Deep learning algorithm for automated segmentation and volume measurement of the liver and spleen using portal venous phase computed tomography images

Yura Ahn; Jee Seok Yoon; Seung Soo Lee; Heung Il Suk; Jung Hee Son; Yu Sub Sung; Yedaun Lee; Bo Kyeong Kang; Ho Sung Kim

doi:10.3348/kjr.2020.0237

Deep learning algorithm for automated segmentation and volume measurement of the liver and spleen using portal venous phase computed tomography images

Yura Ahn, Jee Seok Yoon, Seung Soo Lee, Heung Il Suk, Jung Hee Son, Yu Sub Sung, Yedaun Lee, Bo Kyeong Kang, Ho Sung Kim

Research output: Contribution to journal › Article › peer-review

49 Citations (Scopus)

Abstract

Objective: Measurement of the liver and spleen volumes has clinical implications. Although computed tomography (CT) volumetry is considered to be the most reliable noninvasive method for liver and spleen volume measurement, it has limited application in clinical practice due to its time-consuming segmentation process. We aimed to develop and validate a deep learning algorithm (DLA) for fully automated liver and spleen segmentation using portal venous phase CT images in various liver conditions. Materials and Methods: A DLA for liver and spleen segmentation was trained using a development dataset of portal venous CT images from 813 patients. Performance of the DLA was evaluated in two separate test datasets: dataset-1 which included 150 CT examinations in patients with various liver conditions (i.e., healthy liver, fatty liver, chronic liver disease, cirrhosis, and post-hepatectomy) and dataset-2 which included 50 pairs of CT examinations performed at ours and other institutions. The performance of the DLA was evaluated using the dice similarity score (DSS) for segmentation and Bland-Altman 95% limits of agreement (LOA) for measurement of the volumetric indices, which was compared with that of ground truth manual segmentation. Results: In test dataset-1, the DLA achieved a mean DSS of 0.973 and 0.974 for liver and spleen segmentation, respectively, with no significant difference in DSS across different liver conditions (p = 0.60 and 0.26 for the liver and spleen, respectively). For the measurement of volumetric indices, the Bland-Altman 95% LOA was-0.17 ± 3.07% for liver volume and-0.56 ± 3.78% for spleen volume. In test dataset-2, DLA performance using CT images obtained at outside institutions and our institution was comparable for liver (DSS, 0.982 vs. 0.983; p = 0.28) and spleen (DSS, 0.969 vs. 0.968; p = 0.41) segmentation. Conclusion: The DLA enabled highly accurate segmentation and volume measurement of the liver and spleen using portal venous phase CT images of patients with various liver conditions.

Original language	English
Pages (from-to)	987-997
Number of pages	11
Journal	Korean journal of radiology
Volume	21
Issue number	8
DOIs	https://doi.org/10.3348/kjr.2020.0237
Publication status	Published - 2020 Aug

Bibliographical note

Funding Information:
Received: March 6, 2020 Revised: May 6, 2020 Accepted: May 11, 2020 This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1F1A1048826) and the Bio and Medical Technology Development Program of the NRF, which is funded by the Ministry of Science and ICT (NRF-2016M3A9A7918706). *These authors contributed equally to this work. Corresponding author: Seung Soo Lee, MD, PhD, Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Korea. • E-mail: [email protected]; and Heung-Il Suk, PhD, Department of Artificial Intelligence, Department of Brain and Cognitive Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Korea. • E-mail: [email protected] This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https:// creativecommons.org/licenses/by-nc/4.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Funding Information:
This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1F1A1048826) and the Bio and Medical Technology Development Program of the NRF, which is funded by the Ministry of Science and ICT (NRF-2016M3A9A7918706).Acknowledgments Seung Soo Lee was responsible for the clinical study, and Heung-Il Suk was responsible for the development of the deep learning algorithm. Both authors contributed equally to this study and assume the role of corresponding authors.

Publisher Copyright:
© 2020 The Korean Society of Radiology.

Keywords

Artificial intelligence
Deep learning
Liver
Segmentation
Spleen
Volumetry

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging

Access to Document

10.3348/kjr.2020.0237

Cite this

@article{8a3de2f07eff4ecf89b729900152049d,

title = "Deep learning algorithm for automated segmentation and volume measurement of the liver and spleen using portal venous phase computed tomography images",

abstract = "Objective: Measurement of the liver and spleen volumes has clinical implications. Although computed tomography (CT) volumetry is considered to be the most reliable noninvasive method for liver and spleen volume measurement, it has limited application in clinical practice due to its time-consuming segmentation process. We aimed to develop and validate a deep learning algorithm (DLA) for fully automated liver and spleen segmentation using portal venous phase CT images in various liver conditions. Materials and Methods: A DLA for liver and spleen segmentation was trained using a development dataset of portal venous CT images from 813 patients. Performance of the DLA was evaluated in two separate test datasets: dataset-1 which included 150 CT examinations in patients with various liver conditions (i.e., healthy liver, fatty liver, chronic liver disease, cirrhosis, and post-hepatectomy) and dataset-2 which included 50 pairs of CT examinations performed at ours and other institutions. The performance of the DLA was evaluated using the dice similarity score (DSS) for segmentation and Bland-Altman 95% limits of agreement (LOA) for measurement of the volumetric indices, which was compared with that of ground truth manual segmentation. Results: In test dataset-1, the DLA achieved a mean DSS of 0.973 and 0.974 for liver and spleen segmentation, respectively, with no significant difference in DSS across different liver conditions (p = 0.60 and 0.26 for the liver and spleen, respectively). For the measurement of volumetric indices, the Bland-Altman 95% LOA was-0.17 ± 3.07% for liver volume and-0.56 ± 3.78% for spleen volume. In test dataset-2, DLA performance using CT images obtained at outside institutions and our institution was comparable for liver (DSS, 0.982 vs. 0.983; p = 0.28) and spleen (DSS, 0.969 vs. 0.968; p = 0.41) segmentation. Conclusion: The DLA enabled highly accurate segmentation and volume measurement of the liver and spleen using portal venous phase CT images of patients with various liver conditions.",

keywords = "Artificial intelligence, Deep learning, Liver, Segmentation, Spleen, Volumetry",

author = "Yura Ahn and Yoon, {Jee Seok} and Lee, {Seung Soo} and Suk, {Heung Il} and Son, {Jung Hee} and Sung, {Yu Sub} and Yedaun Lee and Kang, {Bo Kyeong} and Kim, {Ho Sung}",

note = "Funding Information: Received: March 6, 2020 Revised: May 6, 2020 Accepted: May 11, 2020 This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1F1A1048826) and the Bio and Medical Technology Development Program of the NRF, which is funded by the Ministry of Science and ICT (NRF-2016M3A9A7918706). *These authors contributed equally to this work. Corresponding author: Seung Soo Lee, MD, PhD, Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Korea. • E-mail: [email protected]; and Heung-Il Suk, PhD, Department of Artificial Intelligence, Department of Brain and Cognitive Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Korea. • E-mail: [email protected] This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https:// creativecommons.org/licenses/by-nc/4.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. Funding Information: This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1F1A1048826) and the Bio and Medical Technology Development Program of the NRF, which is funded by the Ministry of Science and ICT (NRF-2016M3A9A7918706).Acknowledgments Seung Soo Lee was responsible for the clinical study, and Heung-Il Suk was responsible for the development of the deep learning algorithm. Both authors contributed equally to this study and assume the role of corresponding authors. Publisher Copyright: {\textcopyright} 2020 The Korean Society of Radiology.",

year = "2020",

month = aug,

doi = "10.3348/kjr.2020.0237",

language = "English",

volume = "21",

pages = "987--997",

journal = "Korean journal of radiology",

issn = "1229-6929",

publisher = "Korean Radiological Society",

number = "8",

}

TY - JOUR

T1 - Deep learning algorithm for automated segmentation and volume measurement of the liver and spleen using portal venous phase computed tomography images

AU - Ahn, Yura

AU - Yoon, Jee Seok

AU - Lee, Seung Soo

AU - Suk, Heung Il

AU - Son, Jung Hee

AU - Sung, Yu Sub

AU - Lee, Yedaun

AU - Kang, Bo Kyeong

AU - Kim, Ho Sung

N1 - Funding Information: Received: March 6, 2020 Revised: May 6, 2020 Accepted: May 11, 2020 This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1F1A1048826) and the Bio and Medical Technology Development Program of the NRF, which is funded by the Ministry of Science and ICT (NRF-2016M3A9A7918706). *These authors contributed equally to this work. Corresponding author: Seung Soo Lee, MD, PhD, Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Korea. • E-mail: [email protected]; and Heung-Il Suk, PhD, Department of Artificial Intelligence, Department of Brain and Cognitive Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Korea. • E-mail: [email protected] This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https:// creativecommons.org/licenses/by-nc/4.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. Funding Information: This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1F1A1048826) and the Bio and Medical Technology Development Program of the NRF, which is funded by the Ministry of Science and ICT (NRF-2016M3A9A7918706).Acknowledgments Seung Soo Lee was responsible for the clinical study, and Heung-Il Suk was responsible for the development of the deep learning algorithm. Both authors contributed equally to this study and assume the role of corresponding authors. Publisher Copyright: © 2020 The Korean Society of Radiology.

PY - 2020/8

Y1 - 2020/8

N2 - Objective: Measurement of the liver and spleen volumes has clinical implications. Although computed tomography (CT) volumetry is considered to be the most reliable noninvasive method for liver and spleen volume measurement, it has limited application in clinical practice due to its time-consuming segmentation process. We aimed to develop and validate a deep learning algorithm (DLA) for fully automated liver and spleen segmentation using portal venous phase CT images in various liver conditions. Materials and Methods: A DLA for liver and spleen segmentation was trained using a development dataset of portal venous CT images from 813 patients. Performance of the DLA was evaluated in two separate test datasets: dataset-1 which included 150 CT examinations in patients with various liver conditions (i.e., healthy liver, fatty liver, chronic liver disease, cirrhosis, and post-hepatectomy) and dataset-2 which included 50 pairs of CT examinations performed at ours and other institutions. The performance of the DLA was evaluated using the dice similarity score (DSS) for segmentation and Bland-Altman 95% limits of agreement (LOA) for measurement of the volumetric indices, which was compared with that of ground truth manual segmentation. Results: In test dataset-1, the DLA achieved a mean DSS of 0.973 and 0.974 for liver and spleen segmentation, respectively, with no significant difference in DSS across different liver conditions (p = 0.60 and 0.26 for the liver and spleen, respectively). For the measurement of volumetric indices, the Bland-Altman 95% LOA was-0.17 ± 3.07% for liver volume and-0.56 ± 3.78% for spleen volume. In test dataset-2, DLA performance using CT images obtained at outside institutions and our institution was comparable for liver (DSS, 0.982 vs. 0.983; p = 0.28) and spleen (DSS, 0.969 vs. 0.968; p = 0.41) segmentation. Conclusion: The DLA enabled highly accurate segmentation and volume measurement of the liver and spleen using portal venous phase CT images of patients with various liver conditions.

AB - Objective: Measurement of the liver and spleen volumes has clinical implications. Although computed tomography (CT) volumetry is considered to be the most reliable noninvasive method for liver and spleen volume measurement, it has limited application in clinical practice due to its time-consuming segmentation process. We aimed to develop and validate a deep learning algorithm (DLA) for fully automated liver and spleen segmentation using portal venous phase CT images in various liver conditions. Materials and Methods: A DLA for liver and spleen segmentation was trained using a development dataset of portal venous CT images from 813 patients. Performance of the DLA was evaluated in two separate test datasets: dataset-1 which included 150 CT examinations in patients with various liver conditions (i.e., healthy liver, fatty liver, chronic liver disease, cirrhosis, and post-hepatectomy) and dataset-2 which included 50 pairs of CT examinations performed at ours and other institutions. The performance of the DLA was evaluated using the dice similarity score (DSS) for segmentation and Bland-Altman 95% limits of agreement (LOA) for measurement of the volumetric indices, which was compared with that of ground truth manual segmentation. Results: In test dataset-1, the DLA achieved a mean DSS of 0.973 and 0.974 for liver and spleen segmentation, respectively, with no significant difference in DSS across different liver conditions (p = 0.60 and 0.26 for the liver and spleen, respectively). For the measurement of volumetric indices, the Bland-Altman 95% LOA was-0.17 ± 3.07% for liver volume and-0.56 ± 3.78% for spleen volume. In test dataset-2, DLA performance using CT images obtained at outside institutions and our institution was comparable for liver (DSS, 0.982 vs. 0.983; p = 0.28) and spleen (DSS, 0.969 vs. 0.968; p = 0.41) segmentation. Conclusion: The DLA enabled highly accurate segmentation and volume measurement of the liver and spleen using portal venous phase CT images of patients with various liver conditions.

KW - Artificial intelligence

KW - Deep learning

KW - Liver

KW - Segmentation

KW - Spleen

KW - Volumetry

UR - http://www.scopus.com/inward/record.url?scp=85088156741&partnerID=8YFLogxK

U2 - 10.3348/kjr.2020.0237

DO - 10.3348/kjr.2020.0237

M3 - Article

C2 - 32677383

AN - SCOPUS:85088156741

SN - 1229-6929

VL - 21

SP - 987

EP - 997

JO - Korean journal of radiology

JF - Korean journal of radiology

IS - 8

ER -

Deep learning algorithm for automated segmentation and volume measurement of the liver and spleen using portal venous phase computed tomography images

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this