Quantitative SPECT/CT is potentially useful for more accurate and reliable measurement of glomerular filtration rate (GFR) than conventional planar scintigraphy. However, manual drawing of a volume of interest (VOI) on renal parenchyma in CT images is a labor-intensive and time-consuming task. The aim of this study is to develop a fully automated GFR quantification method based on a deep learning approach to the 3D segmentation of kidney parenchyma in CT. We automatically segmented the kidneys in CT images using the proposed method with remarkably high Dice similarity coefficient relative to the manual segmentation (mean = 0.89). The GFR values derived using manual and automatic segmentation methods were strongly correlated (R2 = 0.96). The absolute difference between the individual GFR values using manual and automatic methods was only 2.90%. Moreover, the two segmentation methods had comparable performance in the urolithiasis patients and kidney donors. Furthermore, both segmentation modalities showed significantly decreased individual GFR in symptomatic kidneys compared with the normal or asymptomatic kidney groups. The proposed approach enables fast and accurate GFR measurement.

Jeong HJ, et al. J Clin Neurol. 2020 Apr;16(2):202-214. https://doi.org/10.3988/jcn.2020.16.2.202

Background: DNA methylation inhibits gene expression by preventing transcription factors from binding to DNA. Functioning of nigrostriatal dopaminergic neurons is influenced by the expression of the dopamine transporter (DAT), and genetic variations in the gene encoding DAT contribute to differences in reward processing. We aimed to investigate the action of DAT methylation on DAT protein expression measured by positron emission tomography (PET). Methods: The emission data were acquired over 90 min with 50 frames after injection of ¹⁸F-FP-CIT using PET. Binding potentials (BP_NDs) of ventral striatum, caudate nucleus, putamen were measured with the simplified reference tissue method. Genomic DNA was extracted from subjects’ blood sampling. Methylation of 4 regions in SLC6A3 gene was assessed using bisulfite pyrosequencing. The mean percentage of methylation (%) for each cluster was calculated by taking the average of all CpG site methylation levels measured within the cluster. Subjects were assessed with the Generalized Reward and Punishment Expectancy Scales (GRAPES) that consists of 30 items related with the reward and punishment that individuals expect for their behaviors. Results: Thirty-five healthy males, with an age range between 20 and 30 years, and a mean age of 24.4 ± 2.7 years, were included in this study. The mean percentage of methylation (%) from cluster C showed a trend of positive correlation with DAT availability of ventral striatum (rho = 0.3712, p = 0.0281), not significant after correction for multiple comparisons, and a significant correlation with GRAPES A: reward expectancy scale (rho = 0.7178, p < 0.0001). Conclusion: DAT methylation from peripheral blood showed a trend of positive correlation with DAT availability of ventral striatum in healthy subjects; however, it was not significant after correction for multiple comparison. The degrees of methylation from cluster C of DAT in peripheral blood were significantly correlated with reward scales of GRAPES A: reward expectancy scale. The association between DAT methylation and DAT expression needs to be investigated further.

The lack of physically measured attenuation maps (μ-maps) for attenuation and scatter correction is an important technical challenge in brain-dedicated stand-alone positron emission tomography (PET) scanners. The accuracy of the calculated attenuation correction is limited by the nonuniformity of tissue composition due to pathologic conditions and the complex structure of facial bones. The aim of this study is to develop an accurate transmission-less attenuation correction method for amyloid-β (Aβ) brain PET studies. We investigated the validity of a deep convolutional neural network trained to produce a CT-derived μ-map (μ-CT) from simultaneously reconstructed activity and attenuation maps using the MLAA (maximum likelihood reconstruction of activity and attenuation) algorithm for Aβ brain PET. The performance of three different structures of U-net models (2D, 2.5D, and 3D) were compared. The U-net models generated less noisy and more uniform μ-maps than MLAA μ-maps. Among the three different U-net models, the patch-based 3D U-net model reduced noise and cross-talk artifacts more effectively. The Dice similarity coefficients between the μ-map generated using 3D U-net and μ-CT in bone and air segments were 0.83 and 0.67. All three U-net models showed better voxel-wise correlation of the μ-maps compared to MLAA. The patch-based 3D U-net model was the best. While the uptake value of MLAA yielded a high percentage error of 20% or more, the uptake value of 3D U-nets yielded the lowest percentage error within 5%. The proposed deep learning approach that requires no transmission data, anatomic image, or atlas/template for PET attenuation correction remarkably enhanced the quantitative accuracy of the simultaneously estimated MLAA μ-maps from Aβ brain PET.