Ophthatome™: an integrated knowledgebase of ophthalmic diseases for translating vision research into the clinic.

BACKGROUND: Medical big data analytics has revolutionized the human healthcare system by introducing processes that facilitate rationale clinical decision making, predictive or prognostic modelling of the disease progression and management, disease surveillance, overall impact on public health and research. Although, the electronic medical records (EMR) system is the digital storehouse of rich medical data of a large patient cohort collected over many years, the data lack sufficient structure to be of clinical value for applying deep learning methods and advanced analytics to improve disease management at an individual patient level or for the discipline in general. Ophthatome™ captures data contained in retrospective electronic medical records between September 2012 and January 2018 to facilitate translational vision research through a knowledgebase of ophthalmic diseases. METHODS: The electronic medical records data from Narayana Nethralaya ophthalmic hospital recorded in the MS-SQL database was mapped and programmatically transferred to MySQL. The captured data was manually curated to preserve data integrity and accuracy. The data was stored in MySQL database management system for ease of visualization, advanced search functions and other knowledgebase applications. RESULTS: Ophthatome™ is a comprehensive and accurate knowledgebase of ophthalmic diseases containing curated clinical, treatment and imaging data of 581,466 ophthalmic subjects from the Indian population, recorded between September 2012 and January 2018. Ophthatome™ provides filters and Boolean searches with operators and modifiers that allow selection of specific cohorts covering 524 distinct ophthalmic disease types and 1800 disease sub-types across 35 different anatomical regions of the eye. The availability of longitudinal data for about 300,000 subjects provides additional opportunity to perform clinical research on disease progression and management including drug responses and management outcomes. The knowledgebase captures ophthalmic diseases in a genetically diverse population providing opportunity to study genetic and environmental factors contributing to or influencing ophthalmic diseases. CONCLUSION: Ophthatome™ will accelerate clinical, genomic, pharmacogenomic and advanced translational research in ophthalmology and vision sciences.

Machine Learning and Image Analysis Applications in the Fight against COVID-19 Pandemic: Datasets, Research Directions, Challenges and Opportunities.

COVID-19 pandemic has become the most devastating disease of the current century and spread over 216 countries around the world. The disease is spreading through outbreaks despite the availability of modern sophisticated medical treatment. Machine Learning and Image Analysis research has been making great progress in many directions in the healthcare field for providing support to subsequent medical diagnosis. In this paper, we have propose three research directions with methodologies in the fight against the pandemic namely: Chest X-Ray (CXR) images classification using deep convolution neural networks with transfer learning to assist diagnosis; Patient Risk prediction of pandemic based on risk factors such as patient characteristics, comorbidities, initial symptoms, vital signs for prognosis of disease; and forecasting of disease spread & case fatality rate using deep neural networks. Further, some of the challenges, open datasets and opportunities are discussed for researchers.

A dataset for automatic contrast enhancement of microscopic malaria infected blood RGB images.

In this article we introduce a malaria infected microscopic images dataset for contrast enhancement which assist for malaria diagnosis more accurately. The dataset contains around two hundred malaria infected, normal, species and various stages of microscopic blood images. We propose and experimentally demonstrate a contrast enhancement technique for this dataset. This simple technique increases the contrast of an image and hence, reveals significant information about malaria infected cells. Experiments on the dataset show the superior performance of our proposed method for contrast enhancement of malaria microscopic imaging.