Department of Radiology, University of Massachusetts Medical School, Worcester, MA, United States of America.
Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL, United States of America.
Phys Med Biol. 2024 Nov 11;69(22). doi: 10.1088/1361-6560/ad8b09.
Deep learning (DL) is becoming increasingly important in generating attenuation maps for accurate attenuation correction (AC) in cardiac perfusion SPECT imaging. Typically, DL models take inputs from initial reconstructed SPECT images, which are performed on the photopeak window and often also on scatter windows. While prior studies have demonstrated improvements in DL performance when scatter window images are incorporated into the DL input, the comprehensive analysis of the impact of employing different scatter windows remains unassessed. Additionally, existing research mainly focuses on applying DL to SPECT scans obtained at clinical standard count levels. This study aimed to assess utilities of DL from two aspects: (1) investigating the impact when different scatter windows were used as input to DL, and (2) evaluating the performance of DL when applied on SPECT scans acquired at a reduced count level.We utilized 1517 subjects, with 386 subjects for testing and the remaining 1131 for training and validation.The results showed that as scatter window width increased from 4% to 30%, a slight improvement was observed in DL estimated attenuation maps. The application of DL models to quarter-count (¼-count) SPECT scans, compared to full-count scans, showed a slight reduction in performance. Nonetheless, discrepancies across different scatter window configurations and between count levels were minimal, with all normalized mean square error (NMSE) values remaining within 2.1% when comparing the different DL attenuation maps to the reference CT maps. For attenuation corrected SPECT slices using DL estimated maps, NMSE values were within 0.5% when compared to CT correction.This study, leveraging an extensive clinical dataset, showed that the performance of DL seemed to be consistent across the use of varied scatter window settings. Moreover, our investigation into reduced count studies indicated that DL could provide accurate AC even at a ¼-count level.
深度学习（DL）在生成准确的心脏灌注 SPECT 成像衰减图方面变得越来越重要。通常，DL 模型从初始重建的 SPECT 图像输入，这些图像是在光电峰窗口上进行的，并且通常也在散射窗口上进行。虽然先前的研究已经证明，在将散射窗口图像纳入 DL 输入时，DL 性能有所提高，但对采用不同散射窗口的全面分析尚未评估。此外，现有研究主要集中在将 DL 应用于在临床标准计数水平获得的 SPECT 扫描上。本研究旨在从两个方面评估 DL 的效用：（1）研究使用不同散射窗口作为 DL 输入时的影响，（2）评估在降低计数水平下应用 DL 时的性能。我们使用了 1517 名受试者，其中 386 名用于测试，其余 1131 名用于训练和验证。结果表明，随着散射窗口宽度从 4%增加到 30%，DL 估计的衰减图略有改善。与全计数扫描相比，DL 模型应用于四分之一计数（¼-count）SPECT 扫描时，性能略有下降。然而，不同散射窗口配置和计数水平之间的差异很小，当将不同的 DL 衰减图与参考 CT 图进行比较时，所有归一化均方误差（NMSE）值都保持在 2.1%以内。对于使用 DL 估计图进行衰减校正的 SPECT 切片，与 CT 校正相比，NMSE 值在 0.5%以内。本研究利用广泛的临床数据集表明，DL 的性能似乎在使用不同的散射窗口设置时保持一致。此外，我们对降低计数研究的调查表明，即使在¼-count 水平下，DL 也可以提供准确的 AC。
