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
Review
. 2021 Nov 22:2021:7265644.
doi: 10.1155/2021/7265644. eCollection 2021.

The Progress of Medical Image Semantic Segmentation Methods for Application in COVID-19 Detection

Amin Valizadeh  1 , Morteza Shariatee  2
Affiliations
Review

The Progress of Medical Image Semantic Segmentation Methods for Application in COVID-19 Detection

Amin Valizadeh et al. Comput Intell Neurosci. .

Abstract

Image medical semantic segmentation has been employed in various areas, including medical imaging, computer vision, and intelligent transportation. In this study, the method of semantic segmenting images is split into two sections: the method of the deep neural network and previous traditional method. The traditional method and the published dataset for segmentation are reviewed in the first step. The presented aspects, including all-convolution network, sampling methods, FCN connector with CRF methods, extended convolutional neural network methods, improvements in network structure, pyramid methods, multistage and multifeature methods, supervised methods, semiregulatory methods, and nonregulatory methods, are then thoroughly explored in current methods based on the deep neural network. Finally, a general conclusion on the use of developed advances based on deep neural network concepts in semantic segmentation is presented.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Examples of ADE20K data images. From left to right and from top to bottom, the first segmentation of object masks is seen. The second to fifth elements of photo segmentation are linked to the object's portions (e.g., body parts, glass parts, and photo board parts). In the sixth segment, parts of the head are displayed (such as the eyes, mouth, and nose) [17].
Figure 2
Figure 2
One of the images in the Cityscapes database [17].
Figure 3
Figure 3
Example of BraTS dataset [24].
Figure 4
Figure 4
Sample image of normal and malignant tumor based on MIAS dataset [25].
Figure 5
Figure 5
Model of artificial neurons [80].
Figure 6
Figure 6
An example of a model of an artificial neural network [85].
Figure 7
Figure 7
FCN architecture [87].
Figure 8
Figure 8
Convolution decomposition network architecture [91].
Figure 9
Figure 9
An example of an available convolution structure (Atrous convolution or hole convolution). (a) Convolution layer with 3 × 3 core size; a normal displacement operation with expansion parameter-1, (b) open convolution with expansion parameter-2, and (c) open convolution with expansion parameter-3 [95].
Figure 10
Figure 10
Three levels of the image pyramid [109].
Figure 11
Figure 11
Image pyramid used in CNN structure [112].
Figure 12
Figure 12
ASPP architecture (distance in convolution is not shown as the real rate in this image) [15].
Figure 13
Figure 13
Demonstration of the structure of a pyramidal pooling [116].
Figure 14
Figure 14
The structure adopted as hypercolumns [124].
Figure 15
Figure 15
(a) Radiographic images of a healthy person's chest. (b) Chest radiographs of patients with COVID-19 [143].
See this image and copyright information in PMC

References

    1. Thoma M. A survey of semantic segmentation. 2016. http://arxiv.org/abs/1602.06541 .
    1. Rezaei M., Farahanipad F., Dillhoff A., Elmasri R., Athitsos V. Weakly-supervised hand part segmentation from depth images. Proceedings of the 14th PErvasive Technologies Related to Assistive Environments Conference; June 2021; Corfu, Greece. pp. 218–225. - DOI
    1. Li Y., Qi H., Dai J., Ji X., Wei Y. Fully convolutional instance-aware semantic segmentation. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition; July 2017; Honolulu, HI, USA. pp. 4438–4446. - DOI
    1. Maldonado-Bascon S., Lafuente-Arroyo S., Gil-Jimenez P., Gomez-Moreno H., Lopez-Ferreras F. Road-sign detection and recognition based on support vector machines. IEEE Transactions on Intelligent Transportation Systems . 2007;8(2):264–278. doi: 10.1109/TITS.2007.895311. - DOI
    1. Cohen A., Rivlin E., Shimshoni I., Sabo E. Memory based active contour algorithm using pixel-level classified images for colon crypt segmentation. Computerized Medical Imaging and Graphics . 2015;43:150–164. doi: 10.1016/j.compmedimag.2014.12.006. - DOI - PubMed