한국정보통신학회논문지 (Journal of the Korea Institute of Information and Communication Engineering)

  • 제20권11호
  • /
  • Pages.2137-2142
  • /
  • 2016
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

심자도에서 신경회로망을 이용한 허혈성 심장질환 분류

A Classification of lschemic Heart Disease using Neural Network in Magnetocardiogram

  • Eum, Sang-hee (Department of Shipbuilding and Marine, Dongju College)
  • 투고 : 2016.10.31
  • 심사 : 2016.11.08
  • 발행 : 2016.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

심장에서 발생된 전류는 전위 뿐만 아니라 자기장을 생성한다. 본 논문에서는 61 채널 양자 간섭 장치 (SQUID) 시스템을 사용하여 심자도 (MCG)의 신호를 취득하고, 이것으로부터 임상적으로 유의하다고 생각되는 다양한 특징 파라미터를 계산한다. 이를 입력으로 신경회로망 알고리즘을 적용하여 허혈성 심장질환의 분류를 수행하였다. 심자도 신호는 전처리 과정을 통해 파라미터의 추출을 용이하게 하였다. 연구에 사용된 데이터는 정상인 10명과 안정형 협심 증세를 보이는 허혈성 심장질환 환자 10명분의 신호이다. 이들 신호로부터 임상적으로 유의한 특징점, 특징 간격 파라미터 및 진폭비를 추출하였다. 심자도 특징 파라미터를 신경회로망 입력으로 사용하여 허혈성 심장질환의 분류가 가능함을 보였다.

The electrical current generated by heart creates not only electric potential but also a magnetic field. In this study, the signals obtained magnetocardiogram(MCG) using 61 channel superconducting quantum interference device(SQUID) system, and the clinical significance of various feature parameters has been developed MCG. Neural network algorithm was used to perform the classification of ischemic heart disease. The MCG signal was obtained to facilitate the extraction of parameters through a process of pre-processing. The data used to research the normal group 10 and ischemic heart disease group 10 with visible signs of stable angina patients. The available clinical indicators were extracted by characteristic point, characteristic interval parameter, and amplitude ratio parameter. The extracted parameters are determined to analysis the significance and clinical parameters were defined. It is possible to classify ischemic heart disease using the MCG feature parameters as a neural network input.

키워드

참고문헌

  1. J. D. Park, Y, Huh, S. O. Jin, and S.C. Jeon, "Extraction of ischemic heart disease diagnosis parameters in magnetocardiogram signal," The Transaction of The Korean Institute of Electrical Engineers, vol. 54D, no. 11, pp. 680-688, Nov. 2005.
  2. IvanVincent "Acute Leukemia Classification Using Sequential Neural Network Classifier in Clinical Decision Support System," Master Thesis, Pukyong National University, 2015.
  3. C. I. Jeon, Y. Huh, B. H. Han, W. S. Chang, S. O. Jin, D. H. Youm, K. U. Kim, H. S. Byun, S. H. Lee, S. Y. Choi, and S. H. Choi, "Automatic Extraction of the Diagnostic Parameters in Magnetocardiogram," The 2004 International Technical Conference on Circuit/Systems, Computers and Communication, pp. 6B2L-5, July 6-8, 2004.
  4. Y. G. Park, C. S. Kang, and H. C. Kwon, "Development of Biomagnetic Measurement and Analysis Technology," Korea Research Institute of Standards and Science, Technical Report, 2007.
  5. S. Y. Park, "Novel solution for the Acute Appendicitis Diagnosis System using Artificial Neural Networks," Ph. D. dissertation, Dongguk University, 2012.
  6. IvanVincent "Acute Leukemia Classification Using Sequential Neural Network Classifier in Clinical Decision Support System," Master Thesis, Pukyong National University, 2015.
  7. S. H. Eum, and J. H. Nam, "The Classification of Heart Sound during Systole and Diastole by Neural Network," Information Journal, Vol. 18, No. 6(A), pp.2363-2368, June, 2015.