Malignant lymphoma affects many patients annually, and among malignant lymphomas, CLL (chronic lymphocytic leukemia), FL (follicular lymphoma), and MCL (mantle cell lymphoma) are difficult for even experienced pathologists to accurately classify.
Jon Fuller and Olivia Klose demonstrate how KNIME, Apache Spark, and Microsoft Azure can enable fast and cheap automated classification of lymphoma type in digital pathology images. Jon and Olivia explain how they use Apache Spark running on an HDInsight cluster within the KNIME Analytics Platform to preprocess the image data and train a deep convolutional neural network on GPU-enabled virtual machines to classify the images. The trained model is then deployed to end users as a web application using the KNIME WebPortal.
Jon Fuller is an application scientist at KNIME, where he works with customers to deploy advanced analytics and help them understand the power of working with cloud resources. Previously, Jon was a postdoctoral researcher at the Heidelberg Institute for Theoretical Studies, where he published several papers on computational biology topics. Jon is a lapsed physicist. He holds a PhD in bioinformatics from the University of Leeds.
Olivia Klose is a software development engineer in the Technical Evangelism and Development Group at Microsoft, where she focuses on all analytics services on Microsoft Azure, in particular Hadoop (HDInsight), Spark, and Machine Learning. Olivia is a frequent speaker at conferences both in Germany and around the world, including TechEd Europe, PASS Summit, and Technical Summit. She studied computer science and mathematics at the University of Cambridge, the Technical University of Munich, and IIT Bombay, with a focus on machine learning in medical imaging.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com