Abstract #1858

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

Ke Fang¹, Zejun Wang^2,3, Zhaoqing Li^2,3, Bao Wang⁴, Guangxu Han^2,3, Zhaowei Cheng¹, Zhihong Chen¹, Chuanjin Lan⁵, Yi Zhang⁶, Peng Zhao⁷, Xinyu Jin¹, Yingchao Liu⁸, and Ruiliang Bai^2,3

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