METHODS: The mid-stream urine collected from both male and female patients diagnosed with dengue fever at Penang General Hospital and fourty-three healthy individuals were analyzed with (1)H NMR spectroscopy, followed by chemometric multivariate analysis. NMR signals which highlighted in the OPLS-DA S-plot were further selected and identified using Human Metabolome Database, Chenomx Profiler.
RESULTS: The results pointed out that NMR urine profiling was able to capture human gender metabolic differences that are important for the distinction of classes of individuals of similar physiological conditions; infected with dengue. Distinct differences between dengue infected patients versus healthy individuals and subtle differences in male versus female infected with dengue were found to be related to the metabolism of amino acid and tricarboxylic acid intermediates cycle.
CONCLUSIONS: The (1)H NMR metabolomic investigation combined with appropriate algorithms and pattern recognition procedures, gave an evidence for the existence of distinct metabolic differentiation of individuals, according to their gender, modulates with the infection risk.
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.