Search

Background/Objectives: The purpose of this study was to analyze relevant areas in acute-stage fluorescein angiography (FA) images, predicting the long-term visual prognosis of branch retinal vein occlusion (BRVO) based on gradient-weighted class activation mapping (Grad-CAM). Methods: This retrospective observational study included 136 eyes with BRVO that were followed up for more than a year post-FA. Cropped grayscale images centered on the fovea (200 × 200 pixels) were manually pre-processed from early-phase FA at the acute phase. Pairs of the cropped FA images and the best-corrected visual acuity (BCVA) in remission at least one year post-FA were used to train a 38-layer ResNet with five-fold cross-validation. Correlations between the ResNet-predicted and true (actually measured) logMAR BCVAs in remission, and between the foveal avascular zone (FAZ) area measured by ImageJ (version 1.52r) from FA images and true logMAR BCVA in remission were evaluated. The heat maps generated by Grad-CAM were evaluated to determine which areas were consumed as computational resources for BCVA prediction. Results: The correlation coefficient between the predicted and true logMAR BCVAs in remission was 0.47, and that between the acute-stage FAZ area and true logMAR BCVA in remission was 0.42 (p < 0.0001 for both). The Grad-CAM-generated heat maps showed that retinal vessels adjacent to the FAZ and the FAZ per se had high selectivity (95.7% and 62.2%, respectively). Conclusions: The Grad-CAM-based analysis demonstrated FAZ-neighboring vessels as the most relevant predictor for the long-term visual prognosis of BRVO. [ABSTRACT FROM AUTHOR]

Research in Western countries has indicated that the cognitive distortions of sexual offenders play an etiological and maintenance role in offending. The present study examines whether the cognitive distortions hypothesized by previous Western studies can be found in Japanese sexual offenders against women. This study used the questionnaire administered by probation officers in the special cognitive-behavioral treatment programs for sexual offenders, which have been implemented since 2006 in Japan. Participants in the offender group were 80 Japanese male probationers and parolees (more than 19 years old, M age = 34.6, SD = 8.8) convicted of rape (n = 39) or indecent assault (n = 41). All of them attended special treatment programs at probation offices. The non-offender comparison group consisted of 95 Japanese male probation officers and police officers (M age = 35.5, SD = 11.4). A factor analysis of the questionnaire responses extracted three factors: Blaming the Victim, Minimization, and Avoidance of Responsibility. The data analyses showed that sexual offenders scored significantly higher than non-offender participants on the three subscales. No significant differences were found among four sexual offender groups classified as rapists or indecent assaulters and with or without previous convictions for sexual offenses. In conclusion, the results of this study indicate that rapists and indecent assaulters placed on probation or parole in Japan hold cognitive distortions concerning sexual assaults against women than the control group of probation and police officers. The findings of this study also suggest that cognitive distortions exhibited by sexual offenders against women transcend cultural divides. [ABSTRACT FROM AUTHOR]