Abstract
BACKGROUND: HeartLander is a tethered robot walker that utilizes suction to adhere to the beating heart. HeartLander can be used for minimally invasive administration of cardiac medications or ablation of tissue. In order to administer injections safely, HeartLander must avoid coronary vasculature. METHODS: Doppler ultrasound signals were recorded using a custom-made cardiac phantom and used to classify different coronary vessel properties. The classification was performed by two machine learning algorithms, the support vector machines and a deep convolutional neural network. These algorithms were then validated in animal trials. RESULTS: Accuracy of identifying vessels above turbulent flow reached greater than 92% in phantom trials and greater than 98% in animal trials. CONCLUSIONS: Through the use of two machine learning algorithms, HeartLander has shown the ability to identify different sized vasculature proximally above turbulent flow. These results indicate that it is feasible to use Doppler ultrasound to identify and avoid coronary vasculature during cardiac interventions using HeartLander.