页面历史记录

提示

title	提示 \| 眼见为实

主要更新与大生物医药领域的一些东西……

面板

title	基于学习的光学相干层析成像图像处理

面板

title	研究内容 \| 深度学习在OCT 降噪上的应用

Optical coherence tomography (OCT) is susceptible to the coherent noise, which is the speckle noise that deteriorates contrast and the detail structural information of OCT images, thus imposing significant limitations on the diagnostic capability of OCT. In this paper, we propose a novel OCT image denoising method by using an end-to-end deep learning network with a perceptually-sensitive loss function. The method has been validated on OCT images acquired from healthy volunteers’ eyes. The label images for training and evaluating OCT denoising deep learning models are images generated by averaging 50 frames of respective registered B-scans acquired from a region with scans occurring in one direction. The results showed that the new approach can outperform other related denoising methods on the aspects of preserving detail structure information of retinal layers and improving the perceptual metrics in the human visual perception.

面板

title	研究内容 \| 深度学习用于OCT 同时降噪及超分辨上的应用

Image Removed

面板

titleColor	gray
borderStyle	solid
title	个人基本信息

姓名：邱彬

研究方向：深度学习在医学图像处理上的应用

年级：2020级硕转博

邮箱：qiub@pku.edu.cn

地址：北京大学王克桢楼

面板

title	相关人员

深度学习技术：姜喆、游云飞

OCT成像技术：黄智宇、胡毅成

面板

title	发表论文清单

一作文章：

Bin Qiu^#, Zhiyu Huang, Xi Liu, Xiangxi Meng, Yunfei You, Gangjun Liu, Kun Yang, Andreas Maier, Qiushi Ren,
and
Yanye Lu^*,
"Noise
“Noise reduction in optical coherence tomography images using a deep neural network with perceptually-sensitive loss function,
"
” Biomed
.
Opt
.
Express 11, 817-830 (2020). 论文链接
Bin Qiu^#, B., Yunfei You, Y., Zhiyu Huang, Z., Xiangxi Meng, X., Zhe Jiang, Z., Chuanqing Zhou, C., Gangjun Liu, G., Kun Yang, K., Qiushi Ren, Q. and Yanye Lu, Y. (2020), N2NSR‐OCT^*, “N2NSR-OCT: Simultaneous denoising Denoising and super‐resolution in optical coherence tomography images using semi‐supervised deep learning. J. Biophotonics. Accepted Author Manuscript. doi:10.1002/jbio.202000282Super-resolution in Optical Coherence Tomography Images using Semi-supervised Deep Learning,” J Biophotonics 13, e202000282 (2020). 论文链接

其他作者序列文章：

Zhe Jiang^#, Zhiyu Huang, Bin Qiu, Xiangxi Meng, Yunfei You, Xi Liu, Gangjun Liu, Chuangqing Chuanqing Zhou, Kun Yang, Andreas Maier, Qiushi Ren, and Yanye Lu^*, "Comparative “Comparative study of deep learning models for optical coherence tomography angiography," ” Biomed . Opt . Express 11, 1580-1597 (2020) 论文链接

提示

title	提示 \| 眼见为实

主要更新与大生物医药领域的一些东西……

面板

title	基于学习的光学相干层析成像图像处理

Image Removed Image Removed

面板

title	研究内容 \| 深度学习在OCT 降噪上的应用

Optical coherence tomography (OCT) is susceptible to the coherent noise, which is the speckle noise that deteriorates contrast and the detail structural information of OCT images, thus imposing significant limitations on the diagnostic capability of OCT. In this paper, we propose a novel OCT image denoising method by using an end-to-end deep learning network with a perceptually-sensitive loss function. The method has been validated on OCT images acquired from healthy volunteers’ eyes

.

The label images for training and evaluating OCT denoising deep learning models are images generated by averaging 50 frames of respective registered B-scans acquired from a region with scans occurring in one direction. The results showed that the new approach can outperform other related denoising methods on the aspects of preserving detail structure information of retinal layers and improving the perceptual metrics in the human visual perception.