文献速递骨显像与常规 SPECT放射性药物与辐射防护

深度卷积神经网络用于闪烁相机图像去噪:蒙特卡洛模拟方法

Denoising of Scintillation Camera Images Using a Deep Convolutional Neural Network: A Monte Carlo Simulation Approach.
PubMed 文献 · J Nucl Med · 2019-07-19

本研究利用蒙特卡洛模拟生成含噪与无噪图像对,训练三种卷积神经网络(CNN)对全身骨扫描图像去噪,并与高斯和中值滤波比较。最佳CNN平均降低变异系数92%,均方误差优于标准滤波;临床评估中,半计数CNN滤波骨扫描检测转移灶能力与标准扫描无显著差异。

要点

  • 最佳CNN平均降低变异系数92%,最佳标准滤波降低88%。
  • 最佳CNN的均方误差在圆柱模体和骨扫描图像上分别优于最佳标准滤波68%和20%。
  • CNN滤波可使扫描时间减半,骨转移评估准确性仍良好。

核心结论

  • 无论噪声水平如何,CNN均可高效去噪且几乎不损失分辨率。
  • CNN滤波使扫描时间减半,骨转移评估仍保持良好准确性。

研究设计与样本

  • 使用蒙特卡洛模拟生成的三组训练图像集(模拟骨扫描、含冷热点的圆柱模体、两者混合)各含40000对无噪与含噪图像,训练三种CNN。
  • 用模拟圆柱模体和模拟骨扫描图像评估CNN,以均方误差为差异指标、变异系数估计噪声降低,并与高斯和median滤波比较。
  • 临床评估比较CNN滤波与高斯滤波的半计数骨扫描与标准骨扫描检测转移灶的能力。

主要发现

  • 最佳CNN平均降低变异系数92%,最佳标准滤波降低88%。
  • 最佳CNN的均方误差在圆柱模体图像上平均优于最佳标准滤波68%,在骨扫描图像上优于20%。
  • 圆柱模体和骨扫描的最佳CNN均为各自专用CNN。
  • 标准、CNN滤波和高斯滤波骨扫描检测转移灶能力无显著差异。

临床怎么用

  • CNN滤波可用于全身骨扫描去噪,有望将扫描时间减半而保持骨转移评估准确性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Scintillation camera images contain a large amount of Poisson noise. We have investigated whether noise can be removed in whole-body bone scans using convolutional neural networks (CNNs) trained with sets of noisy and noiseless images obtained by Monte Carlo simulation. Methods: Three CNNs were generated using 3 different sets of training images: simulated bone scan images, images of a cylindric phantom with hot and cold spots, and a mix of the first two. Each training set consisted of 40,000 noiseless and noisy image pairs. The CNNs were evaluated with simulated images of a cylindric phantom and simulated bone scan images. The mean squared error between filtered and true images was used as difference metric, and the coefficient of variation was used to estimate noise reduction. The CNNs were compared with gaussian and median filters. A clinical evaluation was performed in which the ability to detect metastases for CNN- and gaussian-filtered bone scans with half the number of counts was compared with standard bone scans. Results: The best CNN reduced the coefficient of variation by, on average, 92%, and the best standard filter reduced the coefficient of variation by 88%. The best CNN gave a mean squared error that was on average 68% and 20% better than the best standard filters, for the cylindric and bone scan images, respectively. The best CNNs for the cylindric phantom and bone scans were the dedicated CNNs. No significant differences in the ability to detect metastases were found between standard, CNN-, and gaussian-filtered bone scans. Conclusion: Noise can be removed efficiently regardless of noise level with little or no resolution loss. The CNN filter enables reducing the scanning time by half and still obtaining good accuracy for bone metastasis assessment.

来源:J Nucl Med,查看原文。版权归原作者所有。

引用

  1. Minarik D, Enqvist O, Trägårdh E, et al. Denoising of Scintillation Camera Images Using a Deep Convolutional Neural Network: A Monte Carlo Simulation Approach. J Nucl Med. 2019. PMID: 31324711. doi:10.2967/jnumed.119.226613

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。