Automated Assessment of the Effects of System Limitations Based upon Data collect

点击翻译按钮获取中文摘要

DESCRIPTION (provided by applicant): There are over 700 installed da Vinci robotic surgery systems as of mid 2007 and robotic radical prostatectomies are now the dominant modality of operation for removal of prostates with cancer. Tens of thousands of procedures are performed with da Vinci systems in the United States alone. The da Vinci, even though it's the only commercial robotic surgery system, is now widely available and operating at a clinical volume that makes the investigation of skill development a crucial issue in quality of care. This research aims to establish, deploy, and validate an infrastructure for systematically collecting quantitative motion measurements, system events, and corresponding synchronized video data (procedure data) from surgeons for the duration of their robotic surgery training via the application programming interface (API) of the da Vinci. This will allow surgical motions and clinical events to be studied undisturbed and unmodified by experimental sensors and tools. There is a unique opportunity to integrate an automatic measurement system into a multi-center robotic surgery residency program being presently developed by Intuitive Surgical providing transparent access to a larger number of robotic surgery trainees. To date, most methods of surgical evaluation of robotic surgery are based on manual, subjective evaluation of surgical technique (e.g. the OSATS) and have not looked at system or operation skills. Further, they have been limited to a small set of users. Automated objective assessment frameworks such as the proposed system will be far more suitable for integration into a training curriculum for measurement of system operation skill acquisition. Extension of this work to include statistical analysis may also allow objective assessments for surgical skills. PUBLIC HEALTH RELEVANCE: Robotic prostatectomies are dominant method of treating late state prostate cancer, and robotic hysterectomies and other gynecological procedures are being adopted at similar growth rates. To train tomorrow's surgeons to operate these robotic devices efficiently and to better design future devices, there is an increasing need to understand the effects of complex elements of robotic surgery affecting robotic system training as well as robotic surgery skill acquisition. To meet this need, this work creates the first systematically acquired resource of training data from robotic surgery, and investigates automatic assessment for the effects of system limitations.