Machine Learning for Image Analysis
Stroke is a leading cause of mortality and morbidity in the United States, with approximately 795,000 Americans experiencing a new or recurrent stroke each year. In this project, we aim to: 1) develop a machine learning framework for classifying treatment eligibility, 2) develop a deep convolutional autoencoder to generate novel multimodal image representations from MR and CT to improve classification, and 3) implement visualization techniques that elucidate the relationship between deep features and pathophysiological stroke processes.
Prostate cancer is the second leading cause of cancer death in American men, accounting for 26% of new cancer diagnoses and 9% of cancer deaths in men. The research objective of this R21 is to develop novel techniques using multiparametric magnetic resonance imaging (mp-MRI) and MRI-ultrasound (US) fusion guided biopsy data that provide discriminatory power in distinguishing indolent versus clinically significant prostatic adenocarcinoma based on radiology imaging and digital histology.
Heart Failure Monitoring
Heart failure (HF) is a debilitating disease that affects over five million people in the United States and in 2012 had a direct cost of over $30.7 billion annually. Home monitoring of HF patients has the potential to reduce costs and improve quality of life by reducing preventable hospital readmissions. The goals of this R01 are to: 1) demonstrate that patients are adherent to a home monitoring regimen when using minimally-invasive monitoring technologies; 2) combine the minimally-invasive home monitoring regimen with predictive algorithms to forecast hospital readmission; 3) develop models using electronic health record (EHR) data and a baseline survey to predict levels of adherence to the home monitoring regimen; and 4) explore the pragmatic feasibility of using a mobile app for communicating with patients in prospective pilot study