Panayides A, Pattichis M S, Pattichis C S, Loizou C P, Pantziaris M, Pitsillides A
Department of Computer Science, University of Cyrus, Nicosia, Cyprus.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:5143-6. doi: 10.1109/IEMBS.2009.5334278.
In this paper we define diagnostic Regions of Interest (ROIs) for carotid ultrasound medical video, which we then use as input for Flexible Macroblock Ordering (FMO) slice encoding. We extend the FMO concept by enabling variable quality slice encoding, tightly coupled by each region's diagnostic importance. Redundant Slices (RS) utilization increases compressed video's resilience over error prone transmission mediums. We evaluate our scheme on a series of five (5) carotid ultrasound videos at QCIF and CIF resolutions, for packet loss rates up to 30%. Quality assessment based on a clinical rating system that provides for independent evaluations of the different parts of the video (subjective), as well as PSNR ratings (objective), shows that encoded videos attain enhanced diagnostic performance under noisy environments, while at the same time achieving significant bandwidth demands reductions.
在本文中，我们定义了用于颈动脉超声医学视频的诊断感兴趣区域（ROI），然后将其用作灵活宏块排序（FMO）切片编码的输入。我们通过启用可变质量切片编码来扩展FMO概念，每个区域的诊断重要性紧密耦合。冗余切片（RS）的使用提高了压缩视频在易出错传输介质上的弹性。我们在一系列五（5）个QCIF和CIF分辨率的颈动脉超声视频上评估了我们的方案，丢包率高达30%。基于临床评级系统的质量评估提供了对视频不同部分的独立评估（主观）以及PSNR评级（客观），结果表明编码后的视频在嘈杂环境下具有增强的诊断性能，同时实现了显著的带宽需求降低。
