Lv Li, Zeng Gengsheng L, Chen Gaoyu, Ding Wenxiang, Weng Fenghua, Huang Qiu
School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
Department of Computer Science, Utah Valley University, Orem, USA.
Med Phys. 2024 Sep;51(9):6161-6175. doi: 10.1002/mp.17191. Epub 2024 Jun 3.
The back-projection strategies such as confidence weighting (CW) and most likely annihilation position (MLAP) have been adopted into back-projection-and-filtering-like (BPF-like) deep reconstruction model and shown great potential on fast and accurate PET reconstruction. Although the two methods degenerate to an identical model at the time resolution of 0 ps, they represent two distinct approaches at the realistic time resolutions of current commercial systems. There is a lack of a systematic and fair assessment on these differences.
This work aims to analyze the impact of back-projection variants on CNN-based PET image reconstruction to find the most effective back-projection model, and ultimately contribute to accurate PET reconstruction.
Different back-projection strategies (CW and MLAP) and different angular view processing methods (view-summed and view-grouped) were considered, leading to the comparison of four back-projection variants integrated with the same CNN filtration model. Meanwhile, we investigated two strategies of physical effect compensation, either introducing pre-corrected data as the input or adding a channel of attenuation map to the CNN model. After training models separately on Monte-Carlo-simulated BrainWeb phantoms with full dose (events = 3×10), we tested them on both simulated phantoms and clinical brain scans with two dosage levels. For the performance assessment, peak signal-to-noise ratio (PSNR) and root mean square error (RMSE) were used to evaluate the pixel-wise error, structural similarity index (SSIM) to evaluate the structural similarity, and contrast recovery coefficient (CRC) in manually selected ROI to compare the region recovery.
Compared to two MLAP-based histo-image reconstruction models, two CW-based back-projected image methods produced clearer, sharper, and more detailed images, from both simulated and clinical data. For angular view processing methods, view-grouped histo-image improved image quality, while view-grouped cwbp-image showed no advantage except for contrast recovery. Quantitative analysis on simulated data demonstrated that the view-summed cwbp-image model achieved the best PSNR, RMSE, SSIM, while the 8-view cwbp-image model achieved the best CRC in lesions and the white matter. Additionally, the multi-channel input model including the back-projection image and attenuation map was proved to be the most efficient and simplest method for compensating for physical effects for brain data. Applying Gaussian blur to the histo-image yielded images with limited improvement. All above results hold for both the half-dose and the full-dose cases.
For brain imaging, the evaluation based on metrics PSNR, RMSE, SSIM, and CRC indicates that the view-summed CW-based back-projection variant is the most effective input for the BPF-like reconstruction model using CNN filtration, which can involve the attenuation map through an additional channel to effectively compensate for physical effects.
诸如置信加权（CW）和最可能湮灭位置（MLAP）等反投影策略已被纳入类似反投影与滤波（BPF-like）的深度重建模型中，并在快速准确的PET重建方面显示出巨大潜力。尽管这两种方法在时间分辨率为0 ps时会退化为相同的模型，但在当前商业系统的实际时间分辨率下，它们代表了两种不同的方法。目前缺乏对这些差异的系统且公平的评估。
本研究旨在分析反投影变体对基于CNN的PET图像重建的影响，以找到最有效的反投影模型，并最终有助于实现准确的PET重建。
考虑了不同的反投影策略（CW和MLAP）以及不同的角度视图处理方法（视图求和和视图分组），从而对与相同CNN滤波模型集成的四种反投影变体进行比较。同时，我们研究了两种物理效应补偿策略，即引入预校正数据作为输入或在CNN模型中添加衰减图通道。在使用全剂量（事件数 = 3×10）的蒙特卡洛模拟BrainWeb体模上分别训练模型后，我们在模拟体模和两种剂量水平的临床脑部扫描上对它们进行测试。对于性能评估，使用峰值信噪比（PSNR）和均方根误差（RMSE）来评估逐像素误差，使用结构相似性指数（SSIM）来评估结构相似性，并在手动选择的感兴趣区域中使用对比度恢复系数（CRC）来比较区域恢复情况。
与两个基于MLAP的组织图像重建模型相比，两个基于CW的反投影图像方法从模拟数据和临床数据中都产生了更清晰、更锐利和更详细的图像。对于角度视图处理方法，视图分组的组织图像提高了图像质量，而视图分组的cwbp图像除了对比度恢复外没有优势。对模拟数据的定量分析表明，视图求和的cwbp图像模型实现了最佳的PSNR、RMSE、SSIM，而8视图的cwbp图像模型在病变和白质中实现了最佳的CRC。此外，包括反投影图像和衰减图的多通道输入模型被证明是补偿脑部数据物理效应的最有效和最简单的方法。对组织图像应用高斯模糊产生的图像改进有限。上述所有结果在半剂量和全剂量情况下均成立。
对于脑部成像，基于PSNR、RMSE、SSIM和CRC指标的评估表明，基于视图求和的CW反投影变体是使用CNN滤波的BPF-like重建模型的最有效输入，它可以通过额外的通道纳入衰减图以有效补偿物理效应。
