Prognostic Value of Radiomic Analysis Using Pre- and Post-Treatment 18F-FDG-PET/CT in Patients with Laryngeal Cancer and Hypopharyngeal Cancer.

BACKGROUND: The prognostic value of conducting 18F-FDG PET/CT imaging has yielded different results in patients with laryngeal cancer and hypopharyngeal cancer, but these results are controversial, and there is a lack of dedicated studies on each type of cancer. This study aimed to evaluate whether combining radiomic analysis of pre- and post-treatment 18F-FDG PET/CT imaging features and clinical parameters has additional prognostic value in patients with laryngeal cancer and hypopharyngeal cancer. METHODS: From 2008 to 2016, data on patients diagnosed with cancer of the larynx and hypopharynx were retrospectively collected. The patients underwent pre- and post-treatment 18F-FDG PET/CT imaging. The values of ΔPre-Post PET were measured from the texture features. Least absolute shrinkage and selection operator (LASSO) Cox regression was used to select the most predictive features to formulate a Rad-score for both progression-free survival (PFS) and overall survival (OS). Kaplan-Meier curve analysis and Cox regression were employed to assess PFS and OS. Then, the concordance index (C-index) and calibration plot were used to evaluate the performance of the radiomics nomogram. RESULTS: Study data were collected for a total of 91 patients. The mean follow-up period was 71.5 mo. (8.4-147.3). The Rad-score was formulated based on the texture parameters and was significantly associated with both PFS (p = 0.024) and OS (p = 0.009). When predicting PFS, only the Rad-score demonstrated a significant association (HR 2.1509, 95% CI [1.100-4.207], p = 0.025). On the other hand, age (HR 1.116, 95% CI [1.041-1.197], p = 0.002) and Rad-score (HR 33.885, 95% CI [2.891-397.175], p = 0.005) exhibited associations with OS. The Rad-score value showed good discrimination when it was combined with clinical parameters in both PFS (C-index 0.802-0.889) and OS (C-index 0.860-0.958). The calibration plots also showed a good agreement between the observed and predicted survival probabilities. CONCLUSIONS: Combining clinical parameters with radiomics analysis of pre- and post-treatment 18F-FDG PET/CT parameters in patients with laryngeal cancer and hypopharyngeal cancer might have additional prognostic value.

Effects of the APOEɛ4 Allele on the Relationship Between Tau and Amyloid-ß in Early- and Late-Onset Alzheimer's Disease.

BACKGROUND: Little is known regarding the differential effects of the apolipoprotein E (APOE) ɛ4 on the regional topography of amyloid and tau in patients with both early-onset (EOAD) and late-onset Alzheimer's disease (LOAD). OBJECTIVE: To compare the distribution and association of tau, amyloid, and cortical thickness among groups classified by the presence of APOEɛ4 allele and onset age. METHODS: A total of 165 participants including 54 EOAD patients (29 ɛ4-; 25 ɛ4+), 45 LOAD patients (21 ɛ4-; 24 ɛ4+), and 66 age-matched controls underwent 3T MRI, 18F-THK5351 (THK) and 18F-flutemetamol (FLUTE) PET scans, APOE genotyping, and neuropsychological tests. Data for voxel-wise and standardized uptake values from PET scans were analyzed in the context of APOE and age at onset. RESULTS: EOAD ɛ4- patients showed greater THK retention in the association cortices, whereas their EOAD ɛ4+ counterparts had more retention in medial temporal areas. THK topography of LOAD ɛ4+ was similar to EOAD ɛ4 + . THK correlated positively with FLUTE and conversely with mean cortical thickness, being lowest in EOAD ɛ4-, highest in LOAD ɛ4-, and modest in ɛ4+ groups. Even in the APOEɛ4+ groups, THK tended to correlate with FLUTE and mean cortical thickness in the inferior parietal region in EOAD and in the medial temporal region in LOAD. LOAD ɛ4- manifested with prevalent small vessel disease markers and the lowest correlation between THK retention and cognition. CONCLUSION: Our observations suggest the differential effects of the APOEɛ4 on the relationship between tau and amyloid in EOAD and LOAD.

Central metabolites and peripheral parameters associated neuroinflammation in fibromyalgia patients: A preliminary study.

To identify central metabolites and peripheral measures associated with neuroinflammation in fibromyalgia (FM), we scanned [11C]-(R)-PK11195 positron emission tomography and magnetic resonance spectroscopy in FM patients. We measured associations between neurometabolite levels measured by magnetic resonance spectroscopy and the extent of neuroinflammation inferred by the distribution volume ratios of [11C]-(R)-PK11195 positron emission tomography in 12 FM patients and 13 healthy controls. We also examined the associations between peripheral parameters, such as creatinine and C-reactive protein, and neuroinflammation. In FM patients, we found negative correlations between neuroinflammation and the creatine (Cr)/total creatine (tCr; Cr + phosphocreatine) ratios in the right (r = -0.708, P = .015) and left thalamus (r = -0.718, P = .008). In FM patients, negative correlations were apparent between neuroinflammation and the glutamate/tCr ratio in the right insula (r = -0.746, P = .005). In FM patients, we found negative correlations between neuroinflammation in the left thalamus (r = -0.601, P = .039) and left insula (r = -0.598, P = .040) and the blood creatinine levels. Additionally, we found significant correlations of other peripheral measures with neuroinflammation in FM patients. Our results suggest that both central metabolites, such as Cr and glutamate, and peripheral creatinine and other parameters are associated with neuroinflammation in patients with FM.

Prognostic Value of Axillary Lymph Node Texture Parameters Measured by Pretreatment 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in Locally Advanced Breast Cancer with Neoadjuvant Chemotherapy.

BACKGROUND: This study investigated the prognostic value of axillary lymph node (ALN) heterogeneity texture features through 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) in patients with locally advanced breast cancer (LABC). METHODS: We retrospectively analyzed 158 LABC patients with FDG-avid, pathology-proven, metastatic ALN who underwent neoadjuvant chemotherapy (NAC) and curative surgery. Tumor and ALN texture parameters were extracted from pretreatment 18F-FDG PET/CT using Chang-Gung Image Texture Analysis software. The least absolute shrinkage and selection operator regression was performed to select the most significant predictive texture parameters. The predictive impact of texture parameters was evaluated for both progression-free survival and pathologic NAC response. RESULTS: The median follow-up period of 36.8 months and progression of disease (PD) was observed in 36 patients. In the univariate analysis, ALN textures (minimum standardized uptake value (SUV) (p = 0.026), SUV skewness (p = 0.038), SUV bias-corrected Kurtosis (p = 0.034), total lesion glycolysis (p = 0.011)), tumor textures (low-intensity size zone emphasis (p = 0.045), minimum SUV (p = 0.047), and homogeneity (p = 0.041)) were significant texture predictors. On the Cox regression analysis, ALN SUV skewness was an independent texture predictor of PD (p = 0.016, hazard ratio 2.3, 95% confidence interval 1.16-4.58). CONCLUSIONS: ALN texture feature from pretreatment 18F-FDG PET/CT is useful for the prediction of LABC progression.

Limited power of dopamine transporter mRNA mapping for predicting dopamine transporter availability.

Dopamine transporters (DAT) are transmembrane proteins that translocate dopamine from the extracellular space into presynaptic neurons. We aimed to investigate the predictive power of DAT mRNA for DAT protein expression, measured using positron emission tomography (PET). We performed 18 F-FP-CIT PET scans in 35 healthy individuals. Binding potentials (BPND ) from the ventral striatum, caudate nucleus, putamen, and middle frontal, orbitofrontal, cingulate, parietal, and temporal cortices were measured. DAT gene expression data were obtained from the freely available Allen Human Brain Atlas derived from six healthy donors. The auto-correlation of PET-derived BPND s for DAT was intermediate (mean ρ2  = .66) with ρ2 ranging from .0811 to 1. However, the auto-correlation of mRNA expression was weak across the probes with a mean ρ2 of .09-.23. Cross-correlations between PET-derived BPND s and mRNA expression were weak with a mean ρ2 ranging from 0 to .22 across the probes. In conclusion, we observed weak associations between DAT mRNA expression and DAT availability in human brains. Therefore, DAT mRNA mapping may have only limited predictive power for DAT availability in humans. However, the difference in distribution of DAT mRNA and DAT protein may influence this limitation.

Serotonin transporter is negatively associated with body mass index after glucose loading in humans.

Serotonin transporter (SERT) is a presynaptically localized membrane protein that regulates the serotonin transmission via its reuptake of released serotonin. We hypothesized that glucose loading may change SERT availability from brainstem in humans. An intravenous bolus injection of 18F-FP-CIT was administered after the infusion of glucose or placebo (normal saline), and the emission data were acquired over 90 mins in 33 healthy nonobese subjects. For a volume-of-interest-based analysis, an atlas involving midbrain, and pons was applied. SERT availability, binding potential (BPND), were measured via the simplified reference tissue method with a reference of cerebellum. For a voxel-based analysis, statistical parametric mapping 12 was used with parametric BPND images. BPNDs from midbrain (p=0.8937), and pons (p=0.1115) were not different between glucose and placebo loading. Both of BPNDs from midbrain after glucose, and placebo loading were negatively correlated with body mass index (BMI). BMI showed a trend of negative correlation with glucose-loaded BPND from pons, whereas, placebo-loaded BPNDs from pons did not show any significant association with BMI. In conclusion, SERT availability was negatively correlated with BMI after glucose loading in humans. SERT might have a role in eating behavior through the action of insulin. Further studies are needed to elucidate the underlying mechanism of this phenomenon.

SLC6A3 gene polymorphisms are associated with striatal dopamine transporter changes after glucose loading.

We investigated the association between SLC6A3 gene polymorphisms and changes in dopamine transporter (DAT) availability after glucose loading in humans. An intravenous injection of 18 F-FP-CIT was administered after infusion of glucose or placebo, and the emission data were acquired over 90 min in 38 healthy male participants. DAT availability expressed in terms of binding potential (BPND ) was recorded. The 40-bp variable number of tandem repeats (VNTR) in the 3' untranslated region and two single nucleotide polymorphisms (SNPs), rs2652511 and rs2937639, in the SLC6A3 gene were genotyped. Among the 38 participants, those with a VNTR other than 10R/10R (n = 7) were excluded. The alleles of the two SNPs (rs2652511 and rs2937639) appeared to be inherited together in two fixed combinations (C-G or T-A) in 29 of 31 individuals. The BPND in the ventral striatum (VST), caudate nucleus, and putamen was not significantly different after glucose or placebo loading according to genotype. However, BPND s from the caudate nucleus and putamen of all participants with rs2652511 CT/rs2937639 AG (n = 6) were higher after glucose loading. In conclusion, the SLC6A3 gene polymorphism is associated with the changes in DAT availability after glucose loading. DAT availability after glucose or placebo loading in the VST, caudate nucleus, and putamen did not differ according to the SLC6A3 genotype.

Hedonic Rating of Sucrose Is Sub-Regionally Associated with Striatal Dopamine Transporter in Humans.

BACKGROUND: Eating behavior is determined by both homeostatic and hedonic values. OBJECTIVE: We investigated the association of hedonic value with striatal dopamine transporter (DAT) availability sub-regionally. METHOD: An intravenous bolus injection of 18F-FP-CIT was administered after the infusion of glucose or placebo, and the emission data were acquired over 90 min. DAT availability and binding potential (BPND) were measured via the simplified reference tissue method. Subjects were assessed with sensory taste test of sucrose solutions. The "most liked" sucrose concentration (%) was determined as the hedonic rating for sucrose. RESULTS: Twenty healthy males participated in this study. After glucose loading, BPNDs of putamen significantly increased, and those of caudate nucleus showed the increasing trend, while those of ventral striatum were not significantly different. After glucose loading, the "most liked" sucrose concentration (%) was negatively associated with BPNDs of caudate nucleus and showed the trend of positive association with those from ventral striatum. Slopes of regression lines were significantly different according to the sub-regions of striatum. CONCLUSION: We have highlighted that striatal DAT increased after glucose loading in dorsal striatum, not in ventral striatum. These changes of striatal DAT were sub-regionally associated with the hedonic rating of sucrose from each subject.

Striatal DAT availability does not change after supraphysiological glucose loading dose in humans.

Brain dopamine neurotransmission is regulated by the dopamine transporter (DAT), which drives reuptake of extracellular dopamine into the presynaptic neurons. We hypothesized that the glucose loading dose would affect the striatal DAT availability. An i.v. bolus injection of 18F-FP-CIT was administered after infusion of low-dose glucose (300 mg/kg), high-dose glucose (600 mg/kg) or placebo (normal saline). The emission data were acquired over 90 min in 23 healthy male subjects. Substantial increases of binding potential (BPNDs) from ventral striatum (VST), caudate nucleus, and putamen were observed after low-dose glucose loading (+26.0, +87.0, and +37.8%) and after high-dose glucose loading (+10.4, +51.9, and +22.0%). BPNDs of the caudate nucleus and putamen showed significant differences (P = 0.0472 and 0.0221) after placebo, low-dose glucose, and high-dose glucose loading. BPNDs in the caudate nucleus and putamen after placebo, low-dose glucose, and high-dose glucose loading were positively intercorrelated with each other. In conclusion, striatal DAT changes after physiological glucose loading, but not after supraphysiological glucose loading in humans. DAT availabilities after placebo, low-dose glucose, high-dose glucose loading were correlated to each other in the caudate nucleus and putamen, but not in the VST. Therefore, sub-regional variability in DAT regulatory mechanisms mediated by insulin may exist in humans.

Association Between Visceral Fat and Brain Cortical Thickness in the Elderly: A Neuroimaging Study.

BACKGROUND: Despite emerging evidence suggesting that visceral fat may play a major role in obesity-induced neurodegeneration, little evidence exists on the association between visceral fat and brain cortical thickness in the elderly. PURPOSE: We aimed to examine the association between abdominal fat and brain cortical thickness in a Korean elderly population. METHODS: This cross-sectional study included elderly individuals without dementia (n = 316). Areas of visceral fat and subcutaneous fat (cm2) were estimated from computed tomography scans. Regional cortical thicknesses (mm) were obtained by analyzing brain magnetic resonance images. Given the inverted U-shaped relationship between visceral fat area and global cortical thickness (examined using a generalized additive model), visceral fat area was categorized into quintiles, with the middle quintile being the reference group. A generalized linear model was built to explore brain regions associated with visceral fat. The same approach was used for subcutaneous fat. RESULTS: The mean (standard deviation) age was 67.6 (5.0) years. The highest quintile (vs. the middle quintile) group of visceral fat area had reduced cortical thicknesses in the global [ß = -0.04 mm, standard error (SE) = 0.02 mm, p = 0.004], parietal (ß = -0.04 mm, SE = 0.02 mm, p = 0.01), temporal (ß = -0.05 mm, SE = 0.02 mm, p = 0.002), cingulate (ß = -0.06 mm, SE = 0.02 mm, p = 0.01), and insula lobes (ß = -0.06 mm, SE = 0.03 mm, p = 0.02). None of the regional cortical thicknesses significantly differed between the highest and the middle quintile groups of subcutaneous fat area. CONCLUSION: The findings suggest that a high level of visceral fat, but not subcutaneous fat, is associated with a reduced cortical thickness in the elderly.

No association of Brain-derived neurotrophic factor with striatal dopamine transporter availability in healthy subjects.

OBJECTIVE: Brain-derived neurotrophic factor (BDNF) is a neurotrophin that plays a key role in brain plasticity, synaptic function, neuronal survival, learning, and memory formation. We aimed to investigate the association of BDNF with dopamine transporter (DAT) availabilities measured by positron emission tomography (PET) in healthy subjects. METHODS: Thirty-five healthy, male subjects without brain injury, neuropsychological disorders were included in this study. The emission data were acquired over 90 mins with 50 frames after injection of 18F-FP-CIT using PET. Binding potentials (BPNDs) of ventral striatum (VST), caudate nucleus, putamen were measured with the simplified reference tissue method. The serum BDNF level (pg/mL) was measured through enzyme-linked immunosorbent assay method. RESULTS: Thirty-five healthy males with a mean age of 24.4 ± 2.7 years were included in this study. Multiple regression was done to investigate the association between striatal BPNDs from VST, caudate nucleus, putamen and serum BDNF after adjusting for age. None of striatal BPNDs from VST (p=0.8450), caudate nucleus (p=0.4783), and putamen (p=0.7994) were associated with serum BDNF. CONCLUSION: Striatal DAT availabilities measured from PET were not associated with the serum BDNF in healthy subjects.

The association of DAT gene methylation with striatal DAT availability in healthy subjects.

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 (BPNDs) 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.

Data-driven respiratory phase-matched PET attenuation correction without CT.

We propose a deep learning-based data-driven respiratory phase-matched gated-PET attenuation correction (AC) method that does not need a gated-CT. The proposed method is a multi-step process that consists of data-driven respiratory gating, gated attenuation map estimation using maximum-likelihood reconstruction of attenuation and activity (MLAA) algorithm, and enhancement of the gated attenuation maps using convolutional neural network (CNN). The gated MLAA attenuation maps enhanced by the CNN allowed for the phase-matched AC of gated-PET images. We conducted a non-rigid registration of the gated-PET images to generate motion-free PET images. We trained the CNN by conducting a 3D patch-based learning with 80 oncologic whole-body18F-fluorodeoxyglucose (18F-FDG) PET/CT scan data and applied it to seven regional PET/CT scans that cover the lower lung and upper liver. We investigated the impact of the proposed respiratory phase-matched AC of PET without utilizing CT on tumor size and standard uptake value (SUV) assessment, and PET image quality (%STD). The attenuation corrected gated and motion-free PET images generated using the proposed method yielded sharper organ boundaries and better noise characteristics than conventional gated and ungated PET images. A banana artifact observed in a phase-mismatched CT-based AC was not observed in the proposed approach. By employing the proposed method, the size of tumor was reduced by 12.3% and SUV90%was increased by 13.3% in tumors with larger movements than 5 mm. %STD of liver uptake was reduced by 11.1%. The deep learning-based data-driven respiratory phase-matched AC method improved the PET image quality and reduced the motion artifacts.

Effects of Alzheimer's and Vascular Pathologies on Structural Connectivity in Early- and Late-Onset Alzheimer's Disease.

Early- and late-onset Alzheimer's disease (AD) patients often exhibit distinct features. We sought to compare overall white matter connectivity and evaluate the pathological factors (amyloid, tau, and vascular pathologies) that affect the disruption of connectivity in these two groups. A total of 50 early- and 38 late-onset AD patients, as well as age-matched cognitively normal participants, were enrolled and underwent diffusion-weighted magnetic resonance imaging to construct fractional anisotropy-weighted white matter connectivity maps. [18F]-THK5351 PET, [18F]-Flutemetamol PET, and magnetic resonance imaging were used for the evaluation of tau and related astrogliosis, amyloid, and small vessel disease markers (lacunes and white matter hyperintensities). Cluster-based statistics was performed for connectivity comparisons and correlation analysis between connectivity disruption and the pathological markers. Both patient groups exhibited significantly disrupted connectivity compared to their control counterparts with distinct patterns. Only THK retention was related to connectivity disruption in early-onset AD patients, and this disruption showed correlations with most cognitive scores, while late-onset AD patients had disrupted connectivity correlated with amyloid deposition, white matter hyperintensities, and lacunes in which only a few cognitive scores showed associations. These findings suggest that the pathogenesis of connectivity disruption and its effects on cognition are distinct between EOAD and LOAD.

Abnormal neuroinflammation in fibromyalgia and CRPS using [11C]-(R)-PK11195 PET.

PURPOSE: Fibromyalgia (FM) and complex regional pain syndrome (CRPS) share many pathological mechanisms related to chronic pain and neuroinflammation, which may contribute to the multifactorial pathological mechanisms in both FM and CRPS. The aim of this study was to assess neuroinflammation in FM patients compared with that in patients with CRPS and healthy controls. METHODS: Neuroinflammation was measured as the distribution volume ratio (DVR) of [11C]-(R)-PK11195 positron emission tomography (PET) in 12 FM patients, 11 patients with CRPS and 15 healthy controls. RESULTS: Neuroinflammation in FM patients was significantly higher in the left pre (primary motor cortex) and post (primary somatosensory cortex) central gyri (p < 0.001), right postcentral gyrus (p < 0.005), left superior parietal and superior frontal gyri (p < 0.005), left precuneus (p < 0.01), and left medial frontal gyrus (p = 0.036) compared with healthy controls. Furthermore, the DVR of [11C]-(R)-PK11195 in FM patients demonstrated decreased neuroinflammation in the medulla (p < 0.005), left superior temporal gyrus (p < 0.005), and left amygdala (p = 0.020) compared with healthy controls. CONCLUSIONS: To the authors' knowledge, this report is the first to describe abnormal neuroinflammation levels in the brains of FM patients compared with that in patients with CRPS using [11C]-(R)-PK11195 PET. The results suggested that abnormal neuroinflammation can be an important pathological factor in FM. In addition, the identification of common and different critical regions related to abnormal neuroinflammation in FM, compared with patients with CRPS and healthy controls, may contribute to improved diagnosis and the development of effective medical treatment for patients with FM.

Development and Initial Results of a Brain PET Insert for Simultaneous 7-Tesla PET/MRI Using an FPGA-Only Signal Digitization Method.

In study, we developed a positron emission tomography (PET) insert for simultaneous brain imaging within 7-Tesla (7T) magnetic resonance (MR) imaging scanners. The PET insert has 18 sectors, and each sector is assembled with two-layer depth-of-interaction (DOI)-capable high-resolution block detectors. The PET scanner features a 16.7-cm-long axial field-of-view (FOV) to provide entire human brain images without bed movement. The PET scanner early digitizes a large number of block detector signals at a front-end data acquisition (DAQ) board using a novel field-programmable gate array (FPGA)-only signal digitization method. All the digitized PET data from the front-end DAQ boards are transferred using gigabit transceivers via non-magnetic high-definition multimedia interface (HDMI) cables. A back-end DAQ system provides a common clock and synchronization signal for FPGAs over the HDMI cables. An active cooling system using copper heat pipes is applied for thermal regulation. All the 2.17-mm-pitch crystals with two-layer DOI information were clearly identified in the block detectors, exhibiting a system-level energy resolution of 12.6%. The PET scanner yielded clear hot-rod and Hoffman brain phantom images and demonstrated 3D PET imaging capability without bed movement. We also performed a pilot simultaneous PET/MR imaging study of a brain phantom. The PET scanner achieved a spatial resolution of 2.5 mm at the center FOV (NU 4) and a sensitivity of 18.9 kcps/MBq (NU 2) and 6.19% (NU 4) in accordance with the National Electrical Manufacturers Association (NEMA) standards.

Deep learning-Based 3D inpainting of brain MR images.

The detailed anatomical information of the brain provided by 3D magnetic resonance imaging (MRI) enables various neuroscience research. However, due to the long scan time for 3D MR images, 2D images are mainly obtained in clinical environments. The purpose of this study is to generate 3D images from a sparsely sampled 2D images using an inpainting deep neural network that has a U-net-like structure and DenseNet sub-blocks. To train the network, not only fidelity loss but also perceptual loss based on the VGG network were considered. Various methods were used to assess the overall similarity between the inpainted and original 3D data. In addition, morphological analyzes were performed to investigate whether the inpainted data produced local features similar to the original 3D data. The diagnostic ability using the inpainted data was also evaluated by investigating the pattern of morphological changes in disease groups. Brain anatomy details were efficiently recovered by the proposed neural network. In voxel-based analysis to assess gray matter volume and cortical thickness, differences between the inpainted data and the original 3D data were observed only in small clusters. The proposed method will be useful for utilizing advanced neuroimaging techniques with 2D MRI data.