Combination of [18F]FDG and [18F]PSMA-1007 PET/CT predicts tumour aggressiveness at staging and biochemical failure postoperatively in patients with prostate cancer.

PURPOSE: [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography/computed tomography (PET/CT) has limitations in prostate cancer (PCa) detection owing to low glycolysis in the primary tumour. Recently, prostate-specific membrane antigen (PSMA) PET/CT has been useful for biochemical failure detection and radioligand therapy (RLT) guidance. However, few studies have evaluated its use in primary prostate tumours using PSMA and [18F]FDG PET/CT. This study aimed to evaluate [18F]PSMA-1007 and [18F]FDG PET/CT for primary tumour detection and understand the association of metabolic heterogeneity with clinicopathological characteristics at staging and postoperatively. METHOD: This prospective study included 42 index tumours (27 acinar and 15 ductal-dominant) in 42 patients who underwent [18F]PSMA-1007 and [18F]FDG PET/CT and subsequent radical prostatectomy. All patients were followed for a median of 26 mo, and serum prostate-specific antigen levels were measured every 3 mo to evaluate biochemical failure. One-way analysis of variance, Tukey's multiple comparison test, and Fisher's exact test were performed. RESULTS: All 42 index tumours were detected on [18F]PSMA-1007 PET/CT, whereas only 15 were detected on [18F]FDG PET/CT (62.3% vs. 37.7%, p < 0.0001). A high SUVmax for [18F]PSMA-1007 was observed in tumours with high Gleason scores (GS 6-7 vs. GS 8-10; 12.1 vs. 20.1, p < 0.05). Tumours with [18F]FDG uptake were mostly ductal dominant (acinar-dominant 4/27; ductal-dominant; 11/15, p < 0.001), with lower [18F]PSMA-1007 uptake than tumours without [18F]FDG uptake (SUVmax 16.58 vs. 11.19, p < 0.001). There were 16.6% (7/42) of patients with pStage IV in whom the primary tumours were [18F]FDG positive. Biochemical failure was observed in 14.8% (4/27) of patients with [18F]FDG negative tumours but in 53.3% (8/15) of patients with [18F]FDG positive tumours (p = 0.013). CONCLUSIONS: [18F]PSMA-1007 PET/CT was superior to [18F]FDG PET/CT in detecting primary PCa. In contrast, tumours with [18F]FDG uptake are associated with larger size, a ductal-dominant type, and likely to undergo metastasis at staging and biochemical failure postoperatively.

Breathing-Associated Facial Region Segmentation for Thermal Camera-Based Indirect Breathing Monitoring.

Breathing can be measured in a non-contact method using a thermal camera. The objective of this study investigates non-contact breathing measurements using thermal cameras, which have previously been limited to measuring the nostril only from the front where it is clearly visible. The previous method is challenging to use for other angles and frontal views, where the nostril is not well-represented. In this paper, we defined a new region called the breathing-associated-facial-region (BAFR) that reflects the physiological characteristics of breathing, and extract breathing signals from views of 45 and 90 degrees, including the frontal view where the nostril is not clearly visible. Experiments were conducted on fifteen healthy subjects in different views, including frontal with and without nostril, 45-degree, and 90-degree views. A thermal camera (A655sc model, FLIR systems) was used for non-contact measurement, and biopac (MP150, Biopac-systems-Inc) was used as a chest breathing reference. The results showed that the proposed algorithm could extract stable breathing signals at various angles and views, achieving an average breathing cycle accuracy of 90.9% when applied compared to 65.6% without proposed algorithm. The average correlation value increases from 0.587 to 0.885. The proposed algorithm can be monitored in a variety of environments and extract the BAFR at diverse angles and views.

Visualizing reactive astrocyte-neuron interaction in Alzheimer's disease using 11C-acetate and 18F-FDG.

Reactive astrogliosis is a hallmark of Alzheimer's disease (AD). However, a clinically validated neuroimaging probe to visualize the reactive astrogliosis is yet to be discovered. Here, we show that PET imaging with 11C-acetate and 18F-fluorodeoxyglucose (18F-FDG) functionally visualizes the reactive astrocyte-mediated neuronal hypometabolism in the brains with neuroinflammation and AD. To investigate the alterations of acetate and glucose metabolism in the diseased brains and their impact on the AD pathology, we adopted multifaceted approaches including microPET imaging, autoradiography, immunohistochemistry, metabolomics, and electrophysiology. Two AD rodent models, APP/PS1 and 5xFAD transgenic mice, one adenovirus-induced rat model of reactive astrogliosis, and post-mortem human brain tissues were used in this study. We further curated a proof-of-concept human study that included 11C-acetate and 18F-FDG PET imaging analyses along with neuropsychological assessments from 11 AD patients and 10 healthy control subjects. We demonstrate that reactive astrocytes excessively absorb acetate through elevated monocarboxylate transporter-1 (MCT1) in rodent models of both reactive astrogliosis and AD. The elevated acetate uptake is associated with reactive astrogliosis and boosts the aberrant astrocytic GABA synthesis when amyloid-ß is present. The excessive astrocytic GABA subsequently suppresses neuronal activity, which could lead to glucose uptake through decreased glucose transporter-3 in the diseased brains. We further demonstrate that 11C-acetate uptake was significantly increased in the entorhinal cortex, hippocampus and temporo-parietal neocortex of the AD patients compared to the healthy controls, while 18F-FDG uptake was significantly reduced in the same regions. Additionally, we discover a strong correlation between the patients' cognitive function and the PET signals of both 11C-acetate and 18F-FDG. We demonstrate the potential value of PET imaging with 11C-acetate and 18F-FDG by visualizing reactive astrogliosis and the associated neuronal glucose hypometablosim for AD patients. Our findings further suggest that the acetate-boosted reactive astrocyte-neuron interaction could contribute to the cognitive decline in AD.

Interrelation of striatal dopamine, brain metabolism and cognition in dementia with Lewy bodies.

Dementia with Lewy bodies (DLB), the second most common neurodegenerative dementia, is characterized by cognitive decline, fluctuation of cognition and alertness, visual hallucinations, rapid eye movement sleep behaviour disorder and parkinsonism. Imaging biomarkers are of great importance in diagnosing patients with DLB and associated with characteristic clinical features including cognitive decline. In this study, we investigate interrelation between nigrostriatal dopamine depletion, brain metabolism and cognition in DLB. We enrolled 55 patients with probable DLB (15 with prodromal DLB and 40 with DLB) and 13 healthy controls. All subjects underwent N-(3-[18F]fluoropropyl)-2ß-carbomethoxy-3ß-(4-iodophenyl) nortropane PET/CT, 18F-fluorodeoxyglucose PET/CT, 18F-florbetaben PET/CT and detailed neuropsychological testing. The relationship between striatal dopamine transporter availability and regional brain metabolism was assessed using general linear models, and the effect of striatal dopamine transporter availability and brain metabolism on specific cognitive function was evaluated by multivariate linear regression analysis. Path analyses were used to evaluate the relationship between striatal dopamine transporter availability, fluorodeoxyglucose uptake and cognitive function scores. Additionally, a linear mixed model was used to investigate the association between baseline dopamine transporter availability or brain metabolism and longitudinal cognitive decline. Independent of amyloid deposition, caudate and putamen dopamine transporter availabilities were positively correlated with brain metabolism in the DLB-specific hypometabolic regions, most prominently in the occipital and lateral parietal cortices. Both reduced caudate dopamine and brain hypometabolism were associated with low z-scores of Rey-Osterrieth Complex Figure Test copy, Seoul Verbal Learning Test immediate recall and Controlled Oral Word Association Test (COWAT)-animal. Path analyses showed that the effect of reduced caudate dopamine on the Rey-Osterrieth Complex Figure Test copy z-score was completely mediated by brain hypometabolism, whereas it affected the Seoul Verbal Learning Test immediate recall z-score both directly and via the mediation of brain hypometabolism. Caudate dopamine depletion was directly associated with the COWAT-animal z-score, not mediated by brain hypometabolism. Both baseline caudate dopamine transporter availability and brain hypometabolism were associated with longitudinal cognitive decline, with brain hypometabolism being more relevant. Our findings suggest that in DLB, striatal dopaminergic depletion and brain hypometabolism are closely related, and they differentially affect cognitive dysfunction in an item-specific manner. Additionally, brain hypometabolism would be more relevant to longitudinal cognitive outcomes than striatal dopaminergic degeneration.

Deep learning-based amyloid PET positivity classification model in the Alzheimer's disease continuum by using 2-[18F]FDG PET.

BACKGROUND: Considering the limited accessibility of amyloid position emission tomography (PET) in patients with dementia, we proposed a deep learning (DL)-based amyloid PET positivity classification model from PET images with 2-deoxy-2-[fluorine-18]fluoro-D-glucose (2-[18F]FDG). METHODS: We used 2-[18F]FDG PET datasets from the Alzheimer's Disease Neuroimaging Initiative and Korean Brain Aging Study for the Early diagnosis and prediction of Alzheimer's disease for model development. Moreover, we used an independent dataset from another hospital. A 2.5-D deep learning architecture was constructed using 291 submodules and three axes images as the input. We conducted the voxel-wise analysis to assess the regions with substantial differences in glucose metabolism between the amyloid PET-positive and PET-negative participants. This facilitated an understanding of the deep model classification. In addition, we compared these regions with the classification probability from the submodules. RESULTS: There were 686 out of 1433 (47.9%) and 50 out of 100 (50%) amyloid PET-positive participants in the training and internal validation datasets and the external validation datasets, respectively. With 50 times iterations of model training and validation, the model achieved an AUC of 0.811 (95% confidence interval (CI) of 0.803-0.819) and 0.798 (95% CI, 0.789-0.807) on the internal and external validation datasets, respectively. The area under the curve (AUC) was 0.860 when tested with the model with the highest value (0.864) on the external validation dataset. Moreover, it had 75.0% accuracy, 76.0% sensitivity, 74.0% specificity, and 75.0% F1-score. We found an overlap between the regions within the default mode network, thus generating high classification values. CONCLUSION: The proposed model based on the 2-[18F]FDG PET imaging data and a DL framework might successfully classify amyloid PET positivity in clinical practice, without performing amyloid PET, which have limited accessibility.

Segmentation of white matter hyperintensities on 18F-FDG PET/CT images with a generative adversarial network.

PURPOSE: White matter hyperintensities (WMH) are typically segmented using MRI because WMH are hardly visible on 18F-FDG PET/CT. This retrospective study was conducted to segment WMH and estimate their volumes from 18F-FDG PET with a generative adversarial network (WhyperGAN). METHODS: We selected patients whose interval between MRI and FDG PET/CT scans was within 3 months, from January 2017 to December 2018, and classified them into mild, moderate, and severe groups by following the semiquantitative rating method of Fazekas. For each group, 50 patients were selected, and of them, we randomly selected 35 patients for training and 15 for testing. WMH were automatically segmented from FLAIR MRI with manual adjustment. Patches of WMH were extracted from 18F-FDG PET and segmented MRI. WhyperGAN was compared with H-DenseUnet, a deep learning method widely used for segmentation tasks, for segmentation performance based on the dice similarity coefficient (DSC), recall, and average volume differences (AVD). For volume estimation, the predicted WMH volumes from PET were compared with ground truth volumes. RESULTS: The DSC values were associated with WMH volumes on MRI. For volumes >60 mL, the DSC values were 0.751 for WhyperGAN and 0.564 for H-DenseUnet. For volumes ≤60 mL, the DSC values rapidly decreased as the volume decreased (0.362 for WhyperGAN vs. 0.237 for H-DenseUnet). For recall, WhyperGAN achieved the highest value in the severe group (0.579 for WhyperGAN vs. 0.509 for H-DenseUnet). For AVD, WhyperGAN achieved the lowest score in the severe group (0.494 for WhyperGAN vs. 0.941 for H-DenseUnet). For the WMH volume estimation, WhyperGAN performed better than H-DenseUnet and yielded excellent correlation coefficients (r = 0.998, 0.983, and 0.908 in the severe, moderate, and mild group). CONCLUSIONS: Although limited by visual analysis, the WhyperGAN based can be used to automatically segment and estimate volumes of WMH from 18F-FDG PET/CT. This would increase the usefulness of 18F-FDG PET/CT for the evaluation of WMH in patients with cognitive impairment.

Semantic Segmentation of White Matter in FDG-PET Using Generative Adversarial Network.

In the diagnosis of neurodegenerative disorders, F-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) is used for its ability to detect functional changes at early stages of disease process. However, anatomical information from another modality (CT or MRI) is still needed to properly interpret and localize the radiotracer uptake due to its low spatial resolution. Lack of structural information limits segmentation and accurate quantification of the 18F-FDG PET/CT. The correct segmentation of the brain compartment in 18F-FDG PET/CT will enable the quantitative analysis of the 18F-FDG PET/CT scan alone. In this paper, we propose a method to segment white matter in 18F-FDG PET/CT images using generative adversarial network (GAN). The segmentation result of GAN model was evaluated using evaluation parameters such as dice, AUC-PR, precision, and recall. It was also compared with other deep learning methods. As a result, the proposed method achieves superior segmentation accuracy and reliability compared with other deep learning methods.

Slice-selective learning for Alzheimer's disease classification using a generative adversarial network: a feasibility study of external validation.

PURPOSE: The aim of this feasibility study was to use slice selective learning using a Generative Adversarial Network for external validation. We aimed to build a model less sensitive to PET imaging acquisition environment, since differences in environments negatively influence network performance. To investigate the slice performance, each slice evaluation was performed. METHODS: We trained our model using a 18F-fluorodeoxyglucose ([18F]FDG) PET/CT dataset obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and tested the model with a Severance Hospital dataset. We applied slice selective learning to reduce computational cost and to extract unbiased features. We extracted features of Alzheimer's disease (AD) and normal cognitive (NC) condition using a Boundary Equilibrium Generative Adversarial Network (BEGAN) for stable convergence. Then, we utilized these features to train a support vector machine (SVM) classifier to distinguish AD from NC. RESULTS: The slice range that covered the posterior cingulate cortex (PCC) using double slices showed the best performance. The accuracy, sensitivity, and specificity of our proposed network was 94.33%, 91.78%, and 97.06% using the Severance dataset and 94.82%, 92.11%, and 97.45% using the ADNI dataset. The performance on the two independent datasets showed no statistical difference (p > 0.05). Moreover, there was a statistical difference in the performance between using two slices and one slice as input (p < 0.05). CONCLUSIONS: Our model learned the generalized features of AD and NC for external validation when appropriate slices were selected. This study showed the feasibility of this model with consistent performance when tested using datasets acquired from a variety of image-acquisition environments.