Search

Objective(s): A simple noninvasive microsphere (SIMS) method using 123I-IMP and an improved brain uptake ratio (IBUR) method using 99mTc-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 290 patients who underwent 123I-IMP RI-angiography and 108 patients who underwent 99mTc-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 100%. 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.

Objective(s): To develop the following three attenuation correction (AC) methods for brain 18F-fluorodeoxyglucose-positron emission tomography (PET), using deep learning, and to ascertain their precision levels: (i) indirect method; (ii) direct method; and (iii) direct and high-resolution correction (direct+HRC) method.Methods: We included 53 patients who underwent cranial magnetic resonance imaging (MRI) and computed tomography (CT) and 27 patients who underwent cranial MRI, CT, and PET. After fusion of the magnetic resonance, CT, and PET images, resampling was performed to standardize the field of view and matrix size and prepare the data set. In the indirect method, synthetic CT (SCT) images were generated, whereas in the direct and direct+HRC methods, a U-net structure was used to generate AC images. In the indirect method, attenuation correction was performed using SCT images generated from MRI findings using U-net instead of CT images. In the direct and direct+HRC methods, AC images were generated directly from non-AC images using U-net, followed by image evaluation. The precision levels of AC images generated using the indirect and direct methods were compared based on the normalized mean squared error (NMSE) and structural similarity (SSIM).Results: Visual inspection revealed no difference between the AC images prepared using CT-based attenuation correction and those prepared using the three methods. The NMSE increased in the order indirect, direct, and direct+HRC methods, with values of 0.281×10-3, 4.62×10-3, and 12.7×10-3, respectively. Moreover, the SSIM of the direct+HRC method was 0.975.Conclusion: The direct+HRC method enables accurate attenuation without CT exposure and high-resolution correction without dedicated correction programs.