대한의용생체공학회:의공학회지 (Journal of Biomedical Engineering Research)

  • 제44권3호
  • /
  • Pages.182-189
  • /
  • 2023
  • /
  • 1229-0807(pISSN)
  • /
  • 2288-9396(eISSN)
대한의용생체공학회 (The Korean Society of Medical and Biological Engineering)
권호 표지
DOI QR코드

DOI QR Code

CT 정도관리를 위한 인공지능 모델 적용에 관한 연구

Study on the Application of Artificial Intelligence Model for CT Quality Control

  • 황호성 (을지대학교 일반대학원 의료인공지능학과) ;
  • 김동현 (을지대학교 인공지능융합시스템연구실) ;
  • 김호철 (을지대학교 일반대학원 의료인공지능학과)
  • Ho Seong Hwang (Department of Medical Artificial Intelligent, Graduate School, Eulji University) ;
  • Dong Hyun Kim (Machine Intelligence Convergence System, Eulji University) ;
  • Ho Chul Kim (Department of Medical Artificial Intelligent, Graduate School, Eulji University)
  • 투고 : 2023.05.27
  • 심사 : 2023.06.12
  • 발행 : 2023.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

CT is a medical device that acquires medical images based on Attenuation coefficient of human organs related to X-rays. In addition, using this theory, it can acquire sagittal and coronal planes and 3D images of the human body. Then, CT is essential device for universal diagnostic test. But Exposure of CT scan is so high that it is regulated and managed with special medical equipment. As the special medical equipment, CT must implement quality control. In detail of quality control, Spatial resolution of existing phantom imaging tests, Contrast resolution and clinical image evaluation are qualitative tests. These tests are not objective, so the reliability of the CT undermine trust. Therefore, by applying an artificial intelligence classification model, we wanted to confirm the possibility of quantitative evaluation of the qualitative evaluation part of the phantom test. We used intelligence classification models (VGG19, DenseNet201, EfficientNet B2, inception_resnet_v2, ResNet50V2, and Xception). And the fine-tuning process used for learning was additionally performed. As a result, in all classification models, the accuracy of spatial resolution was 0.9562 or higher, the precision was 0.9535, the recall was 1, the loss value was 0.1774, and the learning time was from a maximum of 14 minutes to a minimum of 8 minutes and 10 seconds. Through the experimental results, it was concluded that the artificial intelligence model can be applied to CT implements quality control in spatial resolution and contrast resolution.

키워드

참고문헌

  1. Buzug TM. Computed tomography: Springer; 2011.
  2. Prokop M. General principles of MDCT. European journal of radiology. 2003;45:S4-S10. https://doi.org/10.1016/S0720-048X(02)00358-3
  3. Ota H, Takase K, Igarashi K, Chiba Y, Haga K, Saito H, et al. MDCT compared with digital subtraction angiography for assessment of lower extremity arterial occlusive disease: importance of reviewing cross-sectional images. American Journal of Roentgenology. 2004;182(1):201-9. https://doi.org/10.2214/ajr.182.1.1820201
  4. Kim KP, Gil JW, Lee BY, Lee HG. Evaluation of national medical radiation dose. Weekly Health and Illness. 2021;14(23):1614-32.
  5. Lee SG. Current status and policy options for high-tech medical devices in Korea: vertical and horizontal synchronization of health policy. Journal of the Korean Medical Association. 2012;55(10):950-8. https://doi.org/10.5124/jkma.2012.55.10.950
  6. Lee KH. https://www.newspim.com/news/view/20220928000043, accessed on Jun. 08, 2023.
  7. Choi MR. http://www.healthfocus.co.kr/news/articleView.html?idxno=90442, accessed on Jun. 08, 2023.
  8. Yu SJ, Seok JM, Won HS, Jo JH, Hwang DG, Seo SY. Investigation of radiation exposure dose of human body in computed tomography. Proceedings of the Korean Magnestics Society Conference. 2015:70-1.
  9. MEDICAL SERVICE ACT Article 38.
  10. Enforcement Regulations of installation and operation of special medical equipment.
  11. Noh SS, Um HS, Kim HC. Development of Automatized Quantitative Analysis Method in CT Images Evaluation using AAPM Phantom. Journal of the Institute of Electronics and Information Engineers. 2014;51(12):163-73. https://doi.org/10.5573/ieie.2014.51.12.163
  12. Lee KB, Cho YB, Jeong HK, Nam KC, Kim HC. The Study on Automatized Quantitative Assessment Method of CT Image in Quality Control: Focusing on Spatial and Low Contrast Resolution. Journal of the Institute of Electronics and Information Engineers. 2017;54(12):186-94. https://doi.org/10.5573/ieie.2017.54.12.186
  13. Im YJ, Hwang HS, Kim DH, Kim HC. A Study on the Quantitative Evaluation Method of Quality Control using Ultrasound Phantom in Ultrasound Imaging System based on Artificial Intelligence. Journal of Biomedical Engineering Research. 2022;43(6):390-8. https://doi.org/10.9718/JBER.2022.43.6.390
  14. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017:4700-8.
  15. Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. International conference on machine learning. 2019:6105-14.
  16. Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the AAAI conference on artificial intelligence. 2017;31(1).
  17. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016:770-8.
  18. Chollet F. Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017:1251-8.
  19. Feurer M, Hutter F. Hyperparameter optimization. Automated machine learning: Methods, systems, challenges. 2019:3-33.
  20. Ruby U, Yendapalli V. Binary cross entropy with deep learning technique for image classification. Int J Adv Trends Comput Sci Eng. 2020;9(10).
  21. Marreiros AC, Daunizeau J, Kiebel SJ, Friston KJ. Population dynamics: variance and the sigmoid activation function. Neuroimage. 2008;42(1):147-57. https://doi.org/10.1016/j.neuroimage.2008.04.239
  22. Liang J. Confusion Matrix: Machine Learning. POGIL Activity Clearinghouse. 2022;3(4).
  23. Chida K, Kaga Y, Haga Y, Takeda K, Zuguchi M. Quality control phantom for flat panel detector X-ray systems. Health physics. 2013;104(1):97-101. https://doi.org/10.1097/HP.0b013e3182659c72
  24. Vennart W. ICRU Report 54: Medical imaging-the assessment of image quality-ISBN 0-913394-53-X. April 1996, Maryland, USA. Radiography. 1997;3(3):243-4. https://doi.org/10.1016/S1078-8174(97)90038-9
  25. Lee KB, Nam KC, Jang JS, Kim HC. Feasibility of the Quantitative Assessment Method for CT Quality Control in Phantom Image Evaluation. Applied Sciences. 2021;11(8):3570.