게이트심장혈액풀검사에서 딥러닝 기반 좌심실 영역 분할방법의 유용성 평가
Evaluating Usefulness of Deep Learning Based Left Ventricle Segmentation in Cardiac Gated Blood Pool Scan
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
The Cardiac Gated Blood Pool (GBP) scintigram, a nuclear medicine imaging, calculates the left ventricular Ejection Fraction (EF) by segmenting the left ventricle from the heart. However, in order to accurately segment the substructure of the heart, specialized knowledge of cardiac anatomy is required, and depending on the expert's processing, there may be a problem in which the left ventricular EF is calculated differently. In this study, using the DeepLabV3 architecture, GBP images were trained on 93 training data with a ResNet-50 backbone. Afterwards, the trained model was applied to 23 separate test sets of GBP to evaluate the reproducibility of the region of interest and left ventricular EF. Pixel accuracy, dice coefficient, and IoU for the region of interest were 99.32±0.20, 94.65±1.45, 89.89±2.62(%) at the diastolic phase, and 99.26±0.34, 90.16±4.19, and 82.33±6.69(%) at the systolic phase, respectively. Left ventricular EF was calculated to be an average of 60.37±7.32% in the ROI set by humans and 58.68±7.22% in the ROI set by the deep learning segmentation model. (p<0.05) The automated segmentation method using deep learning presented in this study similarly predicts the average human-set ROI and left ventricular EF when a random GBP image is an input. If the automatic segmentation method is developed and applied to the functional examination method that needs to set ROI in the field of cardiac scintigram in nuclear medicine in the future, it is expected to greatly contribute to improving the efficiency and accuracy of processing and analysis by nuclear medicine specialists.
Abstract
The Cardiac Gated Blood Pool (GBP) scintigram, a nuclear medicine imaging, calculates the left ventricular Ejection Fraction (EF) by segmenting the left ventricle from the heart. However, in order to accurately segment the substructure of the heart, specialized knowledge of cardiac anatomy is required, and depending on the expert's processing, there may be a problem in which the left ventricular EF is calculated differently. In this study, using the DeepLabV3 architecture, GBP images were trained on 93 training data with a ResNet-50 backbone. Afterwards, the trained model was applied to 23 separate test sets of GBP to evaluate the reproducibility of the region of interest and left ventricular EF. Pixel accuracy, dice coefficient, and IoU for the region of interest were 99.32±0.20, 94.65±1.45, 89.89±2.62(%) at the diastolic phase, and 99.26±0.34, 90.16±4.19, and 82.33±6.69(%) at the systolic phase, respectively. Left ventricular EF was calculated to be an average of 60.37±7.32% in the ROI set by humans and 58.68±7.22% in the ROI set by the deep learning segmentation model. (p<0.05) The automated segmentation method using deep learning presented in this study similarly predicts the average human-set ROI and left ventricular EF when a random GBP image is an input. If the automatic segmentation method is developed and applied to the functional examination method that needs to set ROI in the field of cardiac scintigram in nuclear medicine in the future, it is expected to greatly contribute to improving the efficiency and accuracy of processing and analysis by nuclear medicine specialists.
참고문헌 (21)
- National Cancer Center, "Cancer registration statistics. Trends in the incidence of breast cancer (1999-2018)", ~
- Abdel-Qadir H, "The risk of heart failure and other cardiovascular hospitalizations after early stage breast cancer : A matched cohort study", JNCI : Journal of the National Cancer Institute, 111(8), pp.854~862 (2019)
- Go CS, "Nuclear Medicine", pp.320~330 (1992), Korea Medical Book
- Hong YM, "Comparison between Echocardiography and Cardiac Cine-MRI : Left Ventricular Volume and Cardiac Output", The Ewha Medical Journal, 15(4), pp.327~335 (1992)
- Kim JY, "Study the Analysis of Comparison with AROI and MROI Mode in Gated Cardiac Blood Pool Scan", The Korean Journal of Nuclear Medicine Technology, 12(3), pp.222~228 (2008)
- Frangi AF, "Three-dimensional modeling for functional analysis of cardiac images : A review", IEEE Trans Med Imaging, 20(1), pp.2~5 (2001)
- Liao S, "Representation learning : A unified deep learning framework for automatic prostate MR segmentation", Med Image Comput Comput Assist Interv, 16(Pt 2), pp.254~261 (2013)
- Wu G, "Unsupervised deep feature learning for deformable registration of MR brain images", Med Image Comput Comput Assist Interv, 16(Pt 2), pp.649~656 (2013)
- Chen C, "Deep Learning for Cardiac Image Segmentation : A Review", Front Cardiovasc Med, 7, pp.25~ (2020)
- 임상헌, "Residual Multi-Dilated Recurrent Convolutional U-Net을 이용한 전자동 심장 분할 모델 분석", 정보처리학회논문지. 컴퓨터 및 통신시스템, 9(2), pp.37~44 (2020), 한국정보처리학회[DOI]
- Koo Hyun Jung, "Automated Segmentation of Left Ventricular Myocardium on Cardiac Computed Tomography Using Deep Learning", Korean Journal of Radiology, 21(6), pp.660~669 (2020), 대한영상의학회[DOI]
- Saito S, "Convolutional neural network-based automatic heart segmentation and quantitation in", EJNMMI Res, 11(1), pp.105~ (2021)
- Ronneberger O, "U-net:Convolutional networks for biomedical image segmentation", International Conference on Medical Image Computing and Computer-Assisted Intervention (2015), Springer
- Shelhamer E, "Fully convolutional networks for semantic segmentation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), pp.640~651 (2016)
- Chen LC, "Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation", Intell. Robot. Appl, 34, pp.833~851 (2018)
- Chen LC, "Encoder-decoder with atrous separable convolution for semantic image segmentation", Proceedings of the European Conference on Computer Vision(ECCV) (2018)
- Russell B, "Labelme: A database and web-based tool for image annotation", Int. Journal of Computer Vision, 77 (2007)
- Minaee S, "Image segmentation using deep learning : A survey", IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)
- 김정환, "의미론적 영상 분할의 정확도 향상을 위한 에지 정보 기반 후처리 방법", 한국콘텐츠학회 논문지, 21(3), pp.23~32 (2021), 한국콘텐츠학회[DOI]
- Choi HY, "The Study on Ejection Fraction Change According to Patient Position Difference in Gated Blood Pool Scan", The Korean Journal of Nuclear Medicine Technology, 16(1), pp.91~95 (2012)
- Okada R, "Observer variance in the qualitative evaluation of left ventricular wall motion and the quantitation of left ventricular ejection fraction using rest and exercise multigated blood pool imaging", Circulation, 61(1), pp.128~136 (1980)