From the Department of Biomedical Systems Informatics, Yonsei University, Seoul.
Department of Nuclear Medicine and Molecular Imaging, Ajou University School of Medicine, Suwon, South Korea.
Clin Nucl Med. 2024 May 1;49(5):397-403. doi: 10.1097/RLU.0000000000005129. Epub 2024 Feb 26.
We aimed to develop deep learning (DL)-based attenuation correction models for Tl-201 myocardial perfusion SPECT (MPS) images and evaluate their clinical feasibility.
We conducted a retrospective study of patients with suspected or known coronary artery disease. We proposed a DL-based image-to-image translation technique to transform non-attenuation-corrected images into CT-based attenuation-corrected (CT AC ) images. The model was trained using a modified U-Net with structural similarity index (SSIM) loss and mean squared error (MSE) loss and compared with other models. Segment-wise analysis using a polar map and visual assessment for the generated attenuation-corrected (GEN AC ) images were also performed to evaluate clinical feasibility.
This study comprised 657 men and 328 women (age, 65 ± 11 years). Among the various models, the modified U-Net achieved the highest performance with an average mean absolute error of 0.003, an SSIM of 0.990, and a peak signal-to-noise ratio of 33.658. The performance of the model was not different between the stress and rest datasets. In the segment-wise analysis, the myocardial perfusion of the inferior wall was significantly higher in GEN AC images than in the non-attenuation-corrected images in both the rest and stress test sets ( P < 0.05). In the visual assessment of patients with diaphragmatic attenuation, scores of 4 (similar to CT AC images) or 5 (indistinguishable from CT AC images) were assigned to most GEN AC images (65/68).
Our clinically feasible DL-based attenuation correction models can replace the CT-based method in Tl-201 MPS, and it would be useful in case SPECT/CT is unavailable for MPS.
我们旨在开发基于深度学习（DL）的 Tl-201 心肌灌注 SPECT（MPS）图像衰减校正模型，并评估其临床可行性。
我们对疑似或已知冠心病患者进行了回顾性研究。我们提出了一种基于 DL 的图像到图像转换技术，将未经衰减校正的图像转换为基于 CT 的衰减校正（CT AC）图像。该模型使用经过修改的 U-Net 进行训练，采用结构相似性指数（SSIM）损失和均方误差（MSE）损失，并与其他模型进行比较。还使用极地图进行分段分析，并对生成的衰减校正（GEN AC）图像进行视觉评估，以评估临床可行性。
本研究包括 657 名男性和 328 名女性（年龄 65±11 岁）。在各种模型中，经过修改的 U-Net 表现最佳，平均平均绝对误差为 0.003，SSIM 为 0.990，峰值信噪比为 33.658。该模型在应激和休息数据集之间的性能没有差异。在分段分析中，在休息和应激测试集中，GEN AC 图像的下壁心肌灌注明显高于未经衰减校正的图像（P<0.05）。在对膈肌衰减患者的视觉评估中，大多数 GEN AC 图像的评分（4 分或 5 分）与 CT AC 图像相似（65/68）。
我们开发的基于临床可行的 DL 的衰减校正模型可以替代 Tl-201 MPS 中的 CT 基方法，并且在 SPECT/CT 无法用于 MPS 的情况下将非常有用。
