Generative Adversarial Network-Enhanced Ultra-Low-Dose [18F]-PI-2620 τ PET/MRI in Aging and Neurodegenerative Populations

BACKGROUND AND PURPOSE

With the utility of hybrid τ PET/MR imaging in the screening, diagnosis, and follow-up of individuals with neurodegenerative diseases, we investigated whether deep learning techniques can be used in enhancing ultra-low-dose [18F]-PI-2620 τ PET/MR images to produce diagnostic-quality images.

MATERIALS AND METHODS

Forty-four healthy aging participants and patients with neurodegenerative diseases were recruited for this study, and [18F]-PI-2620 τ PET/MR data were simultaneously acquired. A generative adversarial network was trained to enhance ultra-low-dose τ images, which were reconstructed from a random sampling of 1/20 (approximately 5% of original count level) of the original full-dose data. MR images were also used as additional input channels. Region-based analyses as well as a reader study were conducted to assess the image quality of the enhanced images compared with their full-dose counterparts.

RESULTS

The enhanced ultra-low-dose τ images showed apparent noise reduction compared with the ultra-low-dose images. The regional standard uptake value ratios showed that while, in general, there is an underestimation for both image types, especially in regions with higher uptake, when focusing on the healthy-but-amyloid-positive population (with relatively lower τ uptake), this bias was reduced in the enhanced ultra-low-dose images. The radiotracer uptake patterns in the enhanced images were read accurately compared with their full-dose counterparts.

CONCLUSIONS

The clinical readings of deep learning-enhanced ultra-low-dose τ PET images were consistent with those performed with full-dose imaging, suggesting the possibility of reducing the dose and enabling more frequent examinations for dementia monitoring.

Anhedonia and general distress show dissociable ventromedial prefrontal cortex connectivity in major depressive disorder

Anhedonia, the reduced ability to experience pleasure in response to otherwise rewarding stimuli, is a core symptom of major depressive disorder (MDD). Although the posterior ventromedial prefrontal cortex (pVMPFC) and its functional connections have been consistently implicated in MDD, their roles in anhedonia remain poorly understood. Furthermore, it is unknown whether anhedonia is primarily associated with intrinsic 'resting-state' pVMPFC functional connectivity or an inability to modulate connectivity in a context-specific manner. To address these gaps, a pVMPFC region of interest was first identified using activation likelihood estimation meta-analysis. pVMPFC connectivity was then examined in relation to anhedonia and general distress symptoms of depression, using both resting-state and task-based functional magnetic resonance imaging involving pleasant music, in current MDD and healthy control groups. In MDD, pVMPFC connectivity was negatively correlated with anhedonia but not general distress during music listening in key reward- and emotion-processing regions, including nucleus accumbens, ventral tegmental area/substantia nigra, orbitofrontal cortex and insula, as well as fronto-temporal regions involved in tracking complex sound sequences, including middle temporal gyrus and inferior frontal gyrus. No such dissociations were observed in the healthy controls, and resting-state pVMPFC connectivity did not dissociate anhedonia from general distress in either group. Our findings demonstrate that anhedonia in MDD is associated with context-specific deficits in pVMPFC connectivity with the mesolimbic reward system when encountering pleasurable stimuli, rather than a static deficit in intrinsic resting-state connectivity. Critically, identification of functional circuits associated with anhedonia better characterizes MDD heterogeneity and may help track of one of its core symptoms.

Changes in matrix metalloproteinase (MMP)-2 and MMP-9 in the fetal amnion and chorion during gestation and at term and preterm labor

Increased matrix metalloproteinase (MMP)-9 proteolytic activity is associated with term birth, preterm birth and premature rupture of membranes. However, most studies show no changes with MMP-2, which binds tightly to cell and matrix proteins. We hypothesized better protein extraction would reveal new MMP patterns. Human amnion and chorion were collected from 25 patients at preterm or term, extracted with 2% SDS (a high concentration), and the MMP protein levels and pro-enzyme activities were determined by Western immunoblotting and zymography. MMP-2 protein and MMP-2 and -9 pro-enzyme activities in the amnion increased significantly (p<0.05) with labor at term, and were higher than at preterm labor (p<0.05), when extracted with high SDS concentration. There were no changes in chorion MMPs under any condition. These associations suggest MMP-2 may be another regulator of membrane rupture and other labor-associated mechanisms at term parturition, and its role(s) should be examined further.