Full Text:   <1230>

Summary:  <643>

CLC number: TP391

On-line Access: 2021-09-10

Received: 2020-05-16

Revision Accepted: 2020-10-08

Crosschecked: 2021-08-24

Cited: 0

Clicked: 2266

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Yuxuan Hou

https://orcid.org/0000-0002-0880-6418

Zhong Ren

https://orcid.org/0000-0002-6798-3035

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2021 Vol.22 No.9 P.1169-1178

http://doi.org/10.1631/FITEE.2000234


Learning-based parameter prediction for quality control in three-dimensional medical image compression


Author(s):  Yuxuan Hou, Zhong Ren, Yubo Tao, Wei Chen

Affiliation(s):  State Key Lab of CAD & CG, Zhejiang University, Hangzhou 310058, China; more

Corresponding email(s):   3140104190@zju.edu.cn, renzhong@cad.zju.edu.cn

Key Words:  Medical image compression, High efficiency video coding (HEVC), Quality control, Learning-based


Yuxuan Hou, Zhong Ren, Yubo Tao, Wei Chen. Learning-based parameter prediction for quality control in three-dimensional medical image compression[J]. Frontiers of Information Technology & Electronic Engineering, 2021, 22(9): 1169-1178.

@article{title="Learning-based parameter prediction for quality control in three-dimensional medical image compression",
author="Yuxuan Hou, Zhong Ren, Yubo Tao, Wei Chen",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="22",
number="9",
pages="1169-1178",
year="2021",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2000234"
}

%0 Journal Article
%T Learning-based parameter prediction for quality control in three-dimensional medical image compression
%A Yuxuan Hou
%A Zhong Ren
%A Yubo Tao
%A Wei Chen
%J Frontiers of Information Technology & Electronic Engineering
%V 22
%N 9
%P 1169-1178
%@ 2095-9184
%D 2021
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2000234

TY - JOUR
T1 - Learning-based parameter prediction for quality control in three-dimensional medical image compression
A1 - Yuxuan Hou
A1 - Zhong Ren
A1 - Yubo Tao
A1 - Wei Chen
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 22
IS - 9
SP - 1169
EP - 1178
%@ 2095-9184
Y1 - 2021
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2000234


Abstract: 
quality control is of vital importance in compressing three-dimensional (3D) medical imaging data. Optimal compression parameters need to be determined based on the specific quality requirement. In high efficiency video coding (HEVC), regarded as the state-of-the-art compression tool, the quantization parameter (QP) plays a dominant role in controlling quality. The direct application of a video-based scheme in predicting the ideal parameters for 3D medical image compression cannot guarantee satisfactory results. In this paper we propose a learning-based parameter prediction scheme to achieve efficient quality control. Its kernel is a support vector regression (SVR) based learning model that is capable of predicting the optimal QP from both video-based and structural image features extracted directly from raw data, avoiding time-consuming processes such as pre-encoding and iteration, which are often needed in existing techniques. Experimental results on several datasets verify that our approach outperforms current video-based quality control methods.

基于学习方法的三维医学图像压缩质量控制参数预测

侯宇轩1,任重1,陶煜波1,陈为2
1浙江大学计算机辅助设计与图形学国家重点实验室,中国杭州市,310058
2浙江大学医学院第一附属医院,中国杭州市,310003
摘要:质量控制是三维医学图像压缩过程至关重要的环节,需设定最佳图像压缩参数才能满足特定的压缩质量需求。高效视频编码(HEVC)是目前最先进的压缩工具。其中,量化参数(QP)对HEVC的压缩质量控制起决定性作用,如能对其精确预测,就能完成质量控制的目标;然而,直接将视频压缩领域中的预测方法套用到三维医学数据压缩,精度和效率无法取得令人满意的结果。为此,提出一种基于学习的参数预测方法,用于实现三维医学图像压缩中的高效质量控制。本文方法基于支撑向量回归(SVR),可以直接利用从原始数据中提取的基于视频的特征与基于结构的特征来预测最佳QP,无需经过耗时长的预编码或迭代过程。在若干数据集上的实验结果证明,本文方法比现有方法在预测准确度和速度上表现更好。

关键词:医学图像压缩;高效视频编码(HEVC);质量控制;基于学习方法

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Clark K, Vendt B, Smith K, et al., 2013. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Dig Imag, 26(6):1045-1057.

[2]Dinh KQ, Lee J, Kim J, et al., 2018. Only-reference video quality assessment for video coding using convolutional neural network. Proc 25th IEEE Int Conf on Image Processing, p.2496-2500.

[3]El-Naqa I, Yang YY, Galatsanos NP, et al., 2004. A similarity learning approach to content-based image retrieval: application to digital mammography. IEEE Trans Med Imag, 23(10):1233-1244.

[4]Haralick RM, Shanmugam K, Dinstein IH, 1973. Textural features for image classification. IEEE Trans Syst Man Cybern, 3(6):610-621.

[5]Huynh-Thu Q, Ghanbari M, 2008. Scope of validity of PSNR in image/video quality assessment. Electron Lett, 44(13):800-801.

[6]Kamaci N, Altunbasak Y, Mersereau RM, 2005. Frame bit allocation for the H.264/AVC video coder via Cauchy-density-based rate and distortion models. IEEE Trans Circ Syst Video Technol, 15(8):994-1006.

[7]Kwon DK, Shen MY, Kuo CCJ, 2007. Rate control for H.264 video with enhanced rate and distortion models. IEEE Trans Circ Syst Video Technol, 17(5):517-529.

[8]Lazzerini B, Marcelloni F, Vecchio M, 2010. A multi-objective evolutionary approach to image quality/compression trade-off in JPEG baseline algorithm. Appl Soft Comput, 10(2):548-561.

[9]Liu F, Hernandez-Cabronero M, Sanchez V, et al., 2017. The current role of image compression standards in medical imaging. Information, 8(4):131.

[10]Ma S, Gao W, Lu Y, 2005. Rate-distortion analysis for H.264/AVC video coding and its application to rate control. IEEE Trans Circ Syst Video Technol, 15(12):1533-1544.

[11]Ma SW, Si JJ, Wang SS, 2012. A study on the rate distortion modeling for high efficiency video coding. Proc 19th IEEE Int Conf on Image Processing, p.181-184.

[12]Miaou SG, Chen ST, 2004. Automatic quality control for wavelet-based compression of volumetric medical images using distortion-constrained adaptive vector quantization. IEEE Trans Med Imag, 23(11):1417-1429.

[13]Pan X, Chen ZZ, 2016. Multi-layer quantization control for quality-constrained H.265/HEVC. IEEE Trans Image Process, 26(7):3437-3448.

[14]Patait A, Young E, 2016. High performance video encoding with NVIDIA GPUs. GPU Technology Conf. https://goo.gl/Bdjdgm

[15]Pratt WK, Kane J, Andrews HC, 1969. Hadamard transform image coding. Proc IEEE, 57(1):58-68.

[16]Said A, Pearlman WA, 1996. A new, fast, and efficient image codec based on set partitioning in hierarchical trees. IEEE Trans Circ Syst Video Technol, 6(3):243-250.

[17]Sanchez V, Bartrina-Rapesta J, 2014. Lossless compression of medical images based on HEVC intra coding. IEEE Int Conf on Acoustics, Speech and Signal Processing, p.6622-6626.

[18]Santamaria M, Izquierdo E, Blasi S, et al., 2018. Estimation of rate control parameters for video coding using CNN. IEEE Visual Communications and Image Processing, p.1-4.

[19]Schölkopf B, Smola AJ, Williamson RC, et al., 2000. New support vector algorithms. Neur Comput, 12(5):1207-1245.

[20]Wang HL, Kwong S, 2008. Rate-distortion optimization of rate control for H.264 with adaptive initial quantization parameter determination. IEEE Trans Circ Syst Video Technol, 18(1):140-144.

[21]Wang SJ, Summers RM, 2012. Machine learning and radiology. Med Image Anal, 16(5):933-951.

[22]Wu CY, Su PC, 2013. A content-adaptive distortion-quantization model for H.264/AVC and its applications. IEEE Trans Circ Syst Video Technol, 24(1):113-126.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE