基于深度学习的无CT定量单光子发射计算机断层扫描用于自动评估甲状腺摄取百分比
CT-free quantitative SPECT for automatic evaluation of %thyroid uptake based on deep-learning.
作者信息
Kwon Kyounghyoun, Hwang Donghwi, Oh Dongkyu, Kim Ji Hye, Yoo Jihyung, Lee Jae Sung, Lee Won Woo
机构信息
Department of Health Science and Technology, The Graduate School of Convergence Science and Technology, Seoul National University, Suwon, Republic of Korea.
Department of Nuclear Medicine, Seoul National University Bundang Hospital, 82, Gumi-ro 173 Beon-gil, Bundang-gu, Seongnam, Gyeonggi-do, 13620, Republic of Korea.
出版信息
EJNMMI Phys. 2023 Mar 22;10(1):20. doi: 10.1186/s40658-023-00536-9.
PURPOSE
Quantitative thyroid single-photon emission computed tomography/computed tomography (SPECT/CT) requires computed tomography (CT)-based attenuation correction and manual thyroid segmentation on CT for %thyroid uptake measurements. Here, we aimed to develop a deep-learning-based CT-free quantitative thyroid SPECT that can generate an attenuation map (μ-map) and automatically segment the thyroid.
METHODS
Quantitative thyroid SPECT/CT data (n = 650) were retrospectively analyzed. Typical 3D U-Nets were used for the μ-map generation and automatic thyroid segmentation. Primary emission and scattering SPECTs were inputted to generate a μ-map, and the original μ-map from CT was labeled (268 and 30 for training and validation, respectively). The generated μ-map and primary emission SPECT were inputted for the automatic thyroid segmentation, and the manual thyroid segmentation was labeled (280 and 36 for training and validation, respectively). Other thyroid SPECT/CT (n = 36) and salivary SPECT/CT (n = 29) were employed for verification.
RESULTS
The synthetic μ-map demonstrated a strong correlation (R = 0.972) and minimum error (mean square error = 0.936 × 10, %normalized mean absolute error = 0.999%) of attenuation coefficients when compared to the ground truth (n = 30). Compared to manual segmentation, the automatic thyroid segmentation was excellent with a Dice similarity coefficient of 0.767, minimal thyroid volume difference of - 0.72 mL, and a short 95% Hausdorff distance of 9.416 mm (n = 36). Additionally, %thyroid uptake by synthetic μ-map and automatic thyroid segmentation (CT-free SPECT) was similar to that by the original μ-map and manual thyroid segmentation (SPECT/CT) (3.772 ± 5.735% vs. 3.682 ± 5.516%, p = 0.1090) (n = 36). Furthermore, the synthetic μ-map generation and automatic thyroid segmentation were successfully performed in the salivary SPECT/CT using the deep-learning algorithms trained by thyroid SPECT/CT (n = 29).
CONCLUSION
CT-free quantitative SPECT for automatic evaluation of %thyroid uptake can be realized by deep-learning.
目的
定量甲状腺单光子发射计算机断层扫描/计算机断层扫描（SPECT/CT）需要基于计算机断层扫描（CT）的衰减校正以及在CT上进行手动甲状腺分割以测量甲状腺摄取百分比。在此，我们旨在开发一种基于深度学习的无CT定量甲状腺SPECT，其能够生成衰减图（μ图）并自动分割甲状腺。
方法
对定量甲状腺SPECT/CT数据（n = 650）进行回顾性分析。典型的3D U-Net用于生成μ图和自动甲状腺分割。输入主要发射和散射SPECT以生成μ图，并且将来自CT的原始μ图进行标注（分别有268个和30个用于训练和验证）。将生成的μ图和主要发射SPECT输入以进行自动甲状腺分割，并且将手动甲状腺分割进行标注（分别有280个和36个用于训练和验证）。使用其他甲状腺SPECT/CT（n = 36）和唾液SPECT/CT（n = 29）进行验证。
结果
与真实值（n = 30）相比，合成的μ图在衰减系数方面显示出强相关性（R = 0.972）和最小误差（均方误差 = 0.936×10，归一化平均绝对误差百分比 = 0.999%）。与手动分割相比，自动甲状腺分割效果优异，骰子相似系数为0.767，甲状腺体积最小差异为 -0.72 mL，短95%豪斯多夫距离为9.416 mm（n = 36）。此外，通过合成μ图和自动甲状腺分割（无CT SPECT）得到的甲状腺摄取百分比与通过原始μ图和手动甲状腺分割（SPECT/CT）得到的相似（3.772±5.735% 对 3.682±5.516%，p = 0.1090）（n = 36）。此外，使用由甲状腺SPECT/CT训练的深度学习算法，在唾液SPECT/CT中成功进行了合成μ图生成和自动甲状腺分割（n = 29）。
结论
通过深度学习可实现用于自动评估甲状腺摄取百分比的无CT定量SPECT。
Zotero 插件