SPIVOS
Research type
Research Study
Full title
SPIVOS: Spine Surgery Video Observation Study. The creation of a benchmark video (RGB-Depth) dataset to investigate the feasibility of developing a markerless tracking system for spine surgery.
IRAS ID
341461
Contact name
Ferdinando Rodriguez Y Baena
Contact email
Sponsor organisation
Imperial College London and Imperial College Healthcare NHS Trust
Duration of Study in the UK
3 years, 0 months, 0 days
Research summary
This project aims to develop a deep learning based system for the marker-less tracking of bony spinal tissue during open surgery. Tracking systems are vital for non rigidly pinned surgeries, as the target tissue often deforms or moves, and tracking provides a way of registering intra-operative readings against pre-operative imaging, thus providing the surgeon a way of more precisely incorporating pre-operative information during the surgery. In contrast with marker based tracking used for orthopaedic surgery, this is less intrusive and reduces the likelihood of infection introduced by bone mounted markers, or fiducials. To train our markerless system, we will use a commercial RGB-D(epth) camera to collect frames of RGB colour and depth information. The Azure Kinect, which will be pointed directly at the surgical site from a distance (of approximately 50cm). The field of view will only contain the surgical site, and no identifying features. Similarly, we will also require access to the preoperative images (CT scans). The camera projects near infrared light onto the surgical site, and produces a depth image.
REC name
West Midlands - Solihull Research Ethics Committee
REC reference
24/WM/0214
Date of REC Opinion
5 Dec 2024
REC opinion
Further Information Favourable Opinion