Deep Learning With 18F-Fluorodeoxyglucose-PET Gives Valid Diagnoses for the Uncertain Cases in Memory Impairment of Alzheimer's Disease

Assessment of memory deficits in psychiatric disorders: A systematic literature review

Memory deficits are observed across psychiatric disorders ranging from the prodrome of psychosis to common mental disorders such as anxiety, depression, and dissociative disorders. Memory deficits among patients recovering from psychiatric disorders could be directly related to the primary illness or secondary to the adverse effect of a treatment such as Electroconvulsive Therapy (ECT). The trouble in the meaningful integration of working-memory and episodic memory is the most commonly affected domain that requires routine assessments. An update on the recent trends of methods of assessment of memory deficits is the first step towards understanding and correcting these deficits to target optimum recovery. A systematic literature search was conducted from October 2018 to October 2022 to review the recent methods of assessment of memory deficits in psychiatric disorders. The definition of 'Memory deficit' was operationalized as 'selective processes of memory, commonly required for activities of daily living, and affected among psychiatric disorders resulting in subjective distress and dysfunction'. We included 110 studies, most of them being conducted in western countries on patients with schizophrenia. Other disorders included dementia and mild cognitive impairment. Brief Assessment of Cognition in Schizophrenia, Cambridge Automated Neuropsychological Test Battery, California Verbal Learning Test, Trail Making Test Part A and B, Rey Auditory Verbal Learning Test, Wechsler Memory Scale, Wechsler Adults Intelligence Scale-IV were the most common neuropsychological assessments used. Mini-Mental State Examination and Montreal Cognitive Assessment were the most common bedside assessment tools used while Squire Subjective Memory Questionnaire was commonly used to measure ECT-related memory deficits. The review highlights the recent developments in the field of assessment of memory deficits in psychiatric disorders. Findings recommend and emphasize routine assessment of memory deficits among psychiatric disorders in developing countries especially severe mental illnesses. It remains interesting to see the role of standardized assessments in diagnostic systems given more than a decade of research on memory deficits in psychiatric disorders.

Application of Deep Learning for Prediction of Alzheimer's Disease in PET/MR Imaging

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide. Positron emission tomography/magnetic resonance (PET/MR) imaging is a promising technique that combines the advantages of PET and MR to provide both functional and structural information of the brain. Deep learning (DL) is a subfield of machine learning (ML) and artificial intelligence (AI) that focuses on developing algorithms and models inspired by the structure and function of the human brain's neural networks. DL has been applied to various aspects of PET/MR imaging in AD, such as image segmentation, image reconstruction, diagnosis and prediction, and visualization of pathological features. In this review, we introduce the basic concepts and types of DL algorithms, such as feed forward neural networks, convolutional neural networks, recurrent neural networks, and autoencoders. We then summarize the current applications and challenges of DL in PET/MR imaging in AD, and discuss the future directions and opportunities for automated diagnosis, predictions of models, and personalized medicine. We conclude that DL has great potential to improve the quality and efficiency of PET/MR imaging in AD, and to provide new insights into the pathophysiology and treatment of this devastating disease.