Upgraded W-Net with Attention Gates and Its Application in Unsupervised 3D Liver Segmentation

Dhanunjaya Mitta, Soumick Chatterjee, Soumick Chatterjee, Soumick Chatterjee, Oliver Speck, Oliver Speck, Oliver Speck, Oliver Speck, Andreas Nürnberger, Andreas Nürnberger

Abstract

Segmentation of biomedical images can assist radiologists to make a better diagnosis and take decisions faster by helping in the detection of abnormalities, such as tumors. Manual or semi-automated segmentation, however, can be a time-consuming task. Most deep learning based automated segmentation methods are supervised and rely on manually segmented ground-truth. A possible solution for the problem would be an unsupervised deep learning based approach for automated segmentation, which this research work tries to address. We use a W-Net architecture and modified it, such that it can be applied to 3D volumes. In addition, to suppress noise in the segmentation we added attention gates to the skip connections. The loss for the segmentation output was calculated using soft N-Cuts and for the reconstruction output using SSIM. Conditional Random Fields were used as a post-processing step to fine-tune the results. The proposed method has shown promising results, with a dice coefficient of 0.88 for the liver segmentation compared against manual segmentation.

Download


Paper Citation


in Harvard Style

Mitta D., Chatterjee S., Speck O. and Nürnberger A. (2021). Upgraded W-Net with Attention Gates and Its Application in Unsupervised 3D Liver Segmentation.In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-486-2, pages 488-494. DOI: 10.5220/0010221504880494


in Bibtex Style

@conference{icpram21,
author={Dhanunjaya Mitta and Soumick Chatterjee and Oliver Speck and Andreas Nürnberger},
title={Upgraded W-Net with Attention Gates and Its Application in Unsupervised 3D Liver Segmentation},
booktitle={Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2021},
pages={488-494},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010221504880494},
isbn={978-989-758-486-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Upgraded W-Net with Attention Gates and Its Application in Unsupervised 3D Liver Segmentation
SN - 978-989-758-486-2
AU - Mitta D.
AU - Chatterjee S.
AU - Speck O.
AU - Nürnberger A.
PY - 2021
SP - 488
EP - 494
DO - 10.5220/0010221504880494