Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT

Ziyang Wang; Irina Voiculescu

doi:10.1109/EMBC46164.2021.9629904

Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT

Ziyang Wang^*
, Irina Voiculescu

^*Corresponding author for this work

University of Oxford

Research output: Chapter in Book/Published conference output › Conference publication

27 Citations (Scopus)

Abstract

COVID-19, a new strain of coronavirus disease, has been one of the most serious and infectious disease in the world. Chest CT is essential in prognostication, diagnosing this disease, and assessing the complication. In this paper, a multi-class COVID-19 CT segmentation is proposed aiming at helping radiologists estimate the extent of effected lung volume. We utilized four augmented pyramid networks on an encoder-decoder segmentation framework. Quadruple Augmented Pyramid Network (QAP-Net) not only enable CNN capture features from variation size of CT images, but also act as spatial inter-connections and down-sampling to transfer sufficient feature information for semantic segmentation. Experimental results achieve competitive performance in segmentation with the Dice of 0.8163, which outperforms other state-of-the-art methods, demonstrating the proposed framework can segment of consolidation as well as glass, ground area via COVID-19 chest CT efficiently and accurately.

Original language	English
Title of host publication	2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Publisher	IEEE
Pages	2956-2959
Number of pages	4
ISBN (Electronic)	9781728111797
DOIs	https://doi.org/10.1109/EMBC46164.2021.9629904
Publication status	Published - 9 Dec 2021
Event	43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021 - Virtual, Online, Mexico Duration: 1 Nov 2021 → 5 Nov 2021

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Electronic)	2694-0604

Conference

Conference	43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
Country/Territory	Mexico
City	Virtual, Online
Period	1/11/21 → 5/11/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Computed Tomography
COVID-19
Image Segmentation
Spatial Pyramid Network

Access to Document

10.1109/EMBC46164.2021.9629904

Cite this

Wang, Z., & Voiculescu, I. (2021). Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 2956-2959). (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). IEEE. https://doi.org/10.1109/EMBC46164.2021.9629904

@inproceedings{421b453a0c3e4929b2a97d82231b8361,

title = "Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT",

abstract = "COVID-19, a new strain of coronavirus disease, has been one of the most serious and infectious disease in the world. Chest CT is essential in prognostication, diagnosing this disease, and assessing the complication. In this paper, a multi-class COVID-19 CT segmentation is proposed aiming at helping radiologists estimate the extent of effected lung volume. We utilized four augmented pyramid networks on an encoder-decoder segmentation framework. Quadruple Augmented Pyramid Network (QAP-Net) not only enable CNN capture features from variation size of CT images, but also act as spatial inter-connections and down-sampling to transfer sufficient feature information for semantic segmentation. Experimental results achieve competitive performance in segmentation with the Dice of 0.8163, which outperforms other state-of-the-art methods, demonstrating the proposed framework can segment of consolidation as well as glass, ground area via COVID-19 chest CT efficiently and accurately.",

keywords = "Computed Tomography, COVID-19, Image Segmentation, Spatial Pyramid Network",

author = "Ziyang Wang and Irina Voiculescu",

year = "2021",

month = dec,

day = "9",

doi = "10.1109/EMBC46164.2021.9629904",

language = "English",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

publisher = "IEEE",

pages = "2956--2959",

booktitle = "2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",

address = "United States",

note = "43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021 ; Conference date: 01-11-2021 Through 05-11-2021",

}

Wang, Z & Voiculescu, I 2021, Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT. in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, IEEE, pp. 2956-2959, 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021, Virtual, Online, Mexico, 1/11/21. https://doi.org/10.1109/EMBC46164.2021.9629904

Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT. / Wang, Ziyang; Voiculescu, Irina.
2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2021. p. 2956-2959 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT

AU - Wang, Ziyang

AU - Voiculescu, Irina

PY - 2021/12/9

Y1 - 2021/12/9

N2 - COVID-19, a new strain of coronavirus disease, has been one of the most serious and infectious disease in the world. Chest CT is essential in prognostication, diagnosing this disease, and assessing the complication. In this paper, a multi-class COVID-19 CT segmentation is proposed aiming at helping radiologists estimate the extent of effected lung volume. We utilized four augmented pyramid networks on an encoder-decoder segmentation framework. Quadruple Augmented Pyramid Network (QAP-Net) not only enable CNN capture features from variation size of CT images, but also act as spatial inter-connections and down-sampling to transfer sufficient feature information for semantic segmentation. Experimental results achieve competitive performance in segmentation with the Dice of 0.8163, which outperforms other state-of-the-art methods, demonstrating the proposed framework can segment of consolidation as well as glass, ground area via COVID-19 chest CT efficiently and accurately.

AB - COVID-19, a new strain of coronavirus disease, has been one of the most serious and infectious disease in the world. Chest CT is essential in prognostication, diagnosing this disease, and assessing the complication. In this paper, a multi-class COVID-19 CT segmentation is proposed aiming at helping radiologists estimate the extent of effected lung volume. We utilized four augmented pyramid networks on an encoder-decoder segmentation framework. Quadruple Augmented Pyramid Network (QAP-Net) not only enable CNN capture features from variation size of CT images, but also act as spatial inter-connections and down-sampling to transfer sufficient feature information for semantic segmentation. Experimental results achieve competitive performance in segmentation with the Dice of 0.8163, which outperforms other state-of-the-art methods, demonstrating the proposed framework can segment of consolidation as well as glass, ground area via COVID-19 chest CT efficiently and accurately.

KW - Computed Tomography

KW - COVID-19

KW - Image Segmentation

KW - Spatial Pyramid Network

UR - https://ieeexplore.ieee.org/document/9629904

UR - https://www.scopus.com/pages/publications/85122526590

U2 - 10.1109/EMBC46164.2021.9629904

DO - 10.1109/EMBC46164.2021.9629904

M3 - Conference publication

C2 - 34891865

AN - SCOPUS:85122526590

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 2956

EP - 2959

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

PB - IEEE

T2 - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021

Y2 - 1 November 2021 through 5 November 2021

ER -

Wang Z, Voiculescu I. Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE. 2021. p. 2956-2959. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC46164.2021.9629904

Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this