SAU-Net: Efficient 3D Spine MRI Segmentation Using Inter-Slice Attention

Yichi Zhang, Lin Yuan, Yujia Wang, Jicong Zhang
; Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:903-913, 2020.

Abstract

Accurate segmentation of spine Magnetic Resonance Imaging (MRI) is highly demanded in morphological research, quantitative analysis, and diseases identification, such as spinal canal stenosis, disc herniation and degeneration. However, accurate spine segmentation is challenging because of the irregular shape, artifacts and large variability between slices. To alleviate these problems, spatial information is used for more continuous and accurate segmentation such as by 3D convolutional neural networks (CNN) . However, 3D CNN suffers from higher computational cost, memory cost and risk of over-fitting, especially for medical images where the number of labeled data is limited. To address these problems, we apply the attention mechanism for the utilization of inter-slice information in 3D segmentation tasks based on 2D convolutional networks and propose a spatial attention-based densely connected U-Net (SAU-Net), which consists of Dense U-Net for extraction of intra-slice features and an inter-slice attention module (ISA) to utilize inter-slice information from adjacent slices and refine the segmentation results. Experimental results demonstrate the effectiveness of ISA as well as higher accuracy and efficiency of segmentation results of our method compared with other deep learning methods.

Cite this Paper


BibTeX
@InProceedings{pmlr-v121-zhang20c, title = {SAU-Net: Efficient 3D Spine MRI Segmentation Using Inter-Slice Attention}, author = {Zhang, Yichi and Yuan, Lin and Wang, Yujia and Zhang, Jicong}, pages = {903--913}, year = {2020}, editor = {Tal Arbel and Ismail Ben Ayed and Marleen de Bruijne and Maxime Descoteaux and Herve Lombaert and Christopher Pal}, volume = {121}, series = {Proceedings of Machine Learning Research}, address = {Montreal, QC, Canada}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/zhang20c/zhang20c.pdf}, url = {http://proceedings.mlr.press/v121/zhang20c.html}, abstract = {Accurate segmentation of spine Magnetic Resonance Imaging (MRI) is highly demanded in morphological research, quantitative analysis, and diseases identification, such as spinal canal stenosis, disc herniation and degeneration. However, accurate spine segmentation is challenging because of the irregular shape, artifacts and large variability between slices. To alleviate these problems, spatial information is used for more continuous and accurate segmentation such as by 3D convolutional neural networks (CNN) . However, 3D CNN suffers from higher computational cost, memory cost and risk of over-fitting, especially for medical images where the number of labeled data is limited. To address these problems, we apply the attention mechanism for the utilization of inter-slice information in 3D segmentation tasks based on 2D convolutional networks and propose a spatial attention-based densely connected U-Net (SAU-Net), which consists of Dense U-Net for extraction of intra-slice features and an inter-slice attention module (ISA) to utilize inter-slice information from adjacent slices and refine the segmentation results. Experimental results demonstrate the effectiveness of ISA as well as higher accuracy and efficiency of segmentation results of our method compared with other deep learning methods.} }
Endnote
%0 Conference Paper %T SAU-Net: Efficient 3D Spine MRI Segmentation Using Inter-Slice Attention %A Yichi Zhang %A Lin Yuan %A Yujia Wang %A Jicong Zhang %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-zhang20c %I PMLR %J Proceedings of Machine Learning Research %P 903--913 %U http://proceedings.mlr.press %V 121 %W PMLR %X Accurate segmentation of spine Magnetic Resonance Imaging (MRI) is highly demanded in morphological research, quantitative analysis, and diseases identification, such as spinal canal stenosis, disc herniation and degeneration. However, accurate spine segmentation is challenging because of the irregular shape, artifacts and large variability between slices. To alleviate these problems, spatial information is used for more continuous and accurate segmentation such as by 3D convolutional neural networks (CNN) . However, 3D CNN suffers from higher computational cost, memory cost and risk of over-fitting, especially for medical images where the number of labeled data is limited. To address these problems, we apply the attention mechanism for the utilization of inter-slice information in 3D segmentation tasks based on 2D convolutional networks and propose a spatial attention-based densely connected U-Net (SAU-Net), which consists of Dense U-Net for extraction of intra-slice features and an inter-slice attention module (ISA) to utilize inter-slice information from adjacent slices and refine the segmentation results. Experimental results demonstrate the effectiveness of ISA as well as higher accuracy and efficiency of segmentation results of our method compared with other deep learning methods.
APA
Zhang, Y., Yuan, L., Wang, Y. & Zhang, J.. (2020). SAU-Net: Efficient 3D Spine MRI Segmentation Using Inter-Slice Attention. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in PMLR 121:903-913

Related Material