METHODS: In this paper, we analyze four wide-spread deep learning models designed for the segmentation of three retinal fluids outputting dense predictions in the RETOUCH challenge data. We aim to demonstrate how a patch-based approach could push the performance for each method. Besides, we also evaluate the methods using the OPTIMA challenge dataset for generalizing network performance. The analysis is driven into two sections: the comparison between the four approaches and the significance of patching the images.
RESULTS: The performance of networks trained on the RETOUCH dataset is higher than human performance. The analysis further generalized the performance of the best network obtained by fine-tuning it and achieved a mean Dice similarity coefficient (DSC) of 0.85. Out of the three types of fluids, intraretinal fluid (IRF) is more recognized, and the highest DSC value of 0.922 is achieved using Spectralis dataset. Additionally, the highest average DSC score is 0.84, which is achieved by PaDeeplabv3+ model using Cirrus dataset.
CONCLUSIONS: The proposed method segments the three fluids in the retina with high DSC value. Fine-tuning the networks trained on the RETOUCH dataset makes the network perform better and faster than training from scratch. Enriching the networks with inputting a variety of shapes by extracting patches helped to segment the fluids better than using a full image.
METHODS: We enrolled 67 participants allocated into 3 groups to receive virtual reality exposure therapy, standard stress management, or wait-list group. The virtual reality exposure therapy group received a total of a 30-minute exposure to a virtual reality environment over 2 weeks. The standard stress management group received a stress management program once during the study period.
RESULTS: The results showed a heterogeneous sample, whereby a significantly younger, less-working years, and higher anxiety baseline score were found in the virtual reality exposure therapy group compared to standard stress management and wait-list groups. Nonetheless, the virtual reality exposure therapy group showed a reduction in depression, anxiety, and stress score (P < .001). The standard stress management group showed a reduction in anxiety score only (P = .002), whereas no significant changes were observed in the wait-list group. For positive emotion, all 3 groups showed significant improvement.
CONCLUSION: Short-term virtual reality exposure therapy is a feasible intervention for the negative and positive emotions; however, cautious interpretation is needed due to significant heterogeneous sample. Replication of study with comparable groups is recommended.
METHODS: We performed secondary analysis on data from 25461 respondents of the Global School Health Survey in Malaysia. Descriptive analyses and multivariable logistic regression were performed to determine factors associated with SHS exposure.
RESULTS: Respondents were adolescents of mean age 14.84 (SD=1.45) years, 50.2% of which were male and 49.8% female. Approximately four in ten respondents were exposed to SHS in the past week (41.5%). SHS exposure was significantly higher among respondents who smoked than among non-smokers (85.8% vs 35.7%, p<0.001). The likelihood of exposure to SHS was higher among smoking adolescents (Adjusted OR=1.66, 95% CI: 1.07-2.56) and non-smoking adolescents (AOR=3.15, 95% CI: 1.48-4.71) who had at least one smoking parent/guardian regardless of their own smoking status. Male adolescents had higher risk of SHS exposure compared to their female counterparts (current smoker AOR=1.66, 95% CI: 1.07-2.56; non-smoker AOR=1.50, 95% CI: 1.12-2.00) and increased with age, regardless of their smoking status.
CONCLUSIONS: Our findings suggest that prevalence of exposure to SHS among school-going adolescents in Malaysia is high. Parents should be advised to stop smoking or abstain from smoking in the presence of their children. Education programmes are recommended to increase awareness on avoidance of SHS as well as smoking cessation interventions for both adolescents and their parents.
METHODS: Clinical records of active opioid dependents who underwent MMT between 1 January 2007 and 31 March 2021 in Hospital Tuanku Fauziah, Perlis, Malaysia were retrospectively reviewed. Data collected included baseline demographics, history of illicit drug use, temporal trend in methadone dosage modulation, and co-use of illicit drugs during the MMT.
RESULTS: A total of 87 patients (mean age, 43.9 ± 8.33 years) were included. Their mean duration of involvement in MMT was 7.8 ± 3.69 years. The most commonly used drug was heroin (88.5%), followed by kratom (51.7%). Between 2019 and 2021, 61 (70.1%) patients had ceased abusing opioid, but 51 (58.6%) patients continued using any of the illicit drugs. Methamphetamine and amphetamine co-use was most common (n = 12, 37.5%). Hepatitis C status was not associated with the current methadone dose (U = 539.5, p = 0.186) or the highest dose required (t = -0.291, df = 74, p = 0.772). No predictor for illicit drug abstinence during MMT was identified. Methadone dose positively correlated with frequency of defaulting treatments (r = 0.22, p = 0.042).
CONCLUSION: Among our patients, MMT for opioid dependents cannot sufficiently curb illicit drug use, and there is a shift toward stimulants abuse.