Hashimoto Fumio, Ote Kibo, Onishi Yuya, Tashima Hideaki, Akamatsu Go, Iwao Yuma, Takahashi Miwako, Yamaya Taiga
Central Research Laboratory, Hamamatsu Photonics K. K., 5000 Hirakuchi, Hamana-ku, Hamamatsu 434-8601, Japan.
Institute for Quantum Medical Science, National Institutes for Quantum Science and Technology (QST), 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan.
Phys Med Biol. 2025 May 16;70(10). doi: 10.1088/1361-6560/add63f.
. Positron emission tomography (PET) is affected by statistical noise due to constraints on tracer dose and scan duration, impacting both diagnostic performance and quantitative accuracy. While deep learning-based PET denoising methods have been used to improve image quality, they may introduce over-smoothing, which can obscure critical structural details and compromise quantitative accuracy. We propose a method for making a deep learning solution more reliable and apply it to the conditional deep image prior (DIP).. We introduce the idea ofin the optimization process of conditional DIP, enabling the identification of unstable regions within the network's optimization trajectory. Our method incorporates a stability map, which is derived from multiple intermediate outputs of a moderate neural network at different optimization steps. The final denoised PET image is then obtained by computing a linear combination of the DIP output and the original reconstructed PET image, weighted by the stability map.. We employed eight high-resolution brain PET datasets for comparison. Our method effectively reduces background noise while preserving small structure details in brain [F]FDG PET images. Comparative analysis demonstrated that our approach outperformed existing methods in terms of peak-to-valley ratio and background noise suppression across various low-dose levels. Additionally, region-of-interest analysis confirmed that the proposed method maintains quantitative accuracy without introducing under- or over-estimation. Furthermore, we applied our method to full-dose PET data to assess its impact on image quality. The results revealed that the proposed method significantly reduced background noise while preserving the peak-to-valley ratio at a level comparable to that of unfiltered full-dose PET images.. The proposed method introduces a robust approach to deep learning-based PET denoising, enhancing its reliability and preserving quantitative accuracy. Furthermore, this strategy can potentially advance performance in high-sensitivity PET scanners and surpass the limit of image quality inherent to PET scanners.
正电子发射断层扫描（PET）由于示踪剂剂量和扫描持续时间的限制而受到统计噪声的影响，这会影响诊断性能和定量准确性。虽然基于深度学习的PET去噪方法已被用于提高图像质量，但它们可能会引入过度平滑，从而模糊关键的结构细节并损害定量准确性。我们提出了一种使深度学习解决方案更可靠的方法，并将其应用于条件深度图像先验（DIP）。我们在条件DIP的优化过程中引入了的概念，从而能够识别网络优化轨迹内的不稳定区域。我们的方法结合了一个稳定性图，该图是从一个适度神经网络在不同优化步骤的多个中间输出中导出的。然后，通过计算DIP输出与原始重建PET图像的线性组合，并由稳定性图加权，获得最终的去噪PET图像。我们使用了八个高分辨率脑部PET数据集进行比较。我们的方法有效地降低了背景噪声，同时保留了脑部[F]FDG PET图像中的小结构细节。比较分析表明，在各种低剂量水平下，我们的方法在峰谷比和背景噪声抑制方面优于现有方法。此外，感兴趣区域分析证实，所提出的方法保持了定量准确性，而不会引入低估或高估。此外，我们将我们的方法应用于全剂量PET数据，以评估其对图像质量的影响。结果表明，所提出的方法显著降低了背景噪声，同时将峰谷比保持在与未滤波的全剂量PET图像相当的水平。所提出的方法引入了一种基于深度学习的PET去噪的稳健方法，提高了其可靠性并保留了定量准确性。此外，这种策略有可能提高高灵敏度PET扫描仪的性能，并超越PET扫描仪固有的图像质量极限。
