基于深度学习的重建和代重建算法的噪声功率频谱特性:幻影和临床研究
Yoshinori Funama1, Takeshi Nakaura2, Akira Hasegawa3
1Department of Medical Radiation Sciences, Faculty of Life Sciences, Kumamoto University, Kumamoto, Japan.
European journal of radiology
|June 9, 2023
概括
基于深度学习的重建 (DLR) 与混合代重建 (IR) 和基于模型的IR (MBIR) 相比,在CT图像中显著降低了噪音. DLR保持图像纹理,改善临床环境中的整体图像质量.
科学领域:
- 医疗成像医学成像
- 放射学 放射学是一门学科.
- 图像重建 图像的重建
背景情况:
- 代重建 (IR) 技术,如混合IR和基于模型的IR (MBIR) 在计算机断层扫描 (CT) 中用于减少图像噪声.
- 基于深度学习的重建 (DLR) 是一种新兴的技术,有可能进一步提高图像质量.
研究的目的:
- 为了比较噪声功率谱 (NPS) 属性,并分析混合IR,MBIR和DLR的图像质量.
- 在幻影和临床CT研究中,在类似的噪音水平下评估这些重建方法.
主要方法:
- 进行了一项幻象研究和一项与34名患者的临床研究.
- 噪声功率谱 (NPS),噪声强度比 (NMR) 和中央频率比 (CFR) 为DLR,混合IR和MBIR图像进行了计算.
- 放射科医生对临床图像进行了定性分析.
主要成果:
- DLR实现了与混合IR和MBIR相比的噪音水平,但设置较温和.
- 与混合IR和MBIR相比,DLR显示出优异的降噪 (NMR:0.40) 和频率特征 (CFR:0.76).
- 放射科医生认为DLR图像在视觉上优于混合IR和MBIR图像.
结论:
- 基于深度学习的重建 (DLR) 提高了整体CT图像质量.
- DLR有效地降低了图像噪声,同时保持了基本的图像噪声纹理.
- 与传统的CT重建技术相比,DLR具有优势.
相关概念视频
Reconstruction of Signal using Interpolation
254
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
254
Aliasing
166
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
166


