Autonomous Finite Elements and Deep Learning to Assist Orthopedists and Endocrinologists
Autonomous Finite Elements and Deep Learning to Assist Orthopedists and Endocrinologists
ABSTRACT: Finite element analysis requires a qualified analyst to generate the necessary input data, verify the output and post process the analysis results for a meaningful conclusion. The required expertise and labor efforts precluded the use of FEA in daily medical practice for example. Recent scientific advancements such as low dose CT scans, machine learning, and high order FEA which allows an inherent verification methodology of the numerical accuracy, make it possible to provide a fully autonomous process for assessing bone strength and fracture risk. This autonomous process, named autonomous finite element (AFE) analysis, introduces a paradigm shift in the use of FEA. This talk addresses a novel AFE for patient-specific analysis of human femurs used nowadays in clinical practice: it involves an automatic segmentation of femurs from CT-scans by U-Net, an automatic mesh generation and application of boundary conditions based on anatomical points, a high-order FE analysis with numerical error control, and finally an automatic report with a clear assessment of bone fracture risk. Two specific applications of AFE are presented: a) Determination of the risk of fracture for patients with tumors of the femur and whether a prophylactic surgery is needed. b) Identifying patients with high hip fracture risk as a result of fall on the side.
BIO: Prof. Yosibash has a BSc Cum Laude degree in Aeronatutical Engineering fromt the Israel Institute for Technology - Technion (1987), a MSc Summa Cum Laude degree in Applied Mathematics from the Tel-Aviv Unviersity (1991) and a DSc degree in Mechanical Engineering from Washington University in St. Louis, USA (1994). During 1995-2017 he was a professor of Mechanical Engineering at Ben-Gurion University (full professor since 2008). During 2001-2007 he was an associate professor for research at the Division of Applied Math at Brown University, Providence, RI, USA, and during 2009-2012 he was awarded the Hans Fischer Senior Fellow at the Institute forAdvanced Study at the Technical University of Munich, Germany. Since 2013 he serves as the scientific ambasador of the TUM. Prof. Yosibash is an enterpreneur that extablished two Start-Up companies, is their CTO and the Chairman of the Board of Directors.