相关实验视频

Updated: Jul 11, 2025

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy

Published on: January 12, 2022

基于深度学习的无声化模型对不同噪声水平的光学连贯性断层扫描图像的有效性进行定量分析

Furkan Kirik¹, Farid Iskandarov¹, Kamile Melis Erturk¹

¹Department of Ophthalmology, Faculty of Medicine, Bezmialem Vakif University, Adnan Menderes (Vatan) Avenue, Fatih, Istanbul 34093, Turkiye.

Photodiagnosis and photodynamic therapy

|November 10, 2023

概括

深度学习的Noise2Noise模型有效地减少了低噪音水平的增强深度成像-光学连贯性断层扫描 (EDI-OCT) 图像中的噪音. 然而,它的性能随着噪声的增加而下降,可能会改变原有的胆管结构.

科学领域:

眼科医生眼科眼科
医疗成像医学成像
人工智能的人工智能

背景情况:

增强的深度成像-光学一致性断层扫描 (EDI-OCT) 对于可视化胸腔结构至关重要.
在EDI-OCT图像中的噪音可能会掩盖细节,影响诊断准确度.
深度学习 (DL) 模型在医学成像中提供了降噪的潜力.

研究的目的:

量化评估Noise2Noise (N2N) 深度学习模型在消除EDI-OCT图像噪声方面的有效性.
评估不同噪声水平对N2N模型性能的影响.
为了确定N2N是否保留了原始图像特征和结构相似性.

主要方法:

30名健康参与者的亚叶EDI-OCT图像被人工破坏,具有不同的高斯噪声水平 (25,50,75 SD).
N2N深度学习模型拒绝了损坏的图像.
计算和比较了胆道血管度指数 (CVI),对比度与噪声比 (CNR) 和多尺度结构相似度指数 (MS-SSI).

主要成果:

在最低噪音水平 (25N与25dN相比) 上,N2N无声化没有显著改变CVI或CNR.
噪声降低显著改善了MS-SSI在所有噪声级别 (p < 0.001) 的性能.
最高的MS-SSI,表明与原始图像的最大相似性,是在最低的噪音水平 (25dN) 中观察到的.

结论:

N2N DL 模型有效地消除了低噪音的 EDI-OCT 图像.
增加的噪音水平降低了N2N模型保持原始冠状体结构特征和图像相似性的能力.
对于需要精确结构保存的高噪音EDI-OCT图像,N2N可能不足.

关键词:

冠状动脉血管度指数冠状动脉血管度指数对比度与噪声比的比率.拒绝这种行为,就是拒绝.多尺度结构相似性指数多尺度结构相似性指数噪音对噪音噪音对噪音光学连贯性断层扫描技术.

更多相关视频

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography

Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography

Published on: January 15, 2013

相关概念视频

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

Difference from Background: Limit of Detection

Difference from Background: Limit of Detection

The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...