Obata Yoshihiro, Parkinson Dilworth Y, Pelt Daniël M, Acevedo Claire
Department of Mechanical and Aerospace Engineering, University of California San Diego, San Diego, CA 92161, USA.
Advanced Light Source, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA.
J Synchrotron Radiat. 2025 May 1;32(Pt 3):690-699. doi: 10.1107/S1600577525001833. Epub 2025 Apr 1.
In bone-imaging research, in situ synchrotron radiation micro-computed tomography (SRµCT) mechanical tests are used to investigate the mechanical properties of bone in relation to its microstructure. Low-dose computed tomography (CT) is used to preserve bone's mechanical properties from radiation damage, though it increases noise. To reduce this noise, the self-supervised deep learning method Noise2Inverse was used on low-dose SRµCT images where segmentation using traditional thresholding techniques was not possible. Simulated-dose datasets were created by sampling projection data at full, one-half, one-third, one-fourth and one-sixth frequencies of an in situ SRµCT mechanical test. After convolutional neural networks were trained, Noise2Inverse performance on all dose simulations was assessed visually and by analyzing bone microstructural features. Visually, high image quality was recovered for each simulated dose. Lacunae volume, lacunae aspect ratio and mineralization distributions shifted slightly in full, one-half and one-third dose network results, but were distorted in one-fourth and one-sixth dose network results. Following this, new models were trained using a larger dataset to determine differences between full dose and one-third dose simulations. Significant changes were found for all parameters of bone microstructure, indicating that a separate validation scan may be necessary to apply this technique for microstructure quantification. Noise present during data acquisition from the testing setup was determined to be the primary source of concern for Noise2Inverse viability. While these limitations exist, incorporating dose calculations and optimal imaging parameters enables self-supervised deep learning methods such as Noise2Inverse to be integrated into existing experiments to decrease radiation dose.
在骨成像研究中，原位同步辐射微计算机断层扫描（SRµCT）力学测试用于研究骨的力学性能与其微观结构的关系。低剂量计算机断层扫描（CT）用于保护骨的力学性能免受辐射损伤，尽管这会增加噪声。为了降低这种噪声，在无法使用传统阈值技术进行分割的低剂量SRµCT图像上使用了自监督深度学习方法Noise2Inverse。通过对原位SRµCT力学测试的全频率、二分之一频率、三分之一频率、四分之一频率和六分之一频率的投影数据进行采样，创建了模拟剂量数据集。在训练卷积神经网络后，通过视觉评估和分析骨微观结构特征来评估Noise2Inverse在所有剂量模拟上的性能。从视觉上看，每个模拟剂量都恢复了高图像质量。在全剂量、二分之一剂量和三分之一剂量网络结果中，腔隙体积、腔隙纵横比和矿化分布略有变化，但在四分之一剂量和六分之一剂量网络结果中则出现了扭曲。在此之后，使用更大的数据集训练新模型，以确定全剂量和三分之一剂量模拟之间的差异。发现骨微观结构的所有参数都有显著变化，这表明可能需要单独的验证扫描才能将该技术应用于微观结构量化。测试装置在数据采集过程中存在的噪声被确定为Noise2Inverse可行性的主要关注点。虽然存在这些限制，但结合剂量计算和最佳成像参数可以使Noise2Inverse等自监督深度学习方法集成到现有实验中，以降低辐射剂量。
