Taeko Tomimatsu - Graduate School of Health Sciences, Kumamoto University, Kumamoto, Japan
Kousuke Yamshita - Graduate School of Health Sciences, Kumamoto University, Kumamoto, Japan
Takumi Sakata - Graduate School of Health Sciences, Kumamoto University, Kumamoto, Japan
Ryosuke Kamezaki - Department of Central Radiology Kumamoto University Hospital, Kumamoto, Japan
Ryuji Ikeda - Department of Central Radiology Kumamoto University Hospital, Kumamoto, Japan
Shinya Shiraishi - Department of Diagnostic Radiology, Faculty of Life Sciences, Kumamoto University, Kumamoto, Japan
Yoshikazu Uchiyama - Department of Information and Communication Technology, Faculty of Engineering, University of Miyazaki
Shigeki Ito - Department of Medical Imaging, Faculty of Life Sciences, Kumamoto, Kumamoto , Japan

Objective(s): A simple noninvasive microsphere (SIMS) method using ۱۲۳I-IMP and an improved brain uptake ratio (IBUR) method using ۹۹mTc-ECD for the quantitative measurement of regional cerebral blood flow have been recently reported. The input functions of these methods were determined using the administered dose, which was obtained by analyzing the time activity curve of the pulmonary artery (PA) for SIMS and the ascending aorta (AAo) for the IBUR methods for dynamic chest images. If the PA and AAo regions of interest (ROIs) can be determined using deep convolutional neural networks (DCNN) for segmentation, the accuracy of these ROI-setting methods can be improved through simple analytical operations to ensure repeatability and reproducibility. The purpose of this study was to develop new PA and AAo-ROI setting methods using a DCNN (DCNN-ROI method).Methods: A U-Net architecture based on convolutional neural networks was used to determine the PA and AAo candidate regions. Images of ۲۹۰ patients who underwent ۱۲۳I-IMP RI-angiography and ۱۰۸ patients who underwent ۹۹mTc-ECD RI-angiography were used. The PA and AAo-ROI results for the DCNN-ROI method were compared to those obtained using manual methods. The counts for the input function on the PA and AAo-ROI were determined by integrating the area under the curve (AUC) counts of the time-activity curve of PA and AAo-ROI, respectively. The effectiveness of the DCNN-ROI method was elucidated through a comparison with the integrated AUC counts of the DCNN-ROI and the manual ROI.Results: The coincidence ratio for the locations of the PA and AAo-ROI obtained using the DCNN method and that for the manual method was ۱۰۰%. Strong correlations were observed between the AUC counts using the DCNN and manual methods.Conclusion: New ROI- setting programs were developed using a deep convolution neural network DCNN to determine the input functions for the SIMS and IBUR methods. The accuracy of these methods is comparable to that of the manual method.

DCNN, ۱۲۳I-IMP, ۹۹mTc-ECD, rCBF quantification, ROI setting