Exploring the Role of Deep Learning in Liver Segmentation

Kuanglan Wang; Kwan Ho Chan; Engui Liu; Yan Liu; Qiang Cao; Guangxu Wang; Yuxin He; Shaoyi (Stephen) Liao; Xinying Chen; Lixin Pu

doi:10.1109/ICIBA56860.2023.10165029

Exploring the Role of Deep Learning in Liver Segmentation

Kuanglan Wang
, Kwan Ho Chan^*
, Engui Liu
, Yan Liu
, Qiang Cao
, Guangxu Wang
, Yuxin He
, Shaoyi (Stephen) Liao
, Xinying Chen
, Lixin Pu

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Delineating a target organ is the procedure known as biomedical segmentation. Liver cancer is the second most common cancer to cause death. The automatic liver segmentation from CT scans is a necessary job for the diagnosis of liver cancer disease. However, because of its irregular form and proximity to other organs, the liver is one of the more challenging organs to segment. For liver segmentation in the current research, datasets with only liver labels are typically used, the model is not resistant to cases involving multiple phases and vendors. AbdomenCT1K is a large and various abdominal CT datasets from 12 medical institutions, including cases with multiple diseases, vendors, and phases. To segment the liver, we use the Dense-UNet trained with AbdomenCT-1K, and it achieved the dice of 0.9271 and NSD of 0.9685. We compare different backbone networks in this research, and the results show that our model is more reliable and performs better than many other deep learning models in the prior study. © 2023 IEEE.

Original language	English
Title of host publication	2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA)
Publisher	IEEE
Pages	839-845
Number of pages	7
ISBN (Electronic)	978-1-6654-9079-5
ISBN (Print)	978-1-6654-9080-1
DOIs	https://doi.org/10.1109/ICIBA56860.2023.10165029
Publication status	Published - 2023
Event	3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA 2023) - Chongqing, China Duration: 26 May 2023 → 28 May 2023 http://www.iciba.org/

Publication series

Name	Proceedings of IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA

Conference

Conference	3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA 2023)
Place	China
City	Chongqing
Period	26/05/23 → 28/05/23
Internet address	http://www.iciba.org/

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

UN SDGs

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

SDG 3 Good Health and Well-being

Research Keywords

AbdomenCT-1K
Dense-UNet
image preprocessing
liver segmentation

Access Output

10.1109/ICIBA56860.2023.10165029

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Wang, K., Chan, K. H., Liu, E., Liu, Y., Cao, Q., Wang, G., He, Y., Liao, S., Chen, X., & Pu, L. (2023). Exploring the Role of Deep Learning in Liver Segmentation. In 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) (pp. 839-845). (Proceedings of IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA). IEEE. https://doi.org/10.1109/ICIBA56860.2023.10165029

@inproceedings{8bd5e6fb940c4d2396ce75278aec8385,

title = "Exploring the Role of Deep Learning in Liver Segmentation",

abstract = "Delineating a target organ is the procedure known as biomedical segmentation. Liver cancer is the second most common cancer to cause death. The automatic liver segmentation from CT scans is a necessary job for the diagnosis of liver cancer disease. However, because of its irregular form and proximity to other organs, the liver is one of the more challenging organs to segment. For liver segmentation in the current research, datasets with only liver labels are typically used, the model is not resistant to cases involving multiple phases and vendors. AbdomenCT1K is a large and various abdominal CT datasets from 12 medical institutions, including cases with multiple diseases, vendors, and phases. To segment the liver, we use the Dense-UNet trained with AbdomenCT-1K, and it achieved the dice of 0.9271 and NSD of 0.9685. We compare different backbone networks in this research, and the results show that our model is more reliable and performs better than many other deep learning models in the prior study. {\textcopyright} 2023 IEEE.",

keywords = "AbdomenCT-1K, Dense-UNet, image preprocessing, liver segmentation",

author = "Kuanglan Wang and Chan, \{Kwan Ho\} and Engui Liu and Yan Liu and Qiang Cao and Guangxu Wang and Yuxin He and Liao, \{Shaoyi (Stephen)\} and Xinying Chen and Lixin Pu",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).; 3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA 2023) ; Conference date: 26-05-2023 Through 28-05-2023",

year = "2023",

doi = "10.1109/ICIBA56860.2023.10165029",

language = "English",

isbn = "978-1-6654-9080-1",

series = "Proceedings of IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA",

publisher = "IEEE",

pages = "839--845",

booktitle = "2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA)",

address = "United States",

url = "http://www.iciba.org/",

}

Wang, K, Chan, KH, Liu, E, Liu, Y , Cao, Q , Wang, G , He, Y , Liao, S, Chen, X & Pu, L 2023, Exploring the Role of Deep Learning in Liver Segmentation. in 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA). Proceedings of IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA, IEEE, pp. 839-845, 3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA 2023), Chongqing, China, 26/05/23. https://doi.org/10.1109/ICIBA56860.2023.10165029

Exploring the Role of Deep Learning in Liver Segmentation. / Wang, Kuanglan; Chan, Kwan Ho; Liu, Engui et al.
2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA). IEEE, 2023. p. 839-845 (Proceedings of IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Exploring the Role of Deep Learning in Liver Segmentation

AU - Wang, Kuanglan

AU - Chan, Kwan Ho

AU - Liu, Engui

AU - Liu, Yan

AU - Cao, Qiang

AU - Wang, Guangxu

AU - He, Yuxin

AU - Liao, Shaoyi (Stephen)

AU - Chen, Xinying

AU - Pu, Lixin

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

PY - 2023

Y1 - 2023

N2 - Delineating a target organ is the procedure known as biomedical segmentation. Liver cancer is the second most common cancer to cause death. The automatic liver segmentation from CT scans is a necessary job for the diagnosis of liver cancer disease. However, because of its irregular form and proximity to other organs, the liver is one of the more challenging organs to segment. For liver segmentation in the current research, datasets with only liver labels are typically used, the model is not resistant to cases involving multiple phases and vendors. AbdomenCT1K is a large and various abdominal CT datasets from 12 medical institutions, including cases with multiple diseases, vendors, and phases. To segment the liver, we use the Dense-UNet trained with AbdomenCT-1K, and it achieved the dice of 0.9271 and NSD of 0.9685. We compare different backbone networks in this research, and the results show that our model is more reliable and performs better than many other deep learning models in the prior study. © 2023 IEEE.

AB - Delineating a target organ is the procedure known as biomedical segmentation. Liver cancer is the second most common cancer to cause death. The automatic liver segmentation from CT scans is a necessary job for the diagnosis of liver cancer disease. However, because of its irregular form and proximity to other organs, the liver is one of the more challenging organs to segment. For liver segmentation in the current research, datasets with only liver labels are typically used, the model is not resistant to cases involving multiple phases and vendors. AbdomenCT1K is a large and various abdominal CT datasets from 12 medical institutions, including cases with multiple diseases, vendors, and phases. To segment the liver, we use the Dense-UNet trained with AbdomenCT-1K, and it achieved the dice of 0.9271 and NSD of 0.9685. We compare different backbone networks in this research, and the results show that our model is more reliable and performs better than many other deep learning models in the prior study. © 2023 IEEE.

KW - AbdomenCT-1K

KW - Dense-UNet

KW - image preprocessing

KW - liver segmentation

UR - https://www.scopus.com/pages/publications/85166030169

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85166030169&origin=recordpage

U2 - 10.1109/ICIBA56860.2023.10165029

DO - 10.1109/ICIBA56860.2023.10165029

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-1-6654-9080-1

T3 - Proceedings of IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA

SP - 839

EP - 845

BT - 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA)

PB - IEEE

T2 - 3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA 2023)

Y2 - 26 May 2023 through 28 May 2023

ER -

Wang K, Chan KH, Liu E, Liu Y , Cao Q , Wang G et al. Exploring the Role of Deep Learning in Liver Segmentation. In 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA). IEEE. 2023. p. 839-845. (Proceedings of IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA). Epub 2023 Jul 6. doi: 10.1109/ICIBA56860.2023.10165029

Exploring the Role of Deep Learning in Liver Segmentation

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this