Application of Hybrid Network of UNet and Feature Pyramid Network in Spine Segmentation

Xingxing Liu; Wenxiang Deng; Yang Liu

doi:10.1109/MeMeA52024.2021.9478765

Back

Conference proceeding

Application of Hybrid Network of UNet and Feature Pyramid Network in Spine Segmentation

Xingxing Liu, Wenxiang Deng and Yang Liu

2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA), pp.1-6

06/23/2021

DOI: 10.1109/MeMeA52024.2021.9478765

View Online

Abstract

Spine segmentation is a common task for spinal imaging and spinal surgical navigation. Spine segmentation provides valuable information for the diagnosis, and the segmentation output can also serve as an input for downstream surgical navigation. Unfortunately, spine segmentation is a labor-intensive task. In this study, we applied a deep network combining feature pyramid network (FPN) and UNet to the segmentation of vertebral bodies (VBs), referring as Res50_UNet. Compared with the original UNet, Res50_UNet has the following enhancements: 1) five consecutive spine MRI slices and two coordinate maps are concatenated as the input; 2) the convolutional block from ResNet are used; 3) an FPN architecture is applied to extracting rich multi-scale features and obtaining segmentation output. Experiments were conducted on an annotated T2-weighted MRIs of the lower spine dataset. We have benchmarked Res50_UNet against UNet and other UNet based network structures. It was found that Res50_UNet needs the lowest number of epochs (~1000 epochs) to achieve steady-state performance. The accuracy (AC) of Res50_UNet is higher than 99.5% with only 1000 epochs, which is very impressive. This study demonstrated the feasibility of applying Res50_UNet in spine segmentation. The network integrates the characteristics of FPN and UNet. These results have shown the potential for Res50_UNet in spine MRI segmentation, especially when a low number of epochs is desirable.

Computer Vision

Magnetic Resonance Imaging

Navigation

Surgery

Benchmark testing

deep learning

Feature extraction

Image segmentation

medical image processing

Spine

Spine segmentation

Details

Title: Subtitle: Application of Hybrid Network of UNet and Feature Pyramid Network in Spine Segmentation
Creators: Xingxing Liu - University of Iowa
Wenxiang Deng - University of Iowa
Yang Liu - University of Iowa
Resource Type: Conference proceeding
Publication Details: 2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA), pp.1-6
DOI: 10.1109/MeMeA52024.2021.9478765
Publisher: IEEE
Grant note: University of Iowa (10.13039/100008893)
Language: English
Date published: 06/23/2021
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984197218402771

Metrics

42 Record Views

3 Times Cited - Web of Science