Adversarial EM for variational deep learning: Application to semi-supervised image quality enhancement in low-dose PET and low-dose CT.

In positron emission tomography (PET) and X-ray computed tomography (CT), reducing radiation dose can cause significant degradation in image quality. For image quality enhancement in low-dose PET and CT, we propose a novel theoretical adversarial and variational deep neural network (DNN) framework relying on expectation maximization (EM) based learning, termed adversarial EM (AdvEM). AdvEM proposes an encoder-decoder architecture with a multiscale latent space, and generalized-Gaussian models enabling datum-specific robust statistical modeling in latent space and image space. The model robustness is further enhanced by including adversarial learning in the training protocol. Unlike typical variational-DNN learning, AdvEM proposes latent-space sampling from the posterior distribution, and uses a Metropolis-Hastings scheme. Unlike existing schemes for PET or CT image enhancement which train using pairs of low-dose images with their corresponding normal-dose versions, we propose a semi-supervised AdvEM (ssAdvEM) framework that enables learning using a small number of normal-dose images. AdvEM and ssAdvEM enable per-pixel uncertainty estimates for their outputs. Empirical analyses on real-world PET and CT data involving many baselines, out-of-distribution data, and ablation studies show the benefits of the proposed framework.

On Patterns of Neuropsychiatric Symptoms in Patients With COVID-19: A Systematic Review of Case Reports.

Coronavirus disease 2019 (COVID-19) has various neuropsychiatric manifestations, including psychotic, mood, anxiety disorders, trauma-related disorders, and cognitive disorders, such as delirium. Although the psychosocial effects of the COVID-19 pandemic contribute to an increase in psychiatric comorbidities, the COVID-19 virus is also an independent risk factor. Previous studies have revealed that the virus can invade the neural tissue, which causes an imbalance of neurotransmitters that cause neuropsychiatric symptoms. The aim of this article is to conduct a systematic review to determine the patterns of neuropsychiatric manifestations of COVID-19, discussing the frequency and its impact on pre-existing psychiatric disorders. Thirty-nine case reports were collected and analyzed for a systematic review. They were full-text, peer-reviewed journal publications from November 2020 to February 2021. Fifty-three patients were included in our study. The most frequent symptom was abnormal/bizarre behavior (50.9%), followed by agitation/aggression (49.1%), and the third most common was altered mental status and delirium (47.2%). Only 48% of our patients had a pre-existing psychiatric disorder, including three not formally diagnosed but displayed psychiatric symptoms prior to the COVID-19 infection. Findings suggest a positive correlation of new-onset psychiatric symptoms with the SARS-CoV-2 virus. However, the exact pathophysiology of the virus itself causing neuropsychiatric manifestations needs to be investigated further.

Cannabis, Schizophrenia Risk and Genetics: A Case Report of a Patient With Homozygous Valine Catechol-O-Methyltransferase Polymorphism.

The question of whether cannabis can trigger schizophrenia continues to be a subject of interest. There has been an increasing focus on identifying potential genetic factors that may predispose cannabis users to develop schizophrenia. One such gene identified in many studies codes for a catechol-O-methyltransferase (COMT) enzyme polymorphism. These studies, however, are limited by the inclusion of patients displaying psychotic symptoms during cannabis intoxication and those who continue to display psychotic symptoms after its cessation. The latter is of interest in truly understanding the risk of cannabis triggering schizophrenia and more studies are needed to clarify the potential relationship. We present the case of a 24-year-old female who presented with psychotic symptoms and was diagnosed with schizophrenia after extensive cannabis use. In addition, she had a homozygous valine COMT polymorphism, a genetic variant thought to be associated with a predisposition for schizophrenia in cannabis users. We discuss the significance of our findings in understanding the relationship between cannabis use and the development of schizophrenia in genetically predisposed individuals.