Automatic Finger Tendon Segmentation from Ultrasound Images Using Deep Learning

Chan Pang Kuok, Bo Siang Tsai, Tai-Hua Yang, Fong-chin Su, I. Ming Jou, Yung-Nien Sun

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

Abstract

Ultrasound imaging is the most commonly applied method for the diagnosis and surgery of a trigger finger. However, the ultrasound images are noisy and the boundaries of tissues are usually very unclear and fuzzy. Therefore, an automatic computer assisted tool for the tissues segmentation is desired and developed. The segmentation results of the conventional methods were satisfactory but they usually depended on the prior knowledge. Recently, the deep-learning convolutional neural network (CNN) shows amazing performance on image processing and it can process the image end-to-end. In this study, we propose a finger tendon segmentation CNN which overcomes the requirement of prior knowledge and gives promising results on ultrasound images. The evaluation result is remarkable high with DSC 0.884 on 380 testing images and the prediction time is fast by 0.027 s per image. This work, to our best of knowledge, is the first deep learning finger tendon segmentation method from transverse ultrasound images.

Original languageEnglish
Title of host publicationNew Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers
EditorsChuan-Yu Chang, Chien-Chou Lin, Horng-Horng Lin
PublisherSpringer Verlag
Pages778-784
Number of pages7
ISBN (Print)9789811391897
DOIs
Publication statusPublished - 2019 Jan 1
Event23rd International Computer Symposium, ICS 2018 - Yunlin, Taiwan
Duration: 2018 Dec 202018 Dec 22

Publication series

NameCommunications in Computer and Information Science
Volume1013
ISSN (Print)1865-0929

Conference

Conference23rd International Computer Symposium, ICS 2018
CountryTaiwan
CityYunlin
Period18-12-2018-12-22

Fingerprint

Ultrasound Image
Tendons
Segmentation
Ultrasonics
Prior Knowledge
Neural Networks
Tissue
Neural networks
Ultrasound
Trigger
Surgery
Image Processing
Image processing
Transverse
Imaging
Imaging techniques
Testing
Learning
Deep learning
Prediction

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

Kuok, C. P., Tsai, B. S., Yang, T-H., Su, F., Jou, I. M., & Sun, Y-N. (2019). Automatic Finger Tendon Segmentation from Ultrasound Images Using Deep Learning. In C-Y. Chang, C-C. Lin, & H-H. Lin (Eds.), New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers (pp. 778-784). (Communications in Computer and Information Science; Vol. 1013). Springer Verlag. https://doi.org/10.1007/978-981-13-9190-3_84
Kuok, Chan Pang ; Tsai, Bo Siang ; Yang, Tai-Hua ; Su, Fong-chin ; Jou, I. Ming ; Sun, Yung-Nien. / Automatic Finger Tendon Segmentation from Ultrasound Images Using Deep Learning. New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers. editor / Chuan-Yu Chang ; Chien-Chou Lin ; Horng-Horng Lin. Springer Verlag, 2019. pp. 778-784 (Communications in Computer and Information Science).
@inproceedings{76c54879106c4b8fba1e28a408404b66,
title = "Automatic Finger Tendon Segmentation from Ultrasound Images Using Deep Learning",
abstract = "Ultrasound imaging is the most commonly applied method for the diagnosis and surgery of a trigger finger. However, the ultrasound images are noisy and the boundaries of tissues are usually very unclear and fuzzy. Therefore, an automatic computer assisted tool for the tissues segmentation is desired and developed. The segmentation results of the conventional methods were satisfactory but they usually depended on the prior knowledge. Recently, the deep-learning convolutional neural network (CNN) shows amazing performance on image processing and it can process the image end-to-end. In this study, we propose a finger tendon segmentation CNN which overcomes the requirement of prior knowledge and gives promising results on ultrasound images. The evaluation result is remarkable high with DSC 0.884 on 380 testing images and the prediction time is fast by 0.027 s per image. This work, to our best of knowledge, is the first deep learning finger tendon segmentation method from transverse ultrasound images.",
author = "Kuok, {Chan Pang} and Tsai, {Bo Siang} and Tai-Hua Yang and Fong-chin Su and Jou, {I. Ming} and Yung-Nien Sun",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-981-13-9190-3_84",
language = "English",
isbn = "9789811391897",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "778--784",
editor = "Chuan-Yu Chang and Chien-Chou Lin and Horng-Horng Lin",
booktitle = "New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers",
address = "Germany",

}

Kuok, CP, Tsai, BS, Yang, T-H, Su, F, Jou, IM & Sun, Y-N 2019, Automatic Finger Tendon Segmentation from Ultrasound Images Using Deep Learning. in C-Y Chang, C-C Lin & H-H Lin (eds), New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 1013, Springer Verlag, pp. 778-784, 23rd International Computer Symposium, ICS 2018, Yunlin, Taiwan, 18-12-20. https://doi.org/10.1007/978-981-13-9190-3_84

Automatic Finger Tendon Segmentation from Ultrasound Images Using Deep Learning. / Kuok, Chan Pang; Tsai, Bo Siang; Yang, Tai-Hua; Su, Fong-chin; Jou, I. Ming; Sun, Yung-Nien.

New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers. ed. / Chuan-Yu Chang; Chien-Chou Lin; Horng-Horng Lin. Springer Verlag, 2019. p. 778-784 (Communications in Computer and Information Science; Vol. 1013).

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

TY - GEN

T1 - Automatic Finger Tendon Segmentation from Ultrasound Images Using Deep Learning

AU - Kuok, Chan Pang

AU - Tsai, Bo Siang

AU - Yang, Tai-Hua

AU - Su, Fong-chin

AU - Jou, I. Ming

AU - Sun, Yung-Nien

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Ultrasound imaging is the most commonly applied method for the diagnosis and surgery of a trigger finger. However, the ultrasound images are noisy and the boundaries of tissues are usually very unclear and fuzzy. Therefore, an automatic computer assisted tool for the tissues segmentation is desired and developed. The segmentation results of the conventional methods were satisfactory but they usually depended on the prior knowledge. Recently, the deep-learning convolutional neural network (CNN) shows amazing performance on image processing and it can process the image end-to-end. In this study, we propose a finger tendon segmentation CNN which overcomes the requirement of prior knowledge and gives promising results on ultrasound images. The evaluation result is remarkable high with DSC 0.884 on 380 testing images and the prediction time is fast by 0.027 s per image. This work, to our best of knowledge, is the first deep learning finger tendon segmentation method from transverse ultrasound images.

AB - Ultrasound imaging is the most commonly applied method for the diagnosis and surgery of a trigger finger. However, the ultrasound images are noisy and the boundaries of tissues are usually very unclear and fuzzy. Therefore, an automatic computer assisted tool for the tissues segmentation is desired and developed. The segmentation results of the conventional methods were satisfactory but they usually depended on the prior knowledge. Recently, the deep-learning convolutional neural network (CNN) shows amazing performance on image processing and it can process the image end-to-end. In this study, we propose a finger tendon segmentation CNN which overcomes the requirement of prior knowledge and gives promising results on ultrasound images. The evaluation result is remarkable high with DSC 0.884 on 380 testing images and the prediction time is fast by 0.027 s per image. This work, to our best of knowledge, is the first deep learning finger tendon segmentation method from transverse ultrasound images.

UR - http://www.scopus.com/inward/record.url?scp=85069735935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069735935&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-9190-3_84

DO - 10.1007/978-981-13-9190-3_84

M3 - Conference contribution

AN - SCOPUS:85069735935

SN - 9789811391897

T3 - Communications in Computer and Information Science

SP - 778

EP - 784

BT - New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers

A2 - Chang, Chuan-Yu

A2 - Lin, Chien-Chou

A2 - Lin, Horng-Horng

PB - Springer Verlag

ER -

Kuok CP, Tsai BS, Yang T-H, Su F, Jou IM, Sun Y-N. Automatic Finger Tendon Segmentation from Ultrasound Images Using Deep Learning. In Chang C-Y, Lin C-C, Lin H-H, editors, New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers. Springer Verlag. 2019. p. 778-784. (Communications in Computer and Information Science). https://doi.org/10.1007/978-981-13-9190-3_84