Region of Interest Optimization for Delay-sensitive Telemedicine Applications

Abstract

Telemedicine is a rising technology that is gaining a lot of interest in the recent decades. Several applications of telemedicine are delay-sensitive and need to be operated in real-time. One of which is surgical tele-mentoring where a remote expert surgeon mentors local surgeons during an operation. While the advances done in telecommunications and robotics have made tele-mentoring possible in modern days, there are still many challenges that stop such telemedical applications from being completely legalized and approved as medical tools across the world. One of the main issues is the need for very high bandwidth to allow the surgery to be done accurately in real-time. Such bandwidth requirements are difficult to provide especially in rural areas with limited communications infrastructure. We propose an adaptive Region of Interest (ROI) detection and an optimization model that addresses the trade-off between the overall quality of a surgical video and the network delay. The model aims to maximize the size of the ROI, where highest video quality must be used, depending on the available network throughput, while avoiding excessive degradation of the quality of the background.