Gaidai reliability method for high-dimensional spatio-temporal biosystems.

This study presents novel methodology for pandemic risks assessment for a national health system of interest. The 2019 coronavirus disease (COVID-19) is a contagious disease with certain potential for worldwide spread and potentially significant effects on public health globally. Suggested methodology enables risks assessment of an epidemic, that may happen in the near future at any time, and in any national region of interest. Traditional spatio-temporal reliability methodologies do not have benefit of easily handling health system's high-dimensionality and complex cross-correlations between regional observations. Contrarily, advocated Gaidaireliability approach successfully addresses spatiotemporal clinical observations, as well as multi-regional epidemiological dynamics. This study aimed at benchmarking of a novel bio-statistical technique, enabling national health risk assessment, based on available clinical surveys with dynamically observed patient numbers, while accounting for relevant territorial mappings. The method developed in this study opens up the possibility of accurate epidemiological risk forecast for multi-regional biological and health systems. Suggested bioinformatical methodology may be used in a wide range of public health applications.

Explainable Diabetic Retinopathy Detection and Retinal Image Generation.

Though deep learning has shown successful performance in classifying the label and severity stage of certain diseases, most of them give few explanations on how to make predictions. Inspired by Koch's Postulates, the foundation in evidence-based medicine (EBM) to identify the pathogen, we propose to exploit the interpretability of deep learning application in medical diagnosis. By isolating neuron activation patterns from a diabetic retinopathy (DR) detector and visualizing them, we can determine the symptoms that the DR detector identifies as evidence to make prediction. To be specific, we first define novel pathological descriptors using activated neurons of the DR detector to encode both spatial and appearance information of lesions. Then, to visualize the symptom encoded in the descriptor, we propose Patho-GAN, a new network to synthesize medically plausible retinal images. By manipulating these descriptors, we could even arbitrarily control the position, quantity, and categories of generated lesions. We also show that our synthesized images carry the symptoms directly related to diabetic retinopathy diagnosis. Our generated images are both qualitatively and quantitatively superior to the ones by previous methods. Besides, compared to existing methods that take hours to generate an image, our second level speed endows the potential to be an effective solution for data augmentation.