Meeting Banner
Abstract #0979

Explainable artificial intelligence for automatic detection of early nasopharyngeal carcinoma on MRI

Lun M Wong1, Qi-Yong H Ai1,2, Tiffany Y So1, Jacky WK Lam3,4, and Ann D King1
1Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Hong Kong, Hong Kong, 2Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, Hong Kong, 3Department of Chemical Pathology, The Chinese University of Hong Kong, Hong Kong, Hong Kong, 4State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong, Hong Kong

Synopsis

Keywords: Machine Learning/Artificial Intelligence, Screening, XAI, explainability, deep learningIn this study, we propose a simple method to improve the explainability of artificial intelligence, specifically convolutional neural networks (CNNs), for the automatic detection of early nasopharyngeal carcinoma (NPC) on magnetic resonance imaging (MRI). We show a long-short-term-memory (LSTM) unit can be introduced into a CNN to read 3-dimensional medical image series. A risk curve can be extracted from the LSTM to visualize the “thought process” of the network when it reads through the input MRI slice-by-slice. This modification improves the explainability of the network without reducing performance for the early NPC detections of the original CNN.

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.

Keywords