Delivering Diagnostic Quality Video over Mobile Wireless Networks for Telemedicine

Abstract

In real-time remote diagnosis of emergency medical events, mobility can be enabled by wireless video communications. However, clinical use of this potential advance will depend on definitive and compelling demonstrations of the reliability of diagnostic quality video. Because the medical domain has its own fidelity criteria, it is important to incorporate diagnostic video quality criteria into any video compression system design. To this end, we used flexible algorithms for region-of-interest (ROI) video compression and obtained feedback from medical experts to develop criteria for diagnostically lossless (DL) quality. The design of the system occurred in three steps-measurement of bit rate at which DL quality is achieved through evaluation of videos by medical experts, incorporation of that information into a flexible video encoder through the notion of encoder states, and an encoder state update option based on a built-in quality criterion. Medical experts then evaluated our system for the diagnostic quality of the video, allowing us to verify that it is possible to realize DL quality in the ROI at practical communication data transfer rates, enabling mobile medical assessment over bit-rate limited wireless channels. This work lays the scientific foundation for additional validation through prototyped technology, field testing, and clinical trials.

An overview of recent end-to-end wireless medical video telemedicine systems using 3G

“…In [15], [16], [18], [19] we observe this shift towards the establishment of diagnostic validation criteria in the evaluation of the transmitted medical video.…”

“…The design of an elastic ROI coding which incorporates different quantization levels for ROI and non-ROI, targeting Diagnostically Lossless (DL) encoding over bitrate limited wireless channels utilizing physician expert feedback is presented in [16]. An encoder states diagram for different quality levels is designed and a state transition is considered every Group of Pictures (GOP).…”

H.265 Codec over 4G Networks for Telemedicine System Application

“…However, what one finds in the some existing literature on wireless systems for telemedicine [19] is a discussion of wireless technologies but limited simulation or testing for specific wireless systems. For example, in [3] though a WiMAX simulation was performed, the authors did not state what channel model was used and employed a non-standard wavelet codec, whereas in [9], no specific wireless technology was simulated and an unrealistic error pattern was tested.…”

Global Coding of Multi-source Surveillance Video Data

“…In this series, high compression rate will cause dramatic decrease on the performance of object recognition [2] since there is no distinguish between background and foreground. In order to improve the perceptual quality, the visual redundancy is exploited by assigning higher priority to blocks with high visual sensitivity [3,4] or hiding the coding artifact in the insensitive area [5,6]. However, this scheme does not explicitly classify background and foreground either.…”