Multi-Slice Dense-Sparse Learning for Efficient Liver and Tumor Segmentation

Multi-Slice Dense-Sparse Learning for Efficient Liver and Tumor Segmentation

2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

10.1109/EMBC46164.2021.9629698

https://doi.org/10.1109/embc46164.2021.9629698

Ziyuan Zhao, Zeyu Ma, Yanjie Liu, Zeng Zeng, Pierce KH Chow

deep learning, deep convolutional neural networks, Medical image segmentation

09 December 2021

Zhao, Z., Ma, Z., Liu, Y., Zeng, Z., & Chow, P. K. (2021). Multi-Slice Dense-Sparse Learning for Efficient Liver and Tumor Segmentation. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). doi:10.1109/embc46164.2021.9629698

Accurate automatic liver and tumor segmentation plays a vital role in treatment planning and disease monitoring. Recently, deep convolutional neural network (DCNNs) has obtained tremendous success in 2D and 3D medical image segmentation. However, 2D DCNNs cannot fully leverage the inter-slice information, while 3D DCNNs are computationally expensive and memory intensive. To address these issues, we first propose a novel dense-sparse training flow from a data perspective, in which, densely adjacent slices and sparsely adjacent slices are extracted as inputs for regularizing DCNNs, thereby improving the model performance. Moreover, we design a 2.5D light-weight nnU-Net from a network perspective, in which, depthwise separable convolutions are adopted to improve the efficiency. Extensive experiments on the LiTS dataset have demonstrated the superiority of the proposed method.Clinical relevance— The proposed method can effectively segment livers and tumors from CT scans with low complexity, which can be easily implemented into clinical practice.

Publisher Copyright

This research is supported by core funding from: Institute for Infocomm Research
Grant Reference no. :

© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/18080

2694-0604
2375-7477

978-1-7281-1179-7
978-1-7281-1178-0
978-1-7281-1180-3

Institute for Infocomm Research