arrow
返回

Live 4D-OCT denoising with self-supervised deep learning

delete2023-04-08
delete6
delete
OA
AI
J
Jonas Nienhaus *
P
Philipp Matten
A
Anja Britten
J
Julius Scherer
E
Eva Höck
A
Alexander Freytag
W
Wolfgang Drexler
R
Rainer A. Leitgeb
T
Thomas Schlegl
T
Tilman Schmoll
DOI:10.1038/s41598-023-32695-1delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
By providing three-dimensional visualization of tissues and instruments at high resolution, live volumetric optical coherence tomography (4D-OCT) has the potential to revolutionize ophthalmic surgery. However, the necessary imaging speed is accompanied by increased noise levels. A high data rate and the requirement for minimal latency impose major limitations for real-time noise reduction. In this work, we propose a low complexity neural network for denoising, directly incorporated into the image reconstruction pipeline of a microscope-integrated 4D-OCT prototype with an A-scan rate of 1.2 MHz. For this purpose, we trained a blind-spot network on unpaired OCT images using a self-supervised learning approach. With an optimized U-Net, only a few milliseconds of additional latency were introduced. Simultaneously, these architectural adaptations improved the numerical denoising performance compared to the basic setup, outperforming non-local filtering algorithms. Layers and edges of anatomical structures in B-scans were better preserved than with Gaussian filtering despite comparable processing time. By comparing scenes with and without denoising employed, we show that neural networks can be used to improve visual appearance of volumetric renderings in real time. Enhancing the rendering quality is an important step for the clinical acceptance and translation of 4D-OCT as an intra-surgical guidance tool.
Keyword:
COHERENCE
SPECKLE
DISPERSION
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Scientific Reports 封面图
Scientific Reports
IF:
3.9
论文数:
28.1W
被引数:
83.5W

机构

C
carl zeiss ag
学者数:
384
论文数: 293
被引数: 0
M
Medical University of Vienna
学者数:
3.7W
论文数: 2.5W
被引数: 3.1W
引用论文

引用论文

err
IF0
err
err0
PREAI
err
err分享
err收藏
A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head
err2019-10-08
err83
errOAAI
errDevalla, Sripad Krishna; Subramanian, Giridhar; Tan Hung Pham; Wang, Xiaofei; Perera, Shamira; Tun, Tin A.; Aung, Tin; Schmetterer, Leopold; Thiery, Alexandre H.; Girard, Michael J. A.
err分享
err收藏
err分享
err收藏
Speckle-modulating optical coherence tomography in living mice and humans活体小鼠和人类的散斑调制光学相干断层扫描
err2017-06-20
err127
errOAAI
errLiba, Orly; Lew, Matthew D.; SoRelle, Elliott D.; Dutta, Rebecca; Sen, Debasish; Moshfeghi, Darius M.; Chu, Steven; de la Zerda, Adam
err分享
err收藏
Automatically Enhanced OCT Scans of the Retina: A proof of concept study
err2020-05-08
err24
errOAAI
errApostolopoulos, Stefanos; Salas, Jazmin; Ordonez, Jose L. P.; Tan, Shern Shiou; Ciller, Carlos; Ebneter, Andreas; Zinkernagel, Martin; Sznitman, Raphael; Wolf, Sebastian; De Zanet, Sandro; Munk, Marion R.
err分享
err收藏
Live volumetric (4D) visualization and guidance of in vivo human ophthalmic surgery with intraoperative optical coherence tomography
err2016-08-19
err97
errOAAI
errCarrasco-Zevallos, O. M.; Keller, B.; Viehland, C.; Shen, L.; Waterman, G.; Todorich, B.; Shieh, C.; Hahn, P.; Farsiu, S.; Kuo, A. N.; Toth, C. A.; Izatt, J. A.
err分享
err收藏
Sequential Dose-Dense Doxorubicin, Paclitaxel, and Cyclophosphamide for Resectable High-Risk Breast Cancer: Feasibility and Efficacy
err1999-01-01
err0
PREAI
errC. Hudis; A. Seidman; J. Baselga; G. Raptis; D. Lebwohl; T. Gilewski; M. Moynahan; N. Sklarin; D. Fennelly; J. P.A. Crown; A. Surbone; M. Uhlenhopp; E. Riedel; T. J. Yao; L. Norton
err分享
err收藏
Use of Linearized Euler Equations for Supersonic Jet Noise Prediction
err1998-02-01
err0
PREAI
errR. R. Mankbadi; R. Hixon; S.-H. Shih; L. A. Povinelli
err分享
err收藏
学者 查看更多内容