Meeting Banner
Abstract #2279

Fast and Robust Detection of Fetal Brain in MRI using Transfer Learning based FCN

DEFENG WANG1,2, Jinpeng Li2, YISHAN LUO2,3, DANTONG MIAO4, XIN ZHANG4, Queenie Chan5, Winnie CW CHU2, LIN SHI6,7,8, and BING ZHANG4

1Shenzhen Research Institute, The Chinese University of Hong Kong, Shenzhen, People's Republic of China, 2Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Hong Kong, Hong Kong, 3Shenzhen Research Institute,The Chinese University of Hong Kong, Shenzhen, People's Republic of China, 4Department of Radiology, Nanjing Drum Tower Hospital,The Affiliated Hospital of Nanjing University Medical School, Nanjing, People's Republic of China, 5Philips Healthcare, Hong Kong, 6Chow Yuk Ho Technology Center for Innovative Medicine, Hong Kong, 7Therese Pei Fong Chow Research Centre for Prevention of Dementia, 8Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Hong Kong

In this work, we proposed a transfer learning based FCN method which can automatically detect the fetal brain in MRI. We used the off-the-shelf model weights trained on nature images to initialize a fully connected network (FCN), and then fine-tuned the model on the fetal MRIs. We tested our method on two datasets with different MRI sequences, and the results demonstrated that the proposed method is automatic, fast and robust for detection of fetal brain in MRI.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Abstract

Keywords