Cross Attention Squeeze Excitation Network (CASE-Net) for Whole Body Fetal MRI Segmentation

Sensors

Dylan Young¹  Dafna Sussman¹  Jillian Cardinell¹  Justin Lo¹  Saiee Nithiyanantham¹  Mike Seed²  Steven Miller³  Birgit Ertl-Wagner⁴  Roxana Azma⁴  Matthias W. Wagner⁴  Abirami Kirubarajan⁵  Sherwin Cho⁶ 

[1] Department of Electrical, Computer and Biomedical Engineering, Faculty of Engineering and Architectural Science, Ryerson University, Toronto, ON M5B 2K3, Canada;Division of Cardiology, The Hospital for Sick Children, Toronto, ON M5G 1X8, Canada;Division of Neurology, The Hospital for Sick Children, Toronto, ON M5G 1X8, Canada;Division of Neuroradiology, The Hospital for Sick Children, Toronto, ON M5G 1X8, Canada;Faculty of Medicine, University of Toronto, Toronto, ON M5S 1A8, Canada;Institute for Biomedical Engineering, Science and Technology (iBEST), Ryerson University, St. Michael’s Hospital, Toronto, ON M5B 2K3, Canada;

关键词: deep learning;    fetal MRI;    convolutional neural networks;    automatic segmentation;    squeeze-and-excitation;    attention mechanisms;   

DOI  :  10.3390/s21134490

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown