https://scholars.lib.ntu.edu.tw/handle/123456789/487958
標題: | Automatic Valve Plane Localization in Myocardial Perfusion SPECT/CT by Machine Learning: Anatomic and Clinical Validation | 作者: | Betancur, Julian Rubeaux, Mathieu Fuchs, Tobias A. Otaki, Yuka Arnson, Yoav Slipczuk, Leandro Benz, Dominik C. Germano, Guido Dey, Damini Lin, Chih-Jen Berman, Daniel S. Kaufmann, Philipp A. Slomka, Piotr J. CHIH-JEN LIN |
關鍵字: | Coronary CT angiography; Machine learning; Myocardial perfusion imaging; SPECT quantification; Support vector classification | 公開日期: | 2017 | 卷: | 58 | 期: | 6 | 起(迄)頁: | 961-967 | 來源出版物: | Journal of Nuclear Medicine | 摘要: | Precise definition of the mitral valve plane (VP) during segmentation of the left ventricle for SPECT myocardial perfusion imaging (MPI) quantification often requires manual adjustment, which affects the quantification of perfusion. We developed a machine learning approach using support vector machines (SVM) for automatic VP placement. Methods: A total of 392 consecutive patients undergoing 99mTc-tetrofosmin stress (5 min; mean 6 SD, 350 6 54 MBq) and rest (5 min; 1,024 6 153 MBq) fast SPECT MPI attenuation corrected (AC) by CT and same-day coronary CT angiography were studied; included in the 392 patients were 48 patients who underwent invasive coronary angiography and had no known coronary artery disease. The left ventricle was segmented with standard clinical software (quantitative perfusion SPECT) by 2 experts, adjusting the VP if needed. Two-class SVM models were computed from the expert placements with 10-fold cross validation to separate the patients used for training and those used for validation. SVM probability estimates were used to compute the best VP position. Automatic VP localizations on AC and non-AC images were compared with expert placement on coronary CT angiography. Stress and rest total perfusion deficits and detection of per-vessel obstructive stenosis by invasive coronary angiography were also compared. Results: Bland-Altman 95% confidence intervals (CIs) for VP localization by SVM and experts for AC stress images (bias, 1; 95% CI, 25 to 7 mm) and AC rest images (bias, 1; 95% CI, 27 to 10 mm) were narrower than interexpert 95%CIs for AC stress images (bias, 0; 95% CI, 28 to 8 mm) and AC rest images (bias, 0; 95% CI, 210 to 10 mm) (P , 0.01). Bland-Altman 95% CIs for VP localization by SVM and experts for non-AC stress images (bias, 1; 95% CI, 24 to 6 mm) and non-AC rest images (bias, 2; 95% CI, 27 to 10 mm) were similar to interexpert 95% CIs for non-AC stress images (bias, 0; 95% CI, 26 to 5 mm) and non-AC rest images (bias, 21; 95% CI, 29 to 7 mm) (P was not significant [NS]). For regional detection of obstructive stenosis, ischemic total perfusion deficit areas under the receiver operating characteristic curve for the 2 experts (AUC, 0.79 [95% CI, 0.7-0.87]; AUC, 0.81 [95% CI, 0.73-0.89]) and the SVM (0.82 [0.74-0.9]) for AC data were the same (P 5 NS) and were higher than those for the unadjusted VP (0.63 [0.53-0.73]) (P , 0.01). Similarly, for non-AC data, areas under the receiver operating characteristic curve for the experts (AUC, 0.77 [95% CI, 0.69-0.89]; AUC, 0.8 [95% CI, 0.72-0.88]) and the SVM (0.79 [0.71-0.87]) were the same (P 5 NS) and were higher than those for the unadjusted VP (0.65 [0.56-0.75]) (P , 0.01). Conclusion: Machine learning with SVM allows automatic and accurate VP localization, decreasing user dependence in SPECT MPI quantification. ? 2017 by the Society of Nuclear Medicine and Molecular Imaging. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/487958 | ISSN: | 0161-5505 | DOI: | 10.2967/jnumed.116.179911 | SDG/關鍵字: | iodixanol; tetrofosmin tc 99m; adult; Article; automation; computed tomographic angiography; computed tomography scanner; coronary angiography; coronary artery disease; female; human; image analysis; image segmentation; invasive procedure; major clinical study; male; middle aged; mitral valve plane localization; myocardial perfusion imaging; priority journal; receiver operating characteristic; rest; single photon emission computed tomography-computed tomography; software; SPECT scanner; stress; support vector machine; anatomic landmark; automated pattern recognition; computer assisted diagnosis; diagnostic imaging; evaluation study; machine learning; mitral valve; myocardial perfusion imaging; pathology; procedures; reproducibility; sensitivity and specificity; single photon emission computed tomography-computed tomography; validation study; Anatomic Landmarks; Humans; Image Interpretation, Computer-Assisted; Machine Learning; Middle Aged; Mitral Valve; Myocardial Perfusion Imaging; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Single Photon Emission Computed Tomography Computed Tomography |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。