Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics

Akiho Isshiki; Dar In Tai; Po Hsiang Tsui; Kenji Yoshida; Tadashi Yamaguchi; Shinnosuke Hirata

doi:10.1007/978-981-16-6775-6_36

Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics

Akiho Isshiki, Dar In Tai, Po Hsiang Tsui, Kenji Yoshida, Tadashi Yamaguchi, Shinnosuke Hirata^*

^*Corresponding author for this work

Department of Medical Imaging and Radiological Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The progression of liver fibrosis is the most important indicator that determines the prognosis of patients with diffuse liver disease. Variations in tissue structure triggered by liver fibrosis severely affect the texture and contrast of the ultrasound image. Therefore, progression can be non-invasively evaluated by analyzing ultrasound images. The convolutional neural network (CNN) classification of liver fibrosis stages using ultrasound images has also been studied. In previous studies, grayscale ultrasound images obtained using conventional ultrasound scanners were adopted as the input images. In this study, the modulation and colorization of the ultrasound images by the echo-envelope statistics that correspond to the texture and contrast of the ultrasound images have been proposed. In the proposed method, the colorized ultrasound image in RGB representation comprises the original image and two images modulated by different features of the echo-envelope statistics. Accordingly, the effect enhancement of tissue-structure variation by the colorization of the ultrasound images is promising in improving the accuracy of CNN classification. Therefore, CNN classification of the ultrasound images colorized by their 1st- and 3rd-order moments is demonstrated via the transfer learning of the VGG-16 pretrained network.

Original language	English
Title of host publication	Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022
Editors	Ruidan Su, Yudong Zhang, Han Liu, Alejandro F Frangi
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	441-451
Number of pages	11
ISBN (Print)	9789811667749
DOIs	https://doi.org/10.1007/978-981-16-6775-6_36
State	Published - 2023
Event	International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022 - Leicester, United Kingdom Duration: 20 11 2022 → 21 11 2022

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	810 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022
Country/Territory	United Kingdom
City	Leicester
Period	20/11/22 → 21/11/22

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Keywords

Convolutional neural network
Echo-envelope statistics
Liver fibrosis
Quantitative diagnosis
Ultrasound image

Access to Document

10.1007/978-981-16-6775-6_36

Cite this

Isshiki, A., Tai, D. I., Tsui, P. H., Yoshida, K., Yamaguchi, T., & Hirata, S. (2023). Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics. In R. Su, Y. Zhang, H. Liu, & A. F Frangi (Eds.), Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022 (pp. 441-451). (Lecture Notes in Electrical Engineering; Vol. 810 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-6775-6_36

Isshiki, Akiho ; Tai, Dar In ; Tsui, Po Hsiang et al. / Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics. Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022. editor / Ruidan Su ; Yudong Zhang ; Han Liu ; Alejandro F Frangi. Springer Science and Business Media Deutschland GmbH, 2023. pp. 441-451 (Lecture Notes in Electrical Engineering).

@inproceedings{e7aaae802c6e4b6ca3aafafb90f0a4f7,

title = "Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics",

abstract = "The progression of liver fibrosis is the most important indicator that determines the prognosis of patients with diffuse liver disease. Variations in tissue structure triggered by liver fibrosis severely affect the texture and contrast of the ultrasound image. Therefore, progression can be non-invasively evaluated by analyzing ultrasound images. The convolutional neural network (CNN) classification of liver fibrosis stages using ultrasound images has also been studied. In previous studies, grayscale ultrasound images obtained using conventional ultrasound scanners were adopted as the input images. In this study, the modulation and colorization of the ultrasound images by the echo-envelope statistics that correspond to the texture and contrast of the ultrasound images have been proposed. In the proposed method, the colorized ultrasound image in RGB representation comprises the original image and two images modulated by different features of the echo-envelope statistics. Accordingly, the effect enhancement of tissue-structure variation by the colorization of the ultrasound images is promising in improving the accuracy of CNN classification. Therefore, CNN classification of the ultrasound images colorized by their 1st- and 3rd-order moments is demonstrated via the transfer learning of the VGG-16 pretrained network.",

keywords = "Convolutional neural network, Echo-envelope statistics, Liver fibrosis, Quantitative diagnosis, Ultrasound image",

author = "Akiho Isshiki and Tai, \{Dar In\} and Tsui, \{Po Hsiang\} and Kenji Yoshida and Tadashi Yamaguchi and Shinnosuke Hirata",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022 ; Conference date: 20-11-2022 Through 21-11-2022",

year = "2023",

doi = "10.1007/978-981-16-6775-6\_36",

language = "英语",

isbn = "9789811667749",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "441--451",

editor = "Ruidan Su and Yudong Zhang and Han Liu and \{F Frangi\}, Alejandro",

booktitle = "Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022",

address = "德国",

}

Isshiki, A, Tai, DI, Tsui, PH, Yoshida, K, Yamaguchi, T & Hirata, S 2023, Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics. in R Su, Y Zhang, H Liu & A F Frangi (eds), Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022. Lecture Notes in Electrical Engineering, vol. 810 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 441-451, International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022, Leicester, United Kingdom, 20/11/22. https://doi.org/10.1007/978-981-16-6775-6_36

Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics. / Isshiki, Akiho; Tai, Dar In; Tsui, Po Hsiang et al.
Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022. ed. / Ruidan Su; Yudong Zhang; Han Liu; Alejandro F Frangi. Springer Science and Business Media Deutschland GmbH, 2023. p. 441-451 (Lecture Notes in Electrical Engineering; Vol. 810 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics

AU - Isshiki, Akiho

AU - Tai, Dar In

AU - Tsui, Po Hsiang

AU - Yoshida, Kenji

AU - Yamaguchi, Tadashi

AU - Hirata, Shinnosuke

PY - 2023

Y1 - 2023

N2 - The progression of liver fibrosis is the most important indicator that determines the prognosis of patients with diffuse liver disease. Variations in tissue structure triggered by liver fibrosis severely affect the texture and contrast of the ultrasound image. Therefore, progression can be non-invasively evaluated by analyzing ultrasound images. The convolutional neural network (CNN) classification of liver fibrosis stages using ultrasound images has also been studied. In previous studies, grayscale ultrasound images obtained using conventional ultrasound scanners were adopted as the input images. In this study, the modulation and colorization of the ultrasound images by the echo-envelope statistics that correspond to the texture and contrast of the ultrasound images have been proposed. In the proposed method, the colorized ultrasound image in RGB representation comprises the original image and two images modulated by different features of the echo-envelope statistics. Accordingly, the effect enhancement of tissue-structure variation by the colorization of the ultrasound images is promising in improving the accuracy of CNN classification. Therefore, CNN classification of the ultrasound images colorized by their 1st- and 3rd-order moments is demonstrated via the transfer learning of the VGG-16 pretrained network.

AB - The progression of liver fibrosis is the most important indicator that determines the prognosis of patients with diffuse liver disease. Variations in tissue structure triggered by liver fibrosis severely affect the texture and contrast of the ultrasound image. Therefore, progression can be non-invasively evaluated by analyzing ultrasound images. The convolutional neural network (CNN) classification of liver fibrosis stages using ultrasound images has also been studied. In previous studies, grayscale ultrasound images obtained using conventional ultrasound scanners were adopted as the input images. In this study, the modulation and colorization of the ultrasound images by the echo-envelope statistics that correspond to the texture and contrast of the ultrasound images have been proposed. In the proposed method, the colorized ultrasound image in RGB representation comprises the original image and two images modulated by different features of the echo-envelope statistics. Accordingly, the effect enhancement of tissue-structure variation by the colorization of the ultrasound images is promising in improving the accuracy of CNN classification. Therefore, CNN classification of the ultrasound images colorized by their 1st- and 3rd-order moments is demonstrated via the transfer learning of the VGG-16 pretrained network.

KW - Convolutional neural network

KW - Echo-envelope statistics

KW - Liver fibrosis

KW - Quantitative diagnosis

KW - Ultrasound image

UR - https://www.scopus.com/pages/publications/85180795355

U2 - 10.1007/978-981-16-6775-6_36

DO - 10.1007/978-981-16-6775-6_36

M3 - 会议稿件

AN - SCOPUS:85180795355

SN - 9789811667749

T3 - Lecture Notes in Electrical Engineering

SP - 441

EP - 451

BT - Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022

A2 - Su, Ruidan

A2 - Zhang, Yudong

A2 - Liu, Han

A2 - F Frangi, Alejandro

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022

Y2 - 20 November 2022 through 21 November 2022

ER -

Isshiki A, Tai DI, Tsui PH, Yoshida K, Yamaguchi T, Hirata S. Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics. In Su R, Zhang Y, Liu H, F Frangi A, editors, Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022. Springer Science and Business Media Deutschland GmbH. 2023. p. 441-451. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-16-6775-6_36

Convolutional Neural Network Classification of Liver Fibrosis Stages Using Ultrasonic Images Colorized by Features of Echo-Envelope Statistics

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this