电子学报 ›› 2019, Vol. 47 ›› Issue (7): 1490-1496.DOI: 10.3969/j.issn.0372-2112.2019.07.012

所属专题: 机器学习与智慧医疗

• 学术论文 • 上一篇    下一篇

基于改进导向滤波算法的低剂量CT图像处理

龙邦媛1, 李康1, 吕发金2, 吕宗伟3   

  1. 1. 中国科学院大学重庆医院放射科, 重庆 400013;
    2. 重庆医科大学附属第一医院放射科, 重庆 400016;
    3. 重庆大学输配电装备及系统安全与新技术国家重点实验室, 重庆 400044
  • 收稿日期:2018-03-13 修回日期:2019-03-15 出版日期:2019-07-25
    • 作者简介:
    • 龙邦媛 女,1980年生于重庆.中国科学院大学重庆医院放射科副主任医师.主要研究方向为医学图像处理和心血管疾病医学影像成像.E-mail:bangyuanl@hotmail.com;吕发金 男,1968年生于四川南充.现为重庆医科大学附属第一医院放射科主任、教授、主任医师、硕士生导师.主要研究方向为CT、MRI成像及图像后处理技术.
    • 基金资助:
    • 重庆市卫生计生委 (No.2016MSXM065,No.ZY201702043); 重庆市渝中区科技委 (No.20180107)

Enhanced Guided Image Filtering for the Processing of the Low-Dose CT Images

LONG Bang-yuan1, LI Kang1, LÜ Fa-jin2, LÜ Zong-wei3   

  1. 1. Department of Radiology, The General Hospital of Chongqing, University of Chinese Academy of Sciences, Chongqing 400013, China;
    2. Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China;
    3. State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University, Chongqing 400044, China
  • Received:2018-03-13 Revised:2019-03-15 Online:2019-07-25 Published:2019-07-25
    • Supported by:
    • Health and Family Planning Commission of Chongqing Municipality (No.2016MSXM065, No.ZY201702043); Chongqing Municipal Yuzhong District Science and Technology Bureau (No.20180107)

摘要: 导向滤波算法是一种有效的基于边保持的平滑滤波算法.然而,由于算法中的正则化系数和细节层增益是固定的,可能会导致边附近出现光晕以及背景中出现大量噪声,降低图像的质量.在本文中,首先给出了一种改进的基于边的权重系数计算方法,它能够较准确地实现边保持,减少光晕现象.其次,提出了基于梯度导向的细节层增益计算方法,可以有效地增强细节并且抑制噪声.实验表明,对于含有大量噪声和小细节的低剂量CT图像,本文方法可以减少噪声和光晕的影响,显著提高图像的对比度,满足临床诊断的需要.

关键词: 对比增强, 导向滤波, 低剂量, 计算机断层成像

Abstract: Guided image filtering is an effective edge-preserving smoothing technique. However, because the regularization parameter and amplification factor of the detail layer are fixed instead of content adaptive, the halo effects near the edges and noise in the background may be incurred, which will degrade the quality of the output images further. In this paper, an improved edge-aware weighting is first proposed to preserve the edges more accurately and reduce the halo effects. Then, the amplification factor of the detail layer is calculated in a gradient-directed way for boosting the details while suppressing the noise. Experimental results on the low-dose CT images with heavy noise and small details show that the proposed method can reduce the halo effects and attenuate the noise while enhancing the contrast efficiently. The visual quality of the output images meets the requirement of the clinical diagnosis.

Key words: contrast enhancement, guided image filter, low-dose, computed tomography

中图分类号: