Search

Artificial intelligence (AI) models have received considerable attention in recent years for their ability to identify optical coherence tomography (OCT) biomarkers with clinical diagnostic potential and predict disease progression. This study aims to externally validate a deep learning (DL) algorithm by comparing its segmentation of retinal layers and fluid with a gold-standard method for manually adjusting the automatic segmentation of the Heidelberg Spectralis HRA + OCT software Version 6.16.8.0. A total of sixty OCT images of healthy subjects and patients with intermediate and exudative age-related macular degeneration (AMD) were included. A quantitative analysis of the retinal thickness and fluid area was performed, and the discrepancy between these methods was investigated. The results showed a moderate-to-strong correlation between the metrics extracted by both software types, in all the groups, and an overall near-perfect area overlap was observed, except for in the inner segment ellipsoid (ISE) layer. The DL system detected a significant difference in the outer retinal thickness across disease stages and accurately identified fluid in exudative cases. In more diseased eyes, there was significantly more disagreement between these methods. This DL system appears to be a reliable method for accessing important OCT biomarkers in AMD. However, further accuracy testing should be conducted to confirm its validity in real-world settings to ultimately aid ophthalmologists in OCT imaging management and guide timely treatment approaches. [ABSTRACT FROM AUTHOR]

The existence of crime-related racial stereotypes has been well documented. People tend to associate certain groups with specific crimes, which, in turn, impacts criminal-sentencing decisions through the perceptions of crime severity. This evidence calls for regular updating of rating norms combining these variables. With this objective, and given that most of the normative studies provide norms for a small number of crimes and/or with an insufficient number of participants, a new norming study was conducted. Furthermore, norms from European countries are absent, and the existing ones (mostly with USA-based populations) do not simultaneously examine crime stereotypicality and crime severity. The Crime Stereotypicality and Severity Database (CriSSD) presents normative ratings for a set of 63 crimes on three dimensions: White stereotypicality, Black stereotypicality, and crime severity. The crimes were selected according to a comprehensive procedure. A total of 340 Portuguese participants (72.6% female; Mage = 26.86, SD = 7.65) answered an online survey. Each crime was evaluated by a range of 46–60 participants. Data allowed us to identify a crime typology with three clusters. We present descriptive data (means, standard deviations, and 95% confidence intervals) for each crime. Crime evaluations were associated with sociodemographic characteristics. Additionally, this study gives input regarding the understudied link between crime stereotypes and crime severity, showing that crime severity is predicted by ratings of both Black and White stereotypicality. The CriSSD (available at osf.io/gkbrm) provides a valuable resource for researchers in the field of social psychology to conduct studies with controlled materials on potential disparities in criminal-sentencing decisions. [ABSTRACT FROM AUTHOR]