine and Rehabilitation of The Affiliated Sir Run Run Shaw Hospital AND Interdisciplinary Institute of Neuroscience and Technology, School of Medicine, Zhejiang University, Hangzhou, China, 3Key Laboratory of Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China, 4Department of Radiology, Qilu Hospital of Shandong University, Jinan, China, 5School of Medicine, Shandong University, Jinan, China, 6Shandong Medical Imaging Research Institute, Shandong University, Jinan, China, 7Department of Neurosurgery, Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China, 8Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China

We proposed a customized conventional neural network (CNN) to fasten the computation time of non-linear pharmacokinetic models in DCE-MRI. The results demonstrated that the CNN could shorten the computation time of extended Tofts model of whole-brain data to less than a minute without sacrificing the agreements with conventional non-linear least square (NLLS) fitting. This CNN could serve as an alternative to conventional NLLS fitting for fast assessment of pharmacokinetic parameters in clinical practice.

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

Join Here