Data Support of Generalization Ability of a CNN γ-ray Localization Model for Radiation Imaging

In γ-ray imaging, localization of the γ-ray interaction in the scintillator is critical. Convolutional neural network (CNN) techniques are highly promising for improving γ-ray localization. Our study evaluated the generalization capabilities of a CNN localization model with respect to the γ-ray energy and thickness of the crystal. The model maintained a high positional linearity (PL) and spatial resolution (SR) for ray energies between 59–1460 keV. The PL at the incident surface of the detector was 0.99, and the resolution of the central incident point source ranged between 0.52–1.19 mm. In modified uniform redundant array (MURA) imaging systems using a thick crystal, the CNN γ-ray localization model significantly improved the useful field-of-view (UFOV) from 60.32% to 93.44% compared to the classical centroid localization methods. Additionally, the signal-to-noise ratio (SNR) of the reconstructed images increased from 0.95 to 5.63.

在γ射线成像领域，γ射线与闪烁体相互作用的位置定位至关重要。卷积神经网络（Convolutional Neural Network, CNN）技术在提升γ射线定位性能方面极具应用前景。本研究针对γ射线能量与晶体厚度两个变量，评估了CNN定位模型的泛化能力。该模型在59~1460 keV的射线能量区间内，仍能保持优异的位置线性度（PL）与空间分辨率（SR）。探测器入射面的位置线性度为0.99，中心入射点源的空间分辨率介于0.52~1.19 mm之间。在采用厚晶体的修正型均匀冗余阵列（MURA）成像系统中，相较于经典质心定位方法，该CNN γ射线定位模型可将有效视场（UFOV）从60.32%显著提升至93.44%；此外，重建图像的信噪比（SNR）也从0.95提升至5.63。