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: 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.