期刊
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
卷 60, 期 4, 页码 1111-1121出版社
SPRINGER HEIDELBERG
DOI: 10.1007/s11517-022-02538-8
关键词
Retinal diseases; Optical coherence tomography; Sigmoid function; Image enhancement; Analysis; Image processing
类别
资金
- Youth Science and Technology Fund of Guangxi Natural Science Foundation [2021GXNSFBA220075]
- Guangxi Postdoctoral Special Support Fund [C21RSC90ZN02]
- Scientific Research Fund [YXRSZN03, UF20035Y]
Speckle noise reduces image contrast, limiting the usage of optical coherence tomography (OCT) images. This study proposes a fast and robust image enhancement framework using non-linear statistical parametric technique, improving the interpretability and perception of OCT images. Experimental results demonstrate its effectiveness in providing both quantitative and qualitative information.
Speckle noise reduces the image contrast significantly making the highly scattering structures boundaries difficult to distinguish. This has limited the usage of optical coherence tomography (OCT) images in clinical routine and hindered its potential by depriving clinicians from assessing useful information that are needed in disease monitoring, treatment, progression, and decision making. To overcome this limitation, we propose a fast and robust OCT image enhancement framework using non-linear statistical parametric technique. In the proposed framework, we utilize prior statistical information to model the image to follow Gaussian distribution. After which, a newly designed dual-parametric sigmoid function (DPSF) is utilized to control the dynamic range and contrast level of the image. To balance the intensity range and contrast level, both linear and non-linear normalization operations are performed, then followed by a mapping operation to obtain the enhanced image. Experimentation results on the three OCT vendors show that the proposed method obtained high values in EME, PSNR, SSIM, rho, and low value in MSE of 36.72, 38.87, 0.87, 0.98, and 25.12 for Cirrus; 40.77, 41.84, 0.89, 0.98, and 22.15 for Spectralis; and 30.81, 32.10, 0.81, 0.96, and 28.55 for Topcon OCT devices, respectively. The proposed DPSF framework performs better than the state-of-the-art methods and improves the interpretability and perception of the OCT images, which can provide clinicians and computer vision program with good quantitative and qualitative information.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据