The applications of sensing and localization are becoming more sophisticated in many invasive and non-invasive surgical procedures and there is great interest to apply them to the human heart. Ideally, such tools could be indispensable for allowing physicians to spatially understand relative tissue morphologies and their associated electrical conduction. Yet today there remains a steep divide between the creation of spatial environment models and the contextual understandings of adjacent features. To begin to address this, we explore the problem of anatomical perception by applying deep learning to the identification of internal cardiac anatomy images.

This content is only available via PDF.