Deep segmentation of abdominal organs from MRI: off-the- shelf architectures and improvements

Pedro Furtado

doi:10.1117/12.2580849

15 February 2021 Deep segmentation of abdominal organs from MRI: off-the- shelf architectures and improvements

Pedro Furtado

Proceedings Volume 11596, Medical Imaging 2021: Image Processing; 115963J (2021) https://doi.org/10.1117/12.2580849
Event: SPIE Medical Imaging, 2021, Online Only

Abstract

Deep Learning outperforms prior art in medical imaging tasks. It has been applied to segmentation of Magnetic Resonance Imaging (MRI) scans, where consecutive slices capture relevant body structures for visualization and diagnosis of medical condition. In this work we investigate experimentally the factors that improve segmentation performance of MRI sequences of abdominal organs, including network architecture, pre-training, data augmentation and improvements to loss function. After comparing segmentation network architectures, we choose the best performing one and experimented improvements (data augmentation, training choices). Finally, metrics are fundamental and IoU of each organ in particular, therefore we change loss function to IoU and evaluate the resulting quality. We show that DeepLabV3 is better than competitors by 20 percentage points (pp) or more (depending on the competitor), data augmentation and further enhancements improve performance of DeepLabV3 by 12 percentage points (pp) in average, and that loss function improves performance by up to 13pp as well. Finally, we discuss challenges and further work.

Citation Download Citation

Pedro Furtado "Deep segmentation of abdominal organs from MRI: off-the- shelf architectures and improvements", Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115963J (15 February 2021); https://doi.org/10.1117/12.2580849

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available