Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Automatic Segmentation Algorithm of Intima-media Thickness of Carotid Artery in Portable Ultrasound Image Based on Deep Learning

딥러닝 모델을 이용한 휴대용 무선 초음파 영상에서의 경동맥 내중막 두께 자동 분할 알고리즘 개발

  • Choi, Ja-Young (Department of Biomedical Engineering, College of Health Science, Gachon University) ;
  • Kim, Young Jae (Department of Biomedical Engineering, College of Medicine, Gachon University) ;
  • You, Kyung Min (Gachon Cardiovascular Research Institute, Gachon University) ;
  • Jang, Albert Youngwoo (Gachon Cardiovascular Research Institute, Gachon University) ;
  • Chung, Wook-Jin (Gachon Cardiovascular Research Institute, Gachon University) ;
  • Kim, Kwang Gi (Department of Biomedical Engineering, College of Health Science, Gachon University)
  • 최자영 (가천대학교 보건과학대학 의용생체공학과) ;
  • 김영재 (가천대학교 의과대학 의공학교실) ;
  • 유경민 (가천대학교 심혈관 연구소) ;
  • 장영우 (가천대학교 심혈관 연구소) ;
  • 정욱진 (가천대학교 심혈관 연구소) ;
  • 김광기 (가천대학교 보건과학대학 의용생체공학과)
  • Received : 2021.04.23
  • Accepted : 2021.06.25
  • Published : 2021.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Measuring Intima-media thickness (IMT) with ultrasound images can help early detection of coronary artery disease. As a result, numerous machine learning studies have been conducted to measure IMT. However, most of these studies require several steps of pre-treatment to extract the boundary, and some require manual intervention, so they are not suitable for on-site treatment in urgent situations. in this paper, we propose to use deep learning networks U-Net, Attention U-Net, and Pretrained U-Net to automatically segment the intima-media complex. This study also applied the HE, HS, and CLAHE preprocessing technique to wireless portable ultrasound diagnostic device images. As a result, The average dice coefficient of HE applied Models is 71% and CLAHE applied Models is 70%, while the HS applied Models have improved as 72% dice coefficient. Among them, Pretrained U-Net showed the highest performance with an average of 74%. When comparing this with the mean value of IMT measured by Conventional wired ultrasound equipment, the highest correlation coefficient value was shown in the HS applied pretrained U-Net.

Keywords

Acknowledgement

본 연구는 서울시 산학연 협력사업(과제번호 : BT190153), 범부처 전주기의료기기연구개발사업단(9991006834, KMDF_PR_20200901_0164, KMDF_PR_20200901_0170), 가천대 길병원 인공지능 빅데이터 융합센터(FRD2019-11-03)으로 수행된 연구결과임.

References

  1. Honda O, Sugiyama S, Kugiyama K, Hironobu F, Shinichi N, Shunichi K. Echolucent carotid plaques predict future coronary events in patients with coronary artery disease. Journal of the American College of Cardiology. 2004;43(7):1177-1184. https://doi.org/10.1016/j.jacc.2003.09.063
  2. Kwon T, Kim K, Yoon H, Hyun D, Bae J. Measurement of Carotid Intima-Media Thickness in ultrasound images by means of an automatic segmentation process based on machine learning. The Korean Society of Circulation. 2007;37:103-107. https://doi.org/10.4070/kcj.2007.37.3.103
  3. Liang Q, Wendelhag I, Wikstrand J, Gustavsson TA multiscale dynamic programming procedure for boundary detection in ultrasonic artery images. IEEE Transactions Medical Imaging. 2000;19:127-142. https://doi.org/10.1109/42.836372
  4. Kim JS, Seok HY, Kim BJ. The significance of muscle echo intensity on ultrasound for focal neuropathy: The median- to ulnar-innervated muscle echo intensity ratio in carpal tunnel syndrome. Journal of Clinical Neurophysiology. 2016;127:880-885. https://doi.org/10.1016/j.clinph.2015.04.055
  5. Litjens G, Kooi T, Bejnordi B.E, Setio A.A.A, Ciompi F, Ghafoorian M. A survey on deep learning in medical image analysis. Medical Image Analysis,2017;42:60-88. https://doi.org/10.1016/j.media.2017.07.005
  6. Ravi D, Wong C, Deligianni F, Berthelot M, Perez J.A, Lo B.P.L. Deep Learning for Health Informatics. IEEE Journal of Biomedical and Health Informatics. 2017;21(1):4-21. https://doi.org/10.1109/JBHI.2016.2636665
  7. Li Q, Zhang W, Guan X, Bai Y, Jia J. An improved approach for accurate and efficient measurement of common carotid artery intima-media thickness in ultrasound images. Journal of Biomedical Research International. 2014;2014.
  8. Loizou CP, Pattichis CS, Nicolaides AN, Pantziaris M. Manual and automated media and intima thickness measurements of the common carotid artery. IEEE Transactions Medical Imaging. 2009;56(5).
  9. Li H, Zhang S, Ma R, Chen H, Xi S, Zhang J, Fang J. Ultrasound intima-media thickness measurement of the carotid artery using ant colony optimization combined with a curvelet-based orientation-selective filter. Medical Physics. 2016;43(4):1795-1807. https://doi.org/10.1118/1.4943567
  10. Sudha S, Jayanthi K.B, Rajasekaran C, Madian N, Sunder T. Convolutional Neural Network for Segmentation and Measurement of Intima Media Thickness. Journal of Medical Systems. 2018;42(154).
  11. Liang Q, Wendelhag I, Wikstrand J, Gustavsson T. A multiscale dynamic programming procedure for boundary detection in ultrasonic artery images. IEEE Transactions Medical Imaging. 2000;19(2):127-142. https://doi.org/10.1109/42.836372
  12. Lee SM, Park CM. Application of Artificial Intelligence in Lung Cancer Screening. J Korean Soc Radiol. 2019;80(5);872-879. https://doi.org/10.3348/jksr.2019.80.5.872
  13. Hyun DW, Bae JH, Kim KY, Hwang IK. Measurement of the Carotid Intima, Media and Intima-Media Thickness with Ultrasound and New Software. The Korean Society of Circulation. 2005;35(8):625-632. https://doi.org/10.4070/kcj.2005.35.8.625
  14. Coppola G, Natale F, Torino A, Capasso R, D'Aniello A, Pironti E, Santoro E, Calabro R, Verrotti A. The impact of the ketogenic diet on arterial morphology and endothelial function in children and young adults with epilepsy: A case-control study. Seizure. 2014;23(4):260-265. https://doi.org/10.1016/j.seizure.2013.12.002
  15. Kim DJ. Image contrast enhancement using K-means algorithm. Master's Thesis of Korea Maritime University of Technology. 2008.
  16. Kang HW, Hwang BH, Yun JH, Cho TK, Choi MR. An Adaptive Contrast Enhancement Method by Histogram Compensation. Journal of the Korean Society of Industry-Academic Technology. 2010;11(3):958-964.
  17. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention. 2015;9351:234-241.
  18. Schlemper J, Oktay O, Schaap M, Heinrich M, Kainz B, Glocker B. Attention gated networks: Learning to leverage salient regions in medical images. Medical Image Analysis. 2019;53:197-207. https://doi.org/10.1016/j.media.2019.01.012
  19. Oktay O, Schlemper J, Folgoc L.L, Lee M, Heinrich M, Misawa K. Attention U-Net: Learning Where to Look for the Pancreas. ArXiv. 2018.
  20. Weiss K, Khoshgoftaar T.M, and Wang D.A Survey on Transfer Learning. Journal of Big Data. 2014;3(9):1-40. https://doi.org/10.14361/transcript.9783839425923.fm
  21. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2016;770-778.
  22. Yang HS, Lee KJ, Ahn J, Oh MS, Lee YH, Hong ES, Ryu JC. Carotid Ultrasound: Imaging and Interpretation for Clinicians. Clinical Ultrasound. 2018;3:1-7. https://doi.org/10.18525/cu.2018.3.1.1
  23. Lee SJ, Yu SW, Hong JM, Ahn SH, Jeong SK, Lee JY. Extracranial Carotid Duplex Ultrasonography. Part I - Basic Principles and Standard Examination for Carotid and Vertebral Arteries, and Jugular Veins. Journal of the Neurosonol Neuroimag. 2018;10(2):47-60. https://doi.org/10.31728/jnn.2018.00023