Purpose

Attenuation correction is a critically important step in data correction in positron emission tomography (PET) image formation. The current standard method involves conversion of Hounsfield units from a computed tomography (CT) image to construct attenuation maps (µ-maps) at 511 keV. In this work, the increased sensitivity of long axial field-of-view (LAFOV) PET scanners was exploited to develop and evaluate a deep learning (DL) and joint reconstruction-based method to generate µ-maps utilizing background radiation from lutetium-based (LSO) scintillators.

Methods

Data from 18 subjects were used to train convolutional neural networks to enhance initial µ-maps generated using joint activity and attenuation reconstruction algorithm (MLACF) with transmission data from LSO background radiation acquired before and after the administration of ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) (µ-map_MLACF-PRE and µ-map_MLACF-POST respectively). The deep learning-enhanced µ-maps (µ-map_DL-MLACF-PRE and µ-map_{DL-MLACF-POST}) were compared against MLACF-derived and CT-based maps (µ-map_CT). The performance of the method was also evaluated by assessing PET images reconstructed using each µ-map and computing volume-of-interest based standard uptake value measurements and percentage relative mean error (rME) and relative mean absolute error (rMAE) relative to CT-based method.

Results

No statistically significant difference was observed in rME values for µ-map_DL-MLACF-PRE and µ-map_{DL-MLACF-POST} both in fat-based and water-based soft tissue as well as bones, suggesting that presence of the radiopharmaceutical activity in the body had negligible effects on the resulting µ-maps. The rMAE values µ-map_{DL-MLACF-POST} were reduced by a factor of 3.3 in average compared to the rMAE of µ-map_MLACF-POST. Similarly, the average rMAE values of PET images reconstructed using µ-map_{DL-MLACF-POST} (PET_{DL-MLACF-POST}) were 2.6 times smaller than the average rMAE values of PET images reconstructed using µ-map_MLACF-POST. The mean absolute errors in SUV values of PET_{DL-MLACF-POST} compared to PET_CT were less than 5% in healthy organs, less than 7% in brain grey matter and 4.3% for all tumours combined.

Conclusion

We describe a deep learning-based method to accurately generate µ-maps from PET emission data and LSO background radiation, enabling CT-free attenuation and scatter correction in LAFOV PET scanners.

中文翻译：

---

在长轴 FOV PET 扫描仪中使用 LSO 背景辐射生成全身衰减图的基于深度学习的框架的定量评估

目的

衰减校正是正电子发射断层扫描 (PET) 图像形成中数据校正中至关重要的一步。当前的标准方法涉及将 Hounsfield 单位从计算机断层扫描 (CT) 图像转换为在 511 keV 处构建衰减图（µ-图）。在这项工作中，利用长轴视场 (LAFOV) PET 扫描仪提高的灵敏度来开发和评估深度学习 (DL) 和基于联合重建的方法，以利用基于镥的背景辐射生成 µ-maps (LSO) 闪烁体。

方法

来自 18 名受试者的数据用于训练卷积神经网络，以增强使用联合活动和衰减重建算法 (MLACF) 生成的初始 µ-maps，以及来自 LSO 背景辐射的传输数据，该数据在施用¹⁸ F-氟脱氧葡萄糖 ( ¹⁸ F- FDG)（分别为 µ-map _MLACF-PRE和 µ-map _MLACF-POST）。将深度学习增强的 µ-maps（µ-map _DL-MLACF-PRE和 µ-map _{DL-MLACF-POST}）与 MLACF 派生的和基于 CT 的地图（µ-map _CT). 该方法的性能还通过评估使用每个 µ-map 重建的 PET 图像并计算基于感兴趣体积的标准摄取值测量值以及相对于 CT 的相对平均误差百分比 (rME) 和相对平均绝对误差 (rMAE) 来评估。基于方法。

结果

_{μ-map DL-MLACF-PRE}和 μ-map _{DL-MLACF-POST}在脂肪基和水基软组织以及骨骼中的 rME 值均未观察到统计学上的显着差异，这表明放射性药物活性的存在在身体中对由此产生的 µ-maps 的影响可以忽略不计。_{与 µ-map MLACF} -POST 的 rMAE 相比， µ-map _{DL-MLACF-POST}的 rMAE 值平均降低了 3.3 倍。同样，使用 µ-map _{DL-MLACF-POST} (PET _{DL-MLACF-POST ) 重建的 PET 图像的平均 rMAE 值比使用 µ-map MLACF-POST}重建的 PET 图像的平均 rMAE 值小 2.6 倍. _{与 PET CT}相比， PET _{DL-MLACF-POST}的 SUV 值的平均绝对误差在健康器官中小于 5%，在脑灰质中小于 7%，在所有肿瘤组合中小于 4.3%。

结论

我们描述了一种基于深度学习的方法，可以根据 PET 发射数据和 LSO 背景辐射准确生成 µ 图，从而在 LAFOV PET 扫描仪中实现无 CT 衰减和散射校正。