Deep learning (DL) algorithms have achieved important successes in data analysis tasks, thanks to their capability of revealing complex patterns in data. With the advance of new sensors, data storage, and processing hardware, DL algorithms start dominating various fields including neuropsychiatry. There are many types of DL algorithms for different data types from survey data to functional magnetic resonance imaging scans. Because of limitations in diagnosing, estimating prognosis and treatment response of neuropsychiatric disorders; DL algorithms are becoming promising approaches. In this review, we aim to summarize the most common DL algorithms and their applications in neuropsychiatry and also provide an overview to guide the researchers in choosing the proper DL architecture for their research.

Deep learning (DL) algorithms have achieved important successes in data analysis tasks, thanks to their capability of revealing complex patterns in data. With the advance of new sensors, data storage, and processing hardware, DL algorithms start dominating various fields including neuropsychiatry. There are many types of DL algorithms for different data types from survey data to functional magnetic resonance imaging scans. Because of limitations in diagnosing, estimating prognosis and treatment response of neuropsychiatric disorders; DL algorithms are becoming promising approaches. In this review, we aim to summarize the most common DL algorithms and their applications in neuropsychiatry and also provide an overview to guide the researchers in choosing the proper DL architecture for their research.

Purpose: Since the treatment strategy for benign and malignant pancreatic lesions differ, we aimed to evaluate the clinical value of PET/CT in the diagnosis and management of pancreatic lesions. Methods: Ninety patients who had a histologically confirmed pancreatic lesion were studied. Receiver operating characteristic (ROC) curve analysis was used to investigate the ability of PET/CT to differentiate malignant lesions from benign tumors. Results: The malignant and benign groups comprised 64 and 26 patients, respectively. Despite the similarity in the size of primary tumors (P = 0.588), the mean maximum standardized uptake values (SUVmax) obtained from PET/CT imaging were significantly higher in malignant lesions (9.36 ± 5.9) than those of benign tumors (1.04 ± 2.6, P < 0.001). ROC analysis showed that the optimal SUVmax cutoff value for differentiating malignant lesions (to an accuracy of 91%; 95% confidence interval, 83%–98%) from benign tumors was 3.9 (sensitivity, 92.2%; specificity, 84.6%). Conclusion PET/CT evaluation of pancreatic lesions confers advantages including fine assessment of malignant potential with high sensitivity and accuracy using a threshold SUVmax value of 3.9.