With the development of new radiopharmaceutical therapies, quantitative SPECT/CT has progressively emerged as a crucial tool for dosimetry. One major obstacle of SPECT is its poor resolution, which results in blurring of the activity distribution. Especially for small objects, this so-called partial-volume effect limits the accuracy of activity quantification. Numerous methods for partial-volume correction (PVC) have been proposed, but most methods have the disadvantage of assuming a spatially invariant resolution of the imaging system, which does not hold for SPECT. Furthermore, most methods require a segmentation based on anatomic information. Methods: We introduce DL-PVC, a methodology for PVC of ¹⁷⁷Lu SPECT/CT imaging using deep learning (DL). Training was based on a dataset of 10,000 random activity distributions placed in extended cardiac–torso body phantoms. Realistic SPECT acquisitions were created using the SIMIND Monte Carlo simulation program. SPECT reconstructions without and with resolution modeling were performed using the CASToR and STIR reconstruction software, respectively. The pairs of ground-truth activity distributions and simulated SPECT images were used for training various U-Nets. Quantitative analysis of the performance of these U-Nets was based on metrics such as the structural similarity index measure or normalized root-mean-square error, but also on volume activity accuracy, a new metric that describes the fraction of voxels in which the determined activity concentration deviates from the true activity concentration by less than a certain margin. On the basis of this analysis, the optimal parameters for normalization, input size, and network architecture were identified. Results: Our simulation-based analysis revealed that DL-PVC (0.95/7.8%/35.8% for structural similarity index measure/normalized root-mean-square error/volume activity accuracy) outperforms SPECT without PVC (0.89/10.4%/12.1%) and after iterative Yang PVC (0.94/8.6%/15.1%). Additionally, we validated DL-PVC on ¹⁷⁷Lu SPECT/CT measurements of 3-dimensionally printed phantoms of different geometries. Although DL-PVC showed activity recovery similar to that of the iterative Yang method, no segmentation was required. In addition, DL-PVC was able to correct other image artifacts such as Gibbs ringing, making it clearly superior at the voxel level. Conclusion: In this work, we demonstrate the added value of DL-PVC for quantitative ¹⁷⁷Lu SPECT/CT. Our analysis validates the functionality of DL-PVC and paves the way for future deployment on clinical image data.

随着新放射性药物疗法的发展，定量 SPECT/CT 已逐渐成为剂量测定的重要工具。 SPECT 的一大障碍是其分辨率差，导致活性分布模糊。特别是对于小物体，这种所谓的部分体积效应限制了活动量化的准确性。已经提出了许多用于部分体积校正（PVC）的方法，但大多数方法的缺点是假设成像系统的空间分辨率不变，这不适用于 SPECT。此外，大多数方法需要基于解剖信息进行分割。方法：我们介绍 DL-PVC，一种使用深度学习 (DL) 进行 ¹⁷⁷ Lu SPECT/CT 成像 PVC 的方法。训练基于放置在扩展心脏躯干体模中的 10,000 个随机活动分布的数据集。使用 SIMIND 蒙特卡罗模拟程序创建真实的 SPECT 采集。分别使用 CASTOR 和 STIR 重建软件进行不带分辨率建模和带分辨率建模的 SPECT 重建。地面实况活动分布和模拟 SPECT 图像对用于训练各种 U-Net。对这些 U-Net 性能的定量分析基于结构相似性指数测量或归一化均方根误差等指标，而且还基于体积活动准确性，这是一种新的指标，描述了确定的体素的分数活度浓度与真实活度浓度的偏差小于一定幅度。在此分析的基础上，确定了归一化、输入大小和网络架构的最佳参数。结果：我们基于模拟的分析表明 DL-PVC (0.结构相似性指数测量/归一化均方根误差/体积活性准确度为 95/7.8%/35.8%）优于无 PVC 的 SPECT（0.89/10.4%/12.1%）和迭代 Yang PVC 后的 SPECT（0.94/8.6%/15.1） %）。此外，我们还在不同几何形状的 3 维打印模型的 ¹⁷⁷ Lu SPECT/CT 测量中验证了 DL-PVC。尽管 DL-PVC 显示出与迭代 Yang 方法类似的活性恢复，但不需要分割。此外，DL-PVC 能够纠正其他图像伪影，例如吉布斯振铃，使其在体素水平上明显优越。结论：在这项工作中，我们证明了 DL-PVC 对于定量 ¹⁷⁷ Lu SPECT/CT 的附加价值。我们的分析验证了 DL-PVC 的功能，并为未来临床图像数据的部署铺平了道路。