Abstract
Convolutional neural networks (CNN) have established state-of-the-art performance in computer vision tasks such as object detection and segmentation. One of the major remaining challenges concerns their ability to capture consistent spatial attributes, especially in medical image segmentation. A way to address this issue is through integrating localization prior into system architecture. The CoordConv layers are extensions of convolutional neural network wherein convolution is conditioned on spatial coordinates. This paper investigates CoordConv as a proficient substitute to convolutional layers for organ segmentation in both fully and weakly supervised settings. Experiments are conducted on two public datasets, SegTHOR, which focuses on the segmentation of thoracic organs at risk in computed tomography (CT) images, and ACDC, which addresses ventricular endocardium segmentation of the heart in MR images. We show that if CoordConv does not significantly increase the accuracy with respect to standard convolution, it may interestingly increase model convergence at almost no additional computational cost.
Original language | English |
---|---|
Title of host publication | 2020 10th International Conference on Image Processing Theory, Tools and Applications, IPTA 2020 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781728187501 |
DOIs | |
Publication status | Published - 9 Nov 2020 |
Externally published | Yes |
Event | 10th International Conference on Image Processing Theory, Tools and Applications, IPTA 2020 - Virtual, Paris, France Duration: 9 Nov 2020 → 12 Nov 2020 |
Publication series
Name | 2020 10th International Conference on Image Processing Theory, Tools and Applications, IPTA 2020 |
---|
Conference
Conference | 10th International Conference on Image Processing Theory, Tools and Applications, IPTA 2020 |
---|---|
Country/Territory | France |
City | Virtual, Paris |
Period | 9/11/20 → 12/11/20 |
Bibliographical note
Funding Information:The authors would like to acknowledge the National Council for Scientific Research of Lebanon (CNRS-L) and the Agence Franc¸aise de la Francophonie (AUF) for granting a doctoral fellowship to Rosana El Jurdi, as well as the ANR (Project APi, grant ANR-18-CE23-0014).
Publisher Copyright:
© 2020 IEEE.
Keywords
- CoordConv
- CT
- Fully Convolutional Networks
- Image segmentation
- Location Prior
- MRI
- Weakly Supervised Learning