RESUMEN
In this paper, we propose a lightweight U-net architecture neural network model based on Dark Channel Prior (DCP) for efficient haze (fog) removal with a single input. The existing DCP requires high computational complexity in its operation. These computations are challenging to accelerate, and the problem is exacerbated when dealing with high-resolution images (videos), making it very difficult to apply to general-purpose applications. Our proposed model addresses this issue by employing a two-stage neural network structure, replacing the computationally complex operations of the conventional DCP with easily accelerated convolution operations to achieve high-quality fog removal. Furthermore, our proposed model is designed with an intuitive structure using a relatively small number of parameters (2M), utilizing resources efficiently. These features demonstrate the effectiveness and efficiency of the proposed model for fog removal. The experimental results show that the proposed neural network model achieves an average Peak Signal-to-Noise Ratio (PSNR) of 26.65 dB and a Structural Similarity Index Measure (SSIM) of 0.88, indicating an improvement in the average PSNR of 11.5 dB and in SSIM of 0.22 compared to the conventional DCP. This shows that the proposed neural network achieves comparable results to CNN-based neural networks that have achieved SOTA-class performance, despite its intuitive structure with a relatively small number of parameters.
RESUMEN
Introduction: The partial estrogen-agonist action of tamoxifen on bone receptors has beneficial effects on bone mineral density. However, in premenopausal women, the use of tamoxifen causes systemic estrogen depletion, which has detrimental effects on bone health. We aim to investigate the association between tamoxifen and osteoporosis in the real world using data from a longitudinal nationwide cohort of Korean patients. Methods: Data were collected from the National Health Insurance claims database in South Korea. Osteoporosis was defined by diagnostic codes accompanying prescription data for osteoporosis. The cumulative incidence was analyzed by Kaplan-Meier survival curves and the risk factors were analyzed using a multivariable Cox proportional hazard regression model. Results: Between 2009 and 2015, of the 4,654 women with ductal carcinoma in situ (DCIS) without prior osteoporosis, 2,970 were prescribed tamoxifen and 1,684 were not. A total of 356 DCIS survivors were later diagnosed with osteoporosis during a median follow-up period of 84 months. In the overall population, tamoxifen was associated with a low risk of osteoporosis, before and after propensity matching adjusted for age, operation type, and comorbidities (before matching, hazard ratio [HR]=0.69, 95% confidence interval [CI]=0.559-0.851, p<0.001; after matching, HR=0.664, 95% CI=0.513-0.858, p=0.002). In the subgroup analysis, findings were consistent in postmenopausal women but were not evident in the younger age group. Conclusion: In a nationwide cohort study, a low risk of osteoporosis was associated with the use of tamoxifen. The protective effect of tamoxifen was more profound in older women and was not related to the incidence of osteoporosis in younger women.