Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Researchers detail new data in Machine Learning. According to news reporting out ofNashville, Tennessee, by NewsRx editors, research stated, “Machine learning (ML) has been increasinglyused to quantify CEST effect. ML models are typically trained using either measured data or fully simulateddata.”Financial support for this research came from National Institutes of Health (NIH) - USA.Our news journalists obtained a quote from the research from Vanderbilt University Medical Center,“However, training with measured data often lacks sufficient training data, whereas training with fullysimulated data may introduce bias because of limited simulations pools. This study introduces a newplatform that combines simulated and measured components to generate partially synthetic CEST data,and to evaluate its feasibility for training ML models to predict amide proton transfer (APT) effect.Partially synthetic CEST signals were created using an inverse summation of APT effects from simulationsand the other components from measurements. Training data were generated by varying APT simulationparameters and applying scaling factors to adjust the measured components, achieving a balance betweensimulation flexibility and fidelity. First, tissue-mimicking CEST signals along with ground truth informationwere created using multiple-pool model simulations to validate this method. Second, an ML model wastrained individually on partially synthetic data, in vivo data, and fully simulated data, to predict APT effectin rat brains bearing 9 L tumors. Experiments on tissue-mimicking data suggest that the ML method usingthe partially synthetic data is accurate in predicting APT. In vivo experiments suggest that our methodprovides more accurate and robust prediction than the training using in vivo data and fully synthetic data.”
NETL
NSTL