Memory-efficient Segmentation of High-resolution Volumetric MicroCT Images

Yuan Wang, Laura Blackie, Irene Miguel-Aliaga, Wenjia Bai
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1322-1335, 2022.

Abstract

In recent years, 3D convolutional neural networks have become the dominant approach for volumetric medical image segmentation. However, compared to their 2D counterparts, 3D networks introduce substantially more training parameters and higher requirement for the GPU memory. This has become a major limiting factor for designing and training 3D networks for high-resolution volumetric images. In this work, we propose a novel memory-efficient network architecture for 3D high-resolution image segmentation. The network incorporates both global and local features via a two-stage U-net-based cascaded framework and at the first stage, a memory-efficient U-net (meU-net) is developed. The features learnt at the two stages are connected via post-concatenation, which further improves the information flow. The proposed segmentation method is evaluated on an ultra high-resolution microCT dataset with typically 250 million voxels per volume. Experiments show that it outperforms state-of-the-art 3D segmentation methods in terms of both segmentation accuracy and memory efficiency.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-wang22a, title = {Memory-efficient Segmentation of High-resolution Volumetric MicroCT Images}, author = {Wang, Yuan and Blackie, Laura and Miguel-Aliaga, Irene and Bai, Wenjia}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1322--1335}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/wang22a/wang22a.pdf}, url = {https://proceedings.mlr.press/v172/wang22a.html}, abstract = {In recent years, 3D convolutional neural networks have become the dominant approach for volumetric medical image segmentation. However, compared to their 2D counterparts, 3D networks introduce substantially more training parameters and higher requirement for the GPU memory. This has become a major limiting factor for designing and training 3D networks for high-resolution volumetric images. In this work, we propose a novel memory-efficient network architecture for 3D high-resolution image segmentation. The network incorporates both global and local features via a two-stage U-net-based cascaded framework and at the first stage, a memory-efficient U-net (meU-net) is developed. The features learnt at the two stages are connected via post-concatenation, which further improves the information flow. The proposed segmentation method is evaluated on an ultra high-resolution microCT dataset with typically 250 million voxels per volume. Experiments show that it outperforms state-of-the-art 3D segmentation methods in terms of both segmentation accuracy and memory efficiency.} }
Endnote
%0 Conference Paper %T Memory-efficient Segmentation of High-resolution Volumetric MicroCT Images %A Yuan Wang %A Laura Blackie %A Irene Miguel-Aliaga %A Wenjia Bai %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-wang22a %I PMLR %P 1322--1335 %U https://proceedings.mlr.press/v172/wang22a.html %V 172 %X In recent years, 3D convolutional neural networks have become the dominant approach for volumetric medical image segmentation. However, compared to their 2D counterparts, 3D networks introduce substantially more training parameters and higher requirement for the GPU memory. This has become a major limiting factor for designing and training 3D networks for high-resolution volumetric images. In this work, we propose a novel memory-efficient network architecture for 3D high-resolution image segmentation. The network incorporates both global and local features via a two-stage U-net-based cascaded framework and at the first stage, a memory-efficient U-net (meU-net) is developed. The features learnt at the two stages are connected via post-concatenation, which further improves the information flow. The proposed segmentation method is evaluated on an ultra high-resolution microCT dataset with typically 250 million voxels per volume. Experiments show that it outperforms state-of-the-art 3D segmentation methods in terms of both segmentation accuracy and memory efficiency.
APA
Wang, Y., Blackie, L., Miguel-Aliaga, I. & Bai, W.. (2022). Memory-efficient Segmentation of High-resolution Volumetric MicroCT Images. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1322-1335 Available from https://proceedings.mlr.press/v172/wang22a.html.

Related Material