Quality assessment for wireless capsule endoscopy videos compressed via HEVC: from diagnostic quality to visual perception

Muhammad Arslan Usman, Muhammad Rehan Usman, Soo Young Shin

    Research output: Contribution to journalArticlepeer-review

    Abstract

    Maintaining the quality of medical images and videos is an essential part of the e-services provided by the healthcare sector. The convergence of modern communication systems and the healthcare industry necessitates the provision of better quality of service and experience by the service provider. Recent inclusion and standardization of the high efficiency video coder (HEVC) has made it possible for medical data to be compressed and transmitted over wireless networks with minimal compromise of the quality. Quality evaluation and assessment of these medical videos transmitted over wireless networks is another important research area that requires further exploration and attention. In this paper, we have conducted an in-depth study of video quality assessment for compressed wireless capsule endoscopy (WCE) videos. Our study includes the performance evaluation of several state-of-the-art objective video quality metrics in terms of determining the quality of compressed WCE videos. Subjective video quality experiments were conducted with the assistance of experts and non-experts in order to predict the diagnostic and visual quality of these medical videos, respectively. The evaluation of the metrics is based on three major performance metrics that include, correlation between the subjective and objective scores, relative statistical performance and computation time. Results show that the metrics information fidelity criterion (IFC), visual information fidelity-(VIF) and especially pixel based VIF stand out as best performing metrics. Furthermore, our paper reports the performance of HEVC compression on medical videos and according to the results, it performs optimally in preserving the diagnostic and visual quality of WCE videos at Quantization Parameter (QP) values of up to 35 and 37 respectively.
    Original languageEnglish
    Pages (from-to)112-134
    JournalComputers in Biology and Medicine
    Volume91
    Early online date9 Oct 2017
    DOIs
    Publication statusPublished - 9 Oct 2017

    Keywords

    • Full reference
    • High efficiency video coding
    • Objective video quality assessment
    • Quantization parameter
    • Subjective video quality assessment
    • Electrical and electronic engineering

    Fingerprint

    Dive into the research topics of 'Quality assessment for wireless capsule endoscopy videos compressed via HEVC: from diagnostic quality to visual perception'. Together they form a unique fingerprint.

    Cite this