Cross Attention Squeeze Excitation Network (CASE-Net) for Whole Body Fetal MRI Segmentation
Justin Lo,
Saiee Nithiyanantham,
Jillian Cardinell,
Dylan Young,
Sherwin Cho,
Abirami Kirubarajan,
Matthias W. Wagner,
Roxana Azma,
Steven Miller,
Mike Seed,
Birgit Ertl-Wagner,
Dafna Sussman
Affiliations
Justin Lo
Department of Electrical, Computer and Biomedical Engineering, Faculty of Engineering and Architectural Science, Ryerson University, Toronto, ON M5B 2K3, Canada
Saiee Nithiyanantham
Department of Electrical, Computer and Biomedical Engineering, Faculty of Engineering and Architectural Science, Ryerson University, Toronto, ON M5B 2K3, Canada
Jillian Cardinell
Department of Electrical, Computer and Biomedical Engineering, Faculty of Engineering and Architectural Science, Ryerson University, Toronto, ON M5B 2K3, Canada
Dylan Young
Department of Electrical, Computer and Biomedical Engineering, Faculty of Engineering and Architectural Science, Ryerson University, Toronto, ON M5B 2K3, Canada
Sherwin Cho
Institute for Biomedical Engineering, Science and Technology (iBEST), Ryerson University, St. Michael’s Hospital, Toronto, ON M5B 2K3, Canada
Abirami Kirubarajan
Faculty of Medicine, University of Toronto, Toronto, ON M5S 1A8, Canada
Matthias W. Wagner
Division of Neuroradiology, The Hospital for Sick Children, Toronto, ON M5G 1X8, Canada
Roxana Azma
Division of Neuroradiology, The Hospital for Sick Children, Toronto, ON M5G 1X8, Canada
Steven Miller
Division of Neurology, The Hospital for Sick Children, Toronto, ON M5G 1X8, Canada
Mike Seed
Division of Cardiology, The Hospital for Sick Children, Toronto, ON M5G 1X8, Canada
Birgit Ertl-Wagner
Division of Neuroradiology, The Hospital for Sick Children, Toronto, ON M5G 1X8, Canada
Dafna Sussman
Department of Electrical, Computer and Biomedical Engineering, Faculty of Engineering and Architectural Science, Ryerson University, Toronto, ON M5B 2K3, Canada
Segmentation of the fetus from 2-dimensional (2D) magnetic resonance imaging (MRI) can aid radiologists with clinical decision making for disease diagnosis. Machine learning can facilitate this process of automatic segmentation, making diagnosis more accurate and user independent. We propose a deep learning (DL) framework for 2D fetal MRI segmentation using a Cross Attention Squeeze Excitation Network (CASE-Net) for research and clinical applications. CASE-Net is an end-to-end segmentation architecture with relevant modules that are evidence based. The goal of CASE-Net is to emphasize localization of contextual information that is relevant in biomedical segmentation, by combining attention mechanisms with squeeze-and-excitation (SE) blocks. This is a retrospective study with 34 patients. Our experiments have shown that our proposed CASE-Net achieved the highest segmentation Dice score of 87.36%, outperforming other competitive segmentation architectures.
