Automatic HCC Detection Using Convolutional Network with Multi-Magnification Input Images

Wei Che Huang, Pau-Choo Chung, Hung-Wen Tsai, Nan-Haw Chow, Ying Zong Juang, Hann Huei Tsai, Shih Hsuan Lin, Cheng Hsiung Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Liver cancer postoperative pathologic examination of stained tissues is an important step in identifying prognostic factors for follow-up care. Traditionally, liver cancer detection would be performed by pathologists with observing the entire biological tissue, resulting in heavy work loading and potential misjudgment. Accordingly, the studies of the automatic pathological examination have been popular for a long period of time. Most approaches of the existing cancer detection, however, only extract cell level information based on single-scale high-magnification patch. In liver tissues, common cell change phenomena such as apoptosis, necrosis, and steatosis are similar in tumor and benign. Hence, the detection may fail when the patch only covered the changed cells area that cannot provide enough neighboring cell structure information. To conquer this problem, the convolutional network architecture with multi-magnification input can provide not only the cell level information by referencing high-magnification patches, but also the cell structure information by referencing low-magnification patches. The detection algorithm consists of two main structures: 1) extraction of cell level and cell structure level feature maps from high-magnification and low-magnification images respectively by separate general convolutional networks, and 2) integration of multi-magnification features by fully connected network. In this paper, VGG16 and Inception V4 were applied as the based convolutional network for liver tumor detection task. The experimental results showed that VGG16 based multi-magnification input convolutional network achieved 91% mIOU on HCC tumor detection task. In addition, with comparison between single-scale CNN (SSCN) and multi-scale CNN (MSCN) approaches, the MSCN demonstrated that the multi-scale patches could provide better performance on HCC classification task.

Original languageEnglish
Title of host publicationProceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages194-198
Number of pages5
ISBN (Electronic)9781538678848
DOIs
Publication statusPublished - 2019 Mar 1
Event1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019 - Hsinchu, Taiwan
Duration: 2019 Mar 182019 Mar 20

Publication series

NameProceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

Conference

Conference1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019
CountryTaiwan
CityHsinchu
Period19-03-1819-03-20

Fingerprint

Liver
Tumors
Tissue
Cell death
Network architecture

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Huang, W. C., Chung, P-C., Tsai, H-W., Chow, N-H., Juang, Y. Z., Tsai, H. H., ... Wang, C. H. (2019). Automatic HCC Detection Using Convolutional Network with Multi-Magnification Input Images. In Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019 (pp. 194-198). [8771535] (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AICAS.2019.8771535
Huang, Wei Che ; Chung, Pau-Choo ; Tsai, Hung-Wen ; Chow, Nan-Haw ; Juang, Ying Zong ; Tsai, Hann Huei ; Lin, Shih Hsuan ; Wang, Cheng Hsiung. / Automatic HCC Detection Using Convolutional Network with Multi-Magnification Input Images. Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 194-198 (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019).
@inproceedings{97e941122d2b47209ea396f714a6bc01,
title = "Automatic HCC Detection Using Convolutional Network with Multi-Magnification Input Images",
abstract = "Liver cancer postoperative pathologic examination of stained tissues is an important step in identifying prognostic factors for follow-up care. Traditionally, liver cancer detection would be performed by pathologists with observing the entire biological tissue, resulting in heavy work loading and potential misjudgment. Accordingly, the studies of the automatic pathological examination have been popular for a long period of time. Most approaches of the existing cancer detection, however, only extract cell level information based on single-scale high-magnification patch. In liver tissues, common cell change phenomena such as apoptosis, necrosis, and steatosis are similar in tumor and benign. Hence, the detection may fail when the patch only covered the changed cells area that cannot provide enough neighboring cell structure information. To conquer this problem, the convolutional network architecture with multi-magnification input can provide not only the cell level information by referencing high-magnification patches, but also the cell structure information by referencing low-magnification patches. The detection algorithm consists of two main structures: 1) extraction of cell level and cell structure level feature maps from high-magnification and low-magnification images respectively by separate general convolutional networks, and 2) integration of multi-magnification features by fully connected network. In this paper, VGG16 and Inception V4 were applied as the based convolutional network for liver tumor detection task. The experimental results showed that VGG16 based multi-magnification input convolutional network achieved 91{\%} mIOU on HCC tumor detection task. In addition, with comparison between single-scale CNN (SSCN) and multi-scale CNN (MSCN) approaches, the MSCN demonstrated that the multi-scale patches could provide better performance on HCC classification task.",
author = "Huang, {Wei Che} and Pau-Choo Chung and Hung-Wen Tsai and Nan-Haw Chow and Juang, {Ying Zong} and Tsai, {Hann Huei} and Lin, {Shih Hsuan} and Wang, {Cheng Hsiung}",
year = "2019",
month = "3",
day = "1",
doi = "10.1109/AICAS.2019.8771535",
language = "English",
series = "Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "194--198",
booktitle = "Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019",
address = "United States",

}

Huang, WC, Chung, P-C, Tsai, H-W, Chow, N-H, Juang, YZ, Tsai, HH, Lin, SH & Wang, CH 2019, Automatic HCC Detection Using Convolutional Network with Multi-Magnification Input Images. in Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019., 8771535, Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 194-198, 1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019, Hsinchu, Taiwan, 19-03-18. https://doi.org/10.1109/AICAS.2019.8771535

Automatic HCC Detection Using Convolutional Network with Multi-Magnification Input Images. / Huang, Wei Che; Chung, Pau-Choo; Tsai, Hung-Wen; Chow, Nan-Haw; Juang, Ying Zong; Tsai, Hann Huei; Lin, Shih Hsuan; Wang, Cheng Hsiung.

Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 194-198 8771535 (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automatic HCC Detection Using Convolutional Network with Multi-Magnification Input Images

AU - Huang, Wei Che

AU - Chung, Pau-Choo

AU - Tsai, Hung-Wen

AU - Chow, Nan-Haw

AU - Juang, Ying Zong

AU - Tsai, Hann Huei

AU - Lin, Shih Hsuan

AU - Wang, Cheng Hsiung

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Liver cancer postoperative pathologic examination of stained tissues is an important step in identifying prognostic factors for follow-up care. Traditionally, liver cancer detection would be performed by pathologists with observing the entire biological tissue, resulting in heavy work loading and potential misjudgment. Accordingly, the studies of the automatic pathological examination have been popular for a long period of time. Most approaches of the existing cancer detection, however, only extract cell level information based on single-scale high-magnification patch. In liver tissues, common cell change phenomena such as apoptosis, necrosis, and steatosis are similar in tumor and benign. Hence, the detection may fail when the patch only covered the changed cells area that cannot provide enough neighboring cell structure information. To conquer this problem, the convolutional network architecture with multi-magnification input can provide not only the cell level information by referencing high-magnification patches, but also the cell structure information by referencing low-magnification patches. The detection algorithm consists of two main structures: 1) extraction of cell level and cell structure level feature maps from high-magnification and low-magnification images respectively by separate general convolutional networks, and 2) integration of multi-magnification features by fully connected network. In this paper, VGG16 and Inception V4 were applied as the based convolutional network for liver tumor detection task. The experimental results showed that VGG16 based multi-magnification input convolutional network achieved 91% mIOU on HCC tumor detection task. In addition, with comparison between single-scale CNN (SSCN) and multi-scale CNN (MSCN) approaches, the MSCN demonstrated that the multi-scale patches could provide better performance on HCC classification task.

AB - Liver cancer postoperative pathologic examination of stained tissues is an important step in identifying prognostic factors for follow-up care. Traditionally, liver cancer detection would be performed by pathologists with observing the entire biological tissue, resulting in heavy work loading and potential misjudgment. Accordingly, the studies of the automatic pathological examination have been popular for a long period of time. Most approaches of the existing cancer detection, however, only extract cell level information based on single-scale high-magnification patch. In liver tissues, common cell change phenomena such as apoptosis, necrosis, and steatosis are similar in tumor and benign. Hence, the detection may fail when the patch only covered the changed cells area that cannot provide enough neighboring cell structure information. To conquer this problem, the convolutional network architecture with multi-magnification input can provide not only the cell level information by referencing high-magnification patches, but also the cell structure information by referencing low-magnification patches. The detection algorithm consists of two main structures: 1) extraction of cell level and cell structure level feature maps from high-magnification and low-magnification images respectively by separate general convolutional networks, and 2) integration of multi-magnification features by fully connected network. In this paper, VGG16 and Inception V4 were applied as the based convolutional network for liver tumor detection task. The experimental results showed that VGG16 based multi-magnification input convolutional network achieved 91% mIOU on HCC tumor detection task. In addition, with comparison between single-scale CNN (SSCN) and multi-scale CNN (MSCN) approaches, the MSCN demonstrated that the multi-scale patches could provide better performance on HCC classification task.

UR - http://www.scopus.com/inward/record.url?scp=85070469791&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070469791&partnerID=8YFLogxK

U2 - 10.1109/AICAS.2019.8771535

DO - 10.1109/AICAS.2019.8771535

M3 - Conference contribution

T3 - Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

SP - 194

EP - 198

BT - Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Huang WC, Chung P-C, Tsai H-W, Chow N-H, Juang YZ, Tsai HH et al. Automatic HCC Detection Using Convolutional Network with Multi-Magnification Input Images. In Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 194-198. 8771535. (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019). https://doi.org/10.1109/AICAS.2019.8771535