A Deep Learning Model to Improve Pathologist Interpretation of Donor Kidney Biopsies

PROJECT SUMMARY ABSTRACT More people die every year from kidney disease than breast or prostate cancerKidney transplantation is life saving but is limited by a shortage of organ donors and an unacceptably high donor organ discard rateThe decision to use or discard a donor kidney relies heavily on manual quantitation of key microscopic findings by pathologistsA major limitation of this microscopic examination is human variability and inefficiency in interpreting the findingsresulting in potentially healthy organs being deemed unsuitable for transplantation or potentially damaged organs being transplanted inappropriatelyOur team developed the first Deep Learning model capable of automatically quantifying percent global glomerulosclerosis in whole slide images of donor kidney frozen section wedge biopsiesThis innovative approach has the potential to transform donor kidney biopsy evaluation by improving pathologist efficiencyaccuracyand precision ultimately resulting in optimized donor organ utilizationdiminished health care costsand improved patient outcomesThe goal of this project is to establish our Deep Learning automated quantitative evaluation as the standard practice of donor kidney evaluation prior to transplantationThis will be achieved by assembling a team of expert kidney pathologists and computer scientists specializing in machine learningThe proposal will evaluate the accuracy and precision of the computerized approach to quantifying percent global glomerulosclerosis and compare these results with current standard of care pathologist evaluationThe feasibility of deploying the Deep Learning model to analyze whole slide images on the cloud will also be examinedThe end product of this STTR will be a web based platform to securely deploy Deep Learning image analysis as a tool to assist pathologists with donor kidney biopsy evaluation PUBLIC HEALTH RELEVANCE STATEMENT Before a kidney can be transplantedthe tissue must be assessed under a microscope to ensure the organ is healthy enough for transplantA major limitation of microscopic examination is human variability in interpreting the findingsresulting in healthy organs being deemed unsuitable for transplantationThis funding will support developing computer algorithms to assist pathologists in microscopic examination of donor kidney tissuesresulting in more consistent and objective biopsy interpretationsminimizing discard of potentially usable kidneys and optimizing organ placement for transplant