Tom Tom Founders Festival 2018

A major challenge of interpreting clinical biopsy images to diagnose disease is the often striking overlap in histopathology between distinct but related conditions. There is a major clinical need to develop new methods in data science to allow clinicians to translate heterogeneous biomedical data extracted from patient samples into accurate, quantitative, and precise diagnostics. The development of such processes in high dimensional clinical research data will support the progress of “precision medicine”, with improved diagnostics, treatments, and clinical outcomes for patients. In this presentation we show preliminary results from an image analysis platform for the automated extraction of quantitative morphologic phenotypes from gastrointestinal (GI) biopsy images. This method will capture complex GI disease phenotypes, which cannot be measured directly using molecular approaches. We also aim to develop methods in data science to support the integration of this data with clinical and molecular data, enabling the construction of biologically informative and clinically useful integrative prognostic models in our case, in Environmental Enteropathy. EE is an acquired small intestinal inflammatory condition underlying high rates of linear growth stunting in children <5y of age in low- and middle-income countries. The histologic appearance of duodenal EE biopsies significantly overlaps with celiac enteropathy. To identify novel features that distinguish these two enteropathies from healthy tissue, we characterized intestinal mucosal alterations in Pakistani infants with EE using Convolutional Neural Networks (CNN).