핵의학 감마카메라 정도관리의 딥러닝 적용
Deep Learning Application of Gamma Camera Quality Control in Nuclear Medicine
2
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
In the field of nuclear medicine, errors are sometimes generated because the assessment of the uniformity of gamma cameras relies on the naked eye of the evaluator. To minimize these errors, we created an artificial intelligence model based on CNN algorithm and wanted to assess its usefulness. We produced 20,000 normal images and partial cold region images using Python, and conducted artificial intelligence training with Resnet18 models. The training results showed that accuracy, specificity and sensitivity were 95.01%, 92.30%, and 97.73%, respectively. According to the results of the evaluation of the confusion matrix of artificial intelligence and expert groups, artificial intelligence was accuracy, specificity and sensitivity of 94.00%, 91.50%, and 96.80%, respectively, and expert groups was accuracy, specificity and sensitivity of 69.00%, 64.00%, and 74.00%, respectively. The results showed that artificial intelligence was better than expert groups. In addition, by checking together with the radiological technologist and AI, errors that may occur during the quality control process can be reduced, providing a better examination environment for patients, providing convenience to radiologists, and improving work efficiency.
Abstract
In the field of nuclear medicine, errors are sometimes generated because the assessment of the uniformity of gamma cameras relies on the naked eye of the evaluator. To minimize these errors, we created an artificial intelligence model based on CNN algorithm and wanted to assess its usefulness. We produced 20,000 normal images and partial cold region images using Python, and conducted artificial intelligence training with Resnet18 models. The training results showed that accuracy, specificity and sensitivity were 95.01%, 92.30%, and 97.73%, respectively. According to the results of the evaluation of the confusion matrix of artificial intelligence and expert groups, artificial intelligence was accuracy, specificity and sensitivity of 94.00%, 91.50%, and 96.80%, respectively, and expert groups was accuracy, specificity and sensitivity of 69.00%, 64.00%, and 74.00%, respectively. The results showed that artificial intelligence was better than expert groups. In addition, by checking together with the radiological technologist and AI, errors that may occur during the quality control process can be reduced, providing a better examination environment for patients, providing convenience to radiologists, and improving work efficiency.
참고문헌 (16)
- 최권택, "고차원 의료 영상을 위한 실시간 인공 신경망", 한국방사선학회논문지, 10(8), pp.637~643 (2016), 한국방사선학회[DOI]
- Ravi D, "Deep learning for health informatics", IEEE Journal of Biomedical and Health Informatics, 21(1), pp.4~21 (2017)
- LeCun Y, "Backpropagation applied to handwritten zip code recognition", Neural Computation, 1(4), pp.541~551 (1989)
- Li J, "CNN-based facial expression recognition from annotated RGB-D images for human–robot interaction", International Journal of Humanoid Robotics, 16(4), pp.1941002~ (2019)
- Research for development of standardized system for quality control of nuclear medicine imaging equipments, "Choi JG", Korea Food & Drug administration, 859~860, pp.12(11-14700000-000071-10) (2008)
- 최재걸, "감마카메라 정도관리 실태 조사", Nuclear Medicine and Molecular Imaging, 42(4), pp.314~322 (2008), 대한핵의학회
- Choi WC, "Actual condition of computerized tomography system in use in Seoul and projection evaluation using AAPM CT Phantom", Master, pp.2009
- Lim JJ, "Evaluation of radiation exposure to medical staff except nuclear medicine department", The Korean Journal of Nuclear Medicine Technology, 20(2), pp.32~35 (2016)
- 노성순, "AAPM Phantom을 이용한 CT 영상 평가 시자동화된 정량적 분석 방법 개발", 전자공학회논문지, 51(12), pp.163~173 (2014), 대한전자공학회
- Quality control of nuclear medicine instruments, "The International Atomic Energy Agency", ~, pp.IAEATECDOC-317 (1984)
- National Physical Laboratory, "Protocol for establishing and maintaining the calibration of medical radionuclide calibrators and their quality control. A National Measurement Good Practice Guide", 93~ (2006)
- He K, "Deep residual learning for image recognition", axRiv(Computer Vision and Pattern Rescognition), ~ (2015)
- Park HK, "Artificial intelligence(AI)health care industry status and trends", Convergence Focus, 148, pp.2~9 (2019)
- Lee HH, "CNN Generalization Error Evaluation Method", Master, pp.2020
- 박정규, "경북 지역 의원급의 X선 발생장치 정도관리 실태", 한국콘텐츠학회 논문지, 10(9), pp.267~275 (2010), 한국콘텐츠학회
- Larson DB, "Imaging quality control in the era of artificial intelligence", Journal of the American College of Radiology, 16(9), pp.1259~1266 (2019)