Fig 6 - uploaded by Andreas S. Panayides
Content may be subject to copyright.
Box plots for bitrate requirements for the compared schemes for the nine regular videos of the dataset. Here, the last case, in which the video represents a closeup on the plaque is considered an outlier (see Table V for details). We observe that lower quality 40/34/32 (QP4) may be transmitted over 2.5G of mobile communication networks, the recommended case of 38/30/28 (QP5) is well within the typical 3G data rates, while the highest quality of 36/26/24 (QP6) is appropriate for 3.5G networks. In each plot, we display the median, lower, and upper quartiles and confidence interval around the median. Straight lines connect the nearest observations within 1.5 of the interquartile range (IQR) of the lower and upper quartiles. The "+" sign indicates possible outliers with values beyond the ends of the 1.5 × IQR.
Source publication
We propose a unifying framework for efficient encoding, transmission, and quality assessment of atherosclerotic plaque ultrasound video. The approach is based on a spatially varying encoding scheme, where video-slice quantization parameters are varied as a function of diagnostic significance. Video slices are automatically set based on a segmentati...
Contexts in source publication
Context 1
... Table V, bitrate savings of the proposed variable quality FMO with RS scheme when compared to the default FMO scheme are presented. Right column of Table V incorporates the bitrate gains for each of the three quantization level sets for all videos in the dataset. Fig. 6 depicts the required bitrates of all three investigated encoding ...
Context 2
... introduction of packet losses produces significant drops in video quality. The drop in video quality more than justi- fies the overhead of introducing RSs (slightly increased bitrate compared to FMO ROI encoding, see Fig. 6). To see this, we re-examine the example in Fig. 5. At 15% PLR, the use of RSs keeps the clinical video quality at an acceptable level (>35 dB), while all other methods drop below what is acceptable. In fact, there is a 5-dB drop in quality for FMO and FMO ROI that do not use RSs. From Fig. 4, it is clear that both FMO and FMO ROI ...
Context 3
... Table V, bitrate savings of the proposed variable quality FMO with RS scheme when compared to the default FMO scheme are presented. Right column of Table V incorporates the bitrate gains for each of the three quantization level sets for all videos in the dataset. Fig. 6 depicts the required bitrates of all three investigated encoding ...
Context 4
... introduction of packet losses produces significant drops in video quality. The drop in video quality more than justifies the overhead of introducing RSs (slightly increased bitrate compared to FMO ROI encoding, see Fig. 6). To see this, we re-examine the example in Fig. 5. At 15% PLR, the use of RSs keeps the clinical video quality at an acceptable level (>35 dB), while all other methods drop below what is acceptable. In fact, there is a 5-dB drop in quality for FMO and FMO ROI that do not use RSs. From Fig. 4, it is clear that both FMO and FMO ROI ...
Similar publications
As the knowledge society matures, not only distant, but also off-line universities are trying to provide learners with on-line educational contents. Particularly, high effectiveness of mobile devices for e-Learning has been demonstrated by the university sector, which uses distant learning that is based on blended learning. In this paper, we analyz...
Citations
... research delves into diverse topics, including Medical Video Modality-Aware (m-aware) systems, which adapt encoding, transmission, and evaluation based on individual video modality properties [5][6][7][8][9]. Multilayer and cross-layer optimization systems aim for optimal performance [10][11][12][13], alongside studies focusing on clinical quality assessment protocols and recommendations [14][15][16][17][18][19][20][21][22][23]. ...
This paper investigates a multifaceted approach to fortifying telemedicine services within a self-powered Disaster Recovery Network (DRN) infrastructure. It introduces an array of innovative methodologies and algorithms tailored to address the logistical complexities of constructing an environmentally friendly DRN infrastructure. Additionally, it delves into the fundamental factors influencing the system's behavior, defines key performance indicators, and outlines performance measurement techniques. The study emphasizes the critical need for seamless integration of diverse reliability methods by introducing a novel blockchain-based DRN clustering algorithm, coupled with an intelligently managed solar energy system. Specifically, it presents the "Duty Cycle Estimation (DCE) – Event Driven Duty Cycling (EDDC)" technique using the Ubicom IP 2022 platform. Moreover, it proposes an experimental platform for comprehensive evaluation, assessing network performance, practicality, power efficiency, and resilience under various failure scenarios. This comprehensive assessment serves to advance the field and pave the way for robust and reliable telemedicine services in the face of disaster.
... PSNR ratings). The latter methods allow to deduct the superiority of one codec over the other [20]. Examples of such evaluations are presented in Fig 2, depicting (a) a CCA video (560x448) compressed using a QP of 27 and the x265 codec and (b) a video abstracted from the Netflix dataset (768x432), compressed using a QP of 55 and the AV1 codec. ...
Video streaming applications have witnessed widespread adoption over the past decades due to the rising demand for real-time and on-demand video content across different application domains. As a result, video streaming has become the dominant source of internet traffic, while the abundance of video-driven applications will likely lead to a further increase in the near future, enabled by associated advances in video devices’ capabilities. In that context, there is a strong need to develop efficient compression and video delivery algorithms to accommodate future growth. To this end, this study presents a comparative performance evaluation of six different video codecs. More specifically, we compare the performance of the Versatile Video Coding (VVC) standard developed by the Joint Video Experts Team (JVET) and the AV1 codec developed by the Alliance for Open Media (AOM). Additionally, we assess the capacity of the newly released UVG-266 VVC encoder available from the Ultra Video Group, along with the Essential Video Coding (EVC) standard’s reference implementation. Finally, we include in our experiments the most popular High Efficiency Video Coding (HEVC) implementation, namely x265, together with the VP9 codec. Experimental evaluation based on three general-purpose video datasets (768 \(\times \) 432 and 3840 \(\times \) 2160 video resolutions) and one ultrasound video dataset (560 \(\times \) 448 video resolution) demonstrates that VVC outperforms all rival codecs to date, especially as video resolution increases, followed by AV1.
... The performance of VQA metrics is measured in terms of the correlation between the objective VQA scores and the perceptual ratings provided by human subjects as differential or mean opinion scores (DMOS/ MOS) [71], [66]. Similarly in medical VQA, the medical experts assess the diagnostic capacity of a compressed video, based on clinically established protocols [72]. ...
Recently, there has been an ever-growing demand for virtual reality (VR) and 360° video applications. Different from conventional 2D videos, 360° videos take users into an immersive experience by providing them with a navigable panoramic view. However, achieving adequate quality of experience (QoE) levels poses significant network challenges, especially in mobile delivery setups. Despite the tremendous improvements offered by 5G and beyond mobile networks, streaming 360° videos in a similar fashion to 2D videos is suboptimal, while scaling at high numbers questions the feasibility of the endeavor. This paper explores the utilization of caching and multicasting solutions for the mobile delivery of VR and 360° videos. First, an overview of immersive technologies and their distinctive characteristics is provided. Then, we discuss the network challenges associated with 360° videos and the role of implementing robust caching and multicasting schemes that exploit the unique features of 360° videos and capitalize on the correlations among end-users’ viewports. Having established the foundations and challenges of 360° video streaming, we continue with a comparison of the state-of-the-art literature, while focusing on video streaming optimization aspects. We conclude our work by discussing the status and future research directions.
... Indeed, most of them resort to classical IQA and VQA metrics already designed for natural data. Moreover, all of these works focus only on the quality of video in the context of wireless network transmission and compression [16], [29]- [31]. For example, for quality assessment of compressed laparoscopic videos, Kumcu et al. [32] have used average PSNR, reduced-reference Video Quality Metric (VQM) [33] and average of frame-based FR high dynamic range visual difference predictor (HDR-VDP-2) metric [34]. ...
Video quality assessment is a challenging problem having a critical significance in the context of medical imaging. For instance, in laparoscopic surgery, the acquired video data suffers from different kinds of distortion that not only hinder surgery performance but also affect the execution of subsequent tasks in surgical navigation and robotic surgeries. For this reason, we propose in this paper neural network-based approaches for distortion classification as well as quality prediction. More precisely, a Residual Network (ResNet) based approach is firstly developed for simultaneous ranking and classification task. Then, this architecture is extended to make it appropriate for the quality prediction task by using an additional Fully Connected Neural Network (FCNN). To train the overall architecture (ResNet and FCNN models), transfer learning and end-to-end learning approaches are investigated. Experimental results, carried out on a new laparoscopic video quality database, have shown the efficiency of the proposed methods compared to recent conventional and deep learning based approaches.
... Indeed, most of them resort to classical IQA and VQA metrics already designed for natural data. Moreover, all of these works focus only on the quality of video in the context of wireless network transmission and compression [16], [29]- [31]. For example, for quality assessment of compressed laparoscopic videos, Kumcu et al. [32] have used average PSNR, reduced-reference Video Quality Metric (VQM) [33] and average of frame-based FR high dynamic range visual difference predictor (HDR-VDP-2) metric [34]. ...
Video quality assessment is a challenging problem having a critical significance in the context of medical imaging. For instance, in laparoscopic surgery, the acquired video data suffers from different kinds of distortion that not only hinder surgery performance but also affect the execution of subsequent tasks in surgical navigation and robotic surgeries. For this reason, we propose in this paper neural network-based approaches for distortion classification as well as quality prediction. More precisely, a Residual Network (ResNet) based approach is firstly developed for simultaneous ranking and classification task. Then, this architecture is extended to make it appropriate for the quality prediction task by using an additional Fully Connected Neural Network (FCNN). To train the overall architecture (ResNet and FCNN models), transfer learning and end-to-end learning approaches are investigated. Experimental results, carried out on a new laparoscopic video quality database, have shown the efficiency of the proposed methods compared to recent conventional and deep learning based approaches.
... Additionally, video streaming dominates the delivery of video content. Video-On-Demand (VOD) and Video streaming applications worldwide are experiencing an exponential growth with applications such as video based learning, adaptive medical video communications [5][6][7], mobile gaming and AR/VR. According to Cisco [8], global IP video traffic will account for 82% of the internet traffic in 2020 which is significantly higher than 70% back in 2015. ...
... Additionally, video streaming dominates the delivery of video content. Video-On-Demand (VOD) and Video streaming applications worldwide are experiencing an exponential growth with applications such as video based learning, adaptive medical video communications [5][6][7], mobile gaming and AR/VR. According to Cisco [8], global IP video traffic will account for 82% of the internet traffic in 2020 which is significantly higher than 70% back in 2015. ...
The dissertation proposes the use of a multi-objective optimization framework for designing and selecting among enhanced GOP configurations in video compression standards. The proposed methods achieve fine optimization over a set of general modes that include: (i) maximum video quality, (ii) minimum bitrate, (iii) maximum encoding rate (previously minimum encoding time mode) and (iv) can be shown to improve upon the YouTube/Netflix default encoder mode settings over a set of opposing constraints to guarantee satisfactory performance. The dissertation describes the implementation of a codec-agnostic approach using different video coding standards (x265, VP9, AV1) on a wide range of videos derived from different video datasets. The results demonstrate that the optimal encoding parameters obtained from the Pareto front space can provide significant bandwidth savings without sacrificing video quality. This is achieved by the use of effective regression models that allow for the selection of video encoding settings that are jointly optimal in the encoding time, bitrate, and video quality space. The dissertation applies the proposed methods to x265, VP9, AV1 and using new GOP configurations in x265, delivering over 40% of the optimal encodings in two standard reference videos.
... Diagnostically driven video encoding has come under limelight recently and there have been some recent studies under this domain [9][10][11][12][13][14][15][16]. The aim of such kind of video encoding is to identify regions of interest (ROI) in medical videos, e.g., a tumor in a colonoscopy imagery, and then compressing these regions in a better quality than other regions. ...
Video compression in medical video streaming is one of the key technologies associated with mobile healthcare. Seamless delivery of medical video streams over a resource constrained network emphasizes the need of a video codec that requires minimum bitrates and maintains high perceptual quality. This paper presents a comparative study between High Efficiency Video Coding (HEVC) and its potential successor Versatile Video Coding (VVC) in the context of healthcare. A large-scale subjective experiment comprising of twenty-four non-expert participants is presented for eight different test conditions in Full High Definition (FHD) videos. The presented analysis highlights the impact of compression artefacts on the perceptual quality of HEVC and VVC processed videos. Our results and findings show that VVC clearly outperforms HEVC in terms of achieving higher compression, while maintaining high quality in FHD videos. VVC requires upto 40% less bitrate for encoding an FHD video at excellent perceptual quality. We have provided rate-quality curves for both encoders and a degree of overlap across both codecs in terms of perceptual quality. Overall, there is a 71% degree of overlap in terms of quality between VVC and HEVC compressed videos for eight different test conditions.
... A completely automated multi-resolution edge snapper (CAMES) was proposed where a multi-resolution framework was employed combining scale-space and statistical classification, followed by automatic segmentation for carotid artery analysis. 95 CAMES had an improvement in segmentation error compared with CALEX as 8% and 42% for the LI and MA interface boundary detection. Bias value had a huge progress of 36% and the figure of merit was 95.8% which was 8.4% improvement compared with CALEX. ...
Stroke is one of the prominent causes of death in the recent days. The existence of susceptible plaque in the carotid artery can be used in ascertaining the possibilities of cardiovascular diseases and long-term disabilities. The imaging modality used for early screening of the disease is B-mode ultrasound image of the person in the artery area. The objective of this article is to give a widespread review of the imaging modes and methods used for studying the carotid artery for identifying stroke, atherosclerosis and related cardiovascular diseases. We encompass the review in methods used for artery wall tracking, intima–media, and lumen segmentation which will help in finding the extent of the disease. Due to the characteristics of the imaging modality used, the images have speckle noise which worsens the image quality. Adaptive homomorphic filtering with wavelet and contourlet transforms, Levy Shrink, gamma distribution were used for image denoising. Learning-based neural network approaches for denoising give better edge preservation. Domain knowledge-based segmentation approaches have proved to provide more accurate intima–media thickness measurements. There is a requirement of useful fully automatic segmentation approaches, 3D, 4D systems, and plaque motion analysis. Taking into consideration the image priors like geometry, imaging physics, intensity and temporal data, image analysis has to be performed. Encouragingly more research has focused on content-specific segmentation and classification techniques. With the evaluation of machine learning algorithms, classifying the image as with or without a fat deposit has gained better accuracy and sensitivity. Machine learning–based approaches like self-organizing map, k-nearest neighborhood and support vector machine achieve promising accuracy and sensitivity in classification. The literature reveals that there is more scope in identifying a patient-specific model in a fully automatic manner.
... A prevailing concept that has been used across medical video modalities involves diagnostically driven encoding [5], [7], [10]. The latter approach, concerns the identification of diagnostic region(s)-of-interest (d-ROIs), using either manual (outlined by a medical expert) or automatic (computer-based segmentation methods) means (see Figs. [2][3]. ...
... A non-exhaustive list of diagnostically driven video technologies include cardiac [11], [12], abdominal aortic aneurysm [13], common carotid artery [10], and femoral artery, ultrasound videos [14], as well as trauma [15], surgery [16], and emergency scenery videos [17]. ...
... Ultrasound image examples of the common carotid artery video dataset I. Fig. 2(a)-(c) depict different ultrasound videos of the CCA dataset I while Fig. 2(c) further depicts the atherosclerotic plaque diagnostic region-of-interest (d-ROI) delineated with a white line. Fig. 2(d) demonstrates an ultrasound video used in [10] where d-ROIs are encoded in higher quality than the background, less diagnostically important regions. difference for equivalent PSNR quality between the two investigated codecs. ...
Video compression is the core technology in mobile (mHealth) and electronic (eHealth) health video streaming applications. With global video traffic projected to reach 82% of all Internet traffic by 2022, there is a strong need to develop efficient compression algorithms to accommodate expected future growth. For the first time in decades, and especially since ISO/IEC MPEG and ITU-T VCEG expert groups strategically joined forces to develop the highly successful H.264/AVC standard, we have two distinct initiatives competing for the best performing video codec. On the one hand, we have the Alliance for Open Media (AOM) that support a new, royalty free video codec generation, termed AV1, based on VP8 and VP9 efforts. On the other hand, the Joint Video Exploration Team (JVET) has been developing the Versatile Video Codec (VVC) as the successor of the High Efficiency Video Coding (HEVC) standard. At the same time, the breadth of applications utilizing video codecs, involving significant content variability and moving across the video resolution ladder, to satisfy different constraints, have resulted in mixed literature results, with respect to the best performing codec. In this paper, we compare the performance of emerging VVC and AV1 codecs, along with popular HEVC implementations, namely the HEVC Test Model (HM) and x265, as well as earlier, VP9 codec, and investigate their suitability for medical applications. To the best of our knowledge, this is the first performance comparison of emerging VVC and AV1 video codecs for use in the healthcare domain. Experimental evaluation based on three datasets (ultrasound, emergency scenery, and general-purpose videos) demonstrate that VVC outperforms all rival codecs while AV1 achieves better compression efficiency than HEVC in all cases but low-resolution (560x448@40Hz) ultrasound videos of the common carotid artery. Furthermore, the use of video despeckling prior to ultrasound video compression can provide significant bitrate savings.
