100 likes | 111 Views
Explore NEC's state-of-the-art machine learning techniques for cancer research, including detailed diagnostics, targeted therapies, personalized medicine, and statistical learning theory.
E N D
Cancer Researchin NEC Labs America’sMachine Learning Dept. Matt Miller Research Staff Member NEC Labs America
Modern Tools for Oncology • Detailed diagnostics • Targeted therapies • Methods of mapping diagnostic results to therapies (“personalized medicine”) • Methods of testing these tools
How Machine Learning Fits In • Detailed diagnostics • Pattern recognition • Targeted therapies • Machine-assisted drug design • Methods of mapping diagnostic results to therapies (“personalized medicine”) • Cocktail design • Methods of testing these tools • Statistical learning theory
How Machine Learning Fits In • Detailed diagnostics • Pattern recognition • Targeted therapies • Machine-assisted drug design • Methods of mapping diagnostic results to therapies (“personalized medicine”) • Cocktail design • Methods of testing these tools • Statistical learning theory
NEC’s Digital Pathology System • Given a digitized pathology image, determine whether benign or malignant. • Initial application: double-check diagnoses of human pathologists. • First implemented for gastric cancer. • Current development work: • Colon cancer • Breast cancer • Prostrate cancer
NEC’s Digital Pathology System ROI’s Image of whole tissue Lo-res analysis (decision-tree like method) Malignant/ Benign Hi-res analysis (SVM’s, CNN’s)
NEC’s Digital Pathology System • Gastric system tested on 1905 biopsies. • Compared against diagnoses by three human pathologists. • 100 malignant cases • Results: • 227 / 1805 (12.6%) false positives • 1 / 100 false negative
Cocktail Design • Assume there is an unknown function • Find a function Such that is good
Cocktail Design: We Have … • Some theoretical results due to Vapnik. • Proposal for an algorithm. • Methods for handling real-world problems • Limits on what machine may try while learning. • Paucity of real cases. • No data to work on.
Vladimir Vapnik Léon Bottou Eric Cosatto Christopher Malon Matt Miller NEC ML People Here Today