Mansouri Zahra, Salimi Yazdan, Akhavanallaf Azadeh, Shiri Isaac, Teixeira Eliluane Pirazzo Andrade, Hou Xinchi, Beauregard Jean-Mathieu, Rahmim Arman, Zaidi Habib
Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland.
Department of Radiology, University of British Columbia, Vancouver, BC, Canada.
Eur J Nucl Med Mol Imaging. 2024 May;51(6):1516-1529. doi: 10.1007/s00259-024-06618-9. Epub 2024 Jan 25.
Accurate dosimetry is critical for ensuring the safety and efficacy of radiopharmaceutical therapies. In current clinical dosimetry practice, MIRD formalisms are widely employed. However, with the rapid advancement of deep learning (DL) algorithms, there has been an increasing interest in leveraging the calculation speed and automation capabilities for different tasks. We aimed to develop a hybrid transformer-based deep learning (DL) model that incorporates a multiple voxel S-value (MSV) approach for voxel-level dosimetry in [Lu]Lu-DOTATATE therapy. The goal was to enhance the performance of the model to achieve accuracy levels closely aligned with Monte Carlo (MC) simulations, considered as the standard of reference. We extended our analysis to include MIRD formalisms (SSV and MSV), thereby conducting a comprehensive dosimetry study.
We used a dataset consisting of 22 patients undergoing up to 4 cycles of [Lu]Lu-DOTATATE therapy. MC simulations were used to generate reference absorbed dose maps. In addition, MIRD formalism approaches, namely, single S-value (SSV) and MSV techniques, were performed. A UNEt TRansformer (UNETR) DL architecture was trained using five-fold cross-validation to generate MC-based dose maps. Co-registered CT images were fed into the network as input, whereas the difference between MC and MSV (MC-MSV) was set as output. DL results are then integrated to MSV to revive the MC dose maps. Finally, the dose maps generated by MSV, SSV, and DL were quantitatively compared to the MC reference at both voxel level and organ level (organs at risk and lesions).
The DL approach showed slightly better performance (voxel relative absolute error (RAE) = 5.28 ± 1.32) compared to MSV (voxel RAE = 5.54 ± 1.4) and outperformed SSV (voxel RAE = 7.8 ± 3.02). Gamma analysis pass rates were 99.0 ± 1.2%, 98.8 ± 1.3%, and 98.7 ± 1.52% for DL, MSV, and SSV approaches, respectively. The computational time for MC was the highest (~2 days for a single-bed SPECT study) compared to MSV, SSV, and DL, whereas the DL-based approach outperformed the other approaches in terms of time efficiency (3 s for a single-bed SPECT). Organ-wise analysis showed absolute percent errors of 1.44 ± 3.05%, 1.18 ± 2.65%, and 1.15 ± 2.5% for SSV, MSV, and DL approaches, respectively, in lesion-absorbed doses.
A hybrid transformer-based deep learning model was developed for fast and accurate dose map generation, outperforming the MIRD approaches, specifically in heterogenous regions. The model achieved accuracy close to MC gold standard and has potential for clinical implementation for use on large-scale datasets.
准确的剂量测定对于确保放射性药物治疗的安全性和有效性至关重要。在当前的临床剂量测定实践中，MIRD形式体系被广泛应用。然而，随着深度学习（DL）算法的快速发展，利用其计算速度和针对不同任务的自动化能力的兴趣日益增加。我们旨在开发一种基于混合变压器的深度学习（DL）模型，该模型结合多体素S值（MSV）方法用于[镥]镥- DOTATATE治疗中的体素级剂量测定。目标是提高模型性能，以达到与被视为参考标准的蒙特卡罗（MC）模拟紧密一致的准确度水平。我们将分析扩展到包括MIRD形式体系（单S值（SSV）和MSV），从而进行全面的剂量测定研究。
我们使用了一个由22例接受多达4个周期[镥]镥- DOTATATE治疗的患者组成的数据集。MC模拟用于生成参考吸收剂量图。此外，还执行了MIRD形式体系方法，即单S值（SSV）和MSV技术。使用五折交叉验证训练一个UNEt变压器（UNETR）DL架构，以生成基于MC的剂量图。配准后的CT图像作为输入馈入网络，而MC与MSV之间的差异（MC - MSV）被设置为输出。然后将DL结果与MSV整合以恢复MC剂量图。最后，在体素水平和器官水平（危险器官和病变）将由MSV、SSV和DL生成的剂量图与MC参考进行定量比较。
与MSV（体素相对绝对误差（RAE）= 5.54 ± 1.4）相比，DL方法表现略优（体素RAE = 5.28 ± 1.32），且优于SSV（体素RAE = 7.8 ± 3.02）。DL、MSV和SSV方法的伽马分析通过率分别为99.0 ± 1.2%、98.8 ± 1.3%和98.7 ± 1.52%。与MSV、SSV和DL相比，MC的计算时间最长（单床位SPECT研究约需2天），而基于DL的方法在时间效率方面优于其他方法（单床位SPECT为3秒）。器官层面分析显示，在病变吸收剂量方面，SSV、MSV和DL方法的绝对百分比误差分别为1.44 ± 3.05%、1.18 ± 2.65%和1.15 ± 2.5%。
开发了一种基于混合变压器的深度学习模型，用于快速准确地生成剂量图，优于MIRD方法，特别是在异质区域。该模型达到了接近MC金标准的准确度，并且有潜力在大规模数据集上用于临床实施。
