CT 정도관리를 위한 인공지능 모델 적용에 관한 연구
Study on the Application of Artificial Intelligence Model for CT Quality Control
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
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 eval- uation 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 res- olution and contrast resolution.
Abstract
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 eval- uation 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 res- olution and contrast resolution.
참고문헌 (25)
- Buzug TM, "Computed tomography" (2011), Springer
- Prokop M, "General principles of MDCT", European journal of radiology, 45, pp.S4~S10 (2003)
- Ota H, "MDCT compared with digital subtraction angiography for assessment of lower extremity arterial occlusive disease : importance of reviewing cross-sectional images", American Journal of Roentgenology, 182(1), pp.201~209 (2004)
- Kim KP, "Evaluation of national medical radiation dose", Weekly Health and Illness, 14(23), pp.1614~1632 (2021)
- 이상규, "우리나라 고가 의료장비 현황과 정책대안: 정책의 수직적, 수평적 동기화", 대한의사협회지, 55(10), pp.950~958 (2012), 대한의사협회[DOI]
- "Lee KH"[URL]
- "Choi MR"[URL]
- Yu SJ, "Investigation of radiation exposure dose of human body in computed tomography", Proceedings of the Korean Magnestics Society Conference, pp.70~71 (2015)
- "MEDICAL SERVICE ACT Article 38", ~
- "Enforcement Regulations of installation and operation of special medical equipment", ~
- 노성순, "AAPM Phantom을 이용한 CT 영상 평가 시자동화된 정량적 분석 방법 개발", 전자공학회논문지, 51(12), pp.163~173 (2014), 대한전자공학회
- 이기백, "CT영상의 품질관리 시 자동화된 정량적 평가방법에 관한 연구: 공간 분해능과 대조도 분해능 중심으로", 전자공학회논문지, 54(12), pp.186~194 (2017), 대한전자공학회
- 임연진, "인공지능을 활용한 초음파영상진단장치에서 초음파 팬텀 영상을 이용한 정도관리의 정량적 평가방법 연구", 의공학회지, 43(6), pp.390~398 (2022), 대한의용생체공학회
- Huang G, "Densely connected convolutional networks", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.4700~4708 (2017)
- Tan M, "Efficientnet: Rethinking model scaling for convolutional neural networks", International conference on machine learning, pp.6105~6114 (2019)
- Szegedy C, "Inception-v4, inception-resnet and the impact of residual connections on learning", Proceedings of the AAAI conference on artificial intelligence, 31(1) (2017)
- He K, "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- Chollet F, "Xception: Deep learning with depthwise separable convolutions", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1251~1258 (2017)
- Feurer M, "Hyperparameter optimization. Automated machine learning", Methods, systems, challenges, pp.3~33 (2019)
- Ruby U, "Binary cross entropy with deep learning technique for image classification", Int J Adv Trends Comput Sci Eng, 9(10) (2020)
- Marreiros AC, "Population dynamics : variance and the sigmoid activation function", Neuroimage, 42(1), pp.147~157 (2008)
- Liang J, "Confusion Matrix: Machine Learning", POGIL Activity Clearinghouse, 3(4) (2022)
- Chida K, "Quality control phantom for flat panel detector X-ray systems", Health physics, 104(1), pp.97~101 (2013)
- Vennart W, "ICRU Report 54: Medical imaging-the assessment of image quality-ISBN 0-913394-53-X. April 1996, Maryland, USA", Radiography, 3(3), pp.243~244 (1997)
- Lee KB, "Feasibility of the Quantitative Assessment Method for CT Quality Control in Phantom Image Evaluation", Applied Sciences, 11(8), pp.3570~ (2021)