Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Feb 7;21(4):1167.
doi: 10.3390/s21041167.

Deep Neural Network-Based Semantic Segmentation of Microvascular Decompression Images

Ruifeng Bai  1   2 , Shan Jiang  1 , Haijiang Sun  1 , Yifan Yang  1   2 , Guiju Li  1
Affiliations

Deep Neural Network-Based Semantic Segmentation of Microvascular Decompression Images

Ruifeng Bai et al. Sensors (Basel). .

Abstract

Image semantic segmentation has been applied more and more widely in the fields of satellite remote sensing, medical treatment, intelligent transportation, and virtual reality. However, in the medical field, the study of cerebral vessel and cranial nerve segmentation based on true-color medical images is in urgent need and has good research and development prospects. We have extended the current state-of-the-art semantic-segmentation network DeepLabv3+ and used it as the basic framework. First, the feature distillation block (FDB) was introduced into the encoder structure to refine the extracted features. In addition, the atrous spatial pyramid pooling (ASPP) module was added to the decoder structure to enhance the retention of feature and boundary information. The proposed model was trained by fine tuning and optimizing the relevant parameters. Experimental results show that the encoder structure has better performance in feature refinement processing, improving target boundary segmentation precision, and retaining more feature information. Our method has a segmentation accuracy of 75.73%, which is 3% better than DeepLabv3+.

Keywords: DeepLabv3+; decoder structure; encoder structure; microvascular decompression image; semantic segmentation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The structure of the semantic-segmentation network for microvascular decompression images.
Figure 2
Figure 2
FDB (feature distillation block).
Figure 3
Figure 3
SRB (shallow residual block).
Figure 4
Figure 4
The Xception model is modified as follows: The second depth-wise separable convolution is replaced by the FDB in the residual block of input flow, middle flow, and exit flow.
Figure 5
Figure 5
Vertical structure of semantic segmentation of microvascular decompression images.
Figure 6
Figure 6
Examples of pre-processing.
Figure 7
Figure 7
Network-model-training loss curve.
Figure 8
Figure 8
Network-model-validation loss curve.
Figure 9
Figure 9
Experimental results and comparison with other methods.
Figure 10
Figure 10
Failure case.
See this image and copyright information in PMC

References

    1. Plis S.M., Hjelm D.R., Salakhutdinov R., Allen E.A., Bockholt H.J., Long J.D., Johnson H.J., Paulsen J.S., Turner J.A., Calhoun V.D. Deep learning for neuroimaging: A validation study. Front. Neurosci. 2014;8:229. doi: 10.3389/fnins.2014.00229. - DOI - PMC - PubMed
    1. Li Q., Cai W., Wang X., Zhou Y., Feng D.D., Chen M. Medical image classification with convolutional neural network; Proceedings of the 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV); Singapore. 10–12 December 2014; pp. 844–848.
    1. Ypsilantis P.P., Siddique M., Sohn H.M., Davies A., Cook G., Goh V., Montana G. Predicting response to neoadjuvant chemotherapy with PET imaging using convolutional neural networks. PLoS ONE. 2015;10:e0137036. doi: 10.1371/journal.pone.0137036. - DOI - PMC - PubMed
    1. Do D.T., Le T.Q., Le N.Q. Using deep neural networks and biological subwords to detect protein S-sulfenylation sites. Brief. Bioinform. 2020 doi: 10.1093/bib/bbaa128. - DOI - PubMed
    1. Turaga S.C., Murray J.F., Jain V., Roth F., Helmstaedter M., Briggman K., Denk W., Seung H.S. Convolutional networks can learn to generate affinity graphs for image segmentation. Neural Comput. 2010;22:511–538. doi: 10.1162/neco.2009.10-08-881. - DOI - PubMed

MeSH terms