ACRF Image X Institute, Faculty of Medicine and Health, The University of Sydney, Sydney, Australia.
School of Physics, The University of Sydney, Sydney, Australia.
Med Phys. 2022 Aug;49(8):5258-5267. doi: 10.1002/mp.15688. Epub 2022 May 15.
Radiotherapy treatment planning incorporating ventilation imaging can reduce the incidence of radiation-induced lung injury. The gold-standard of ventilation imaging, using nuclear medicine, has limitations with respect to availability and cost.
An alternative type of ventilation imaging to nuclear medicine uses 4DCT (or breath-hold CT [BHCT] pair) with deformable image registration (DIR) and a ventilation metric to produce a CT ventilation image (CTVI). The purpose of this study is to investigate the application of machine learning as an alternative to DIR-based methods when producing CTVIs.
A patient dataset of 15 inhale and exhale BHCTs and Galligas PET ventilation images were used to train and test a 2D U-Net style convolutional neural network. The neural network established relationships between axial input BHCT image pairs and axial labeled Galligas PET images and was evaluated using eightfold cross-validation. Once trained, the neural network could produce a CTVI from an input BHCT image pair. The CTVIs produced by the neural network were qualitatively assessed visually and quantitatively compared to a Galligas PET ventilation image using a Spearman correlation and Dice similarity coefficient (DSC). The DSC measured the spatial overlap between three segmented equal lung volumes by ventilation (high, medium, and low functioning lung [LFL]).
The mean Spearman correlation between the CTVIs and the Galligas PET ventilation images was 0.58 ± 0.14. The mean DSC over high, medium, and LFL between the CTVIs and Galligas PET ventilation images was 0.55 ± 0.06. Visually, a systematic overprediction of ventilation within the lung was observed in the CTVIs with respect to the Galligas PET ventilation images, with jagged regions of ventilation in the sagittal and coronal planes.
A convolutional neural network was developed that could produce a CTVI from a BHCT image pair, which was then compared with a Galligas PET ventilation image. The performance of this machine learning method was comparable to previous benchmark studies investigating a DIR-based CTVI, warranting future development, and investigation of applying machine learning to a CTVI.
纳入通气成像的放射治疗计划可降低放射性肺损伤的发生率。核医学通气成像的金标准在可用性和成本方面存在局限性。
一种替代核医学的通气成像方法是使用 4DCT（或屏气 CT [BHCT] 对）与变形图像配准（DIR）和通气度量来生成 CT 通气图像（CTVI）。本研究的目的是研究在生成 CTVI 时使用机器学习替代 DIR 方法的应用。
使用 15 例吸气和呼气 BHCT 以及 Galligas PET 通气图像的患者数据集来训练和测试二维 U-Net 风格的卷积神经网络。该神经网络建立了轴向输入 BHCT 图像对与轴向标记 Galligas PET 图像之间的关系，并使用 8 折交叉验证进行评估。训练完成后，神经网络可以从输入的 BHCT 图像对生成 CTVI。通过视觉定性评估和使用 Spearman 相关系数和 Dice 相似系数（DSC）与 Galligas PET 通气图像进行定量比较来评估生成的 CTVI。DSC 测量了三个按通气（高、中、低功能肺[LFL]）分段的等体积肺之间的空间重叠。
CTVI 与 Galligas PET 通气图像之间的平均 Spearman 相关系数为 0.58±0.14。CTVI 与 Galligas PET 通气图像之间的高、中、LFL 之间的平均 DSC 为 0.55±0.06。从视觉上看，与 Galligas PET 通气图像相比，CTVI 中观察到肺部通气的系统过度预测，矢状面和冠状面存在通气的锯齿状区域。
开发了一种可以从 BHCT 图像对生成 CTVI 的卷积神经网络，然后将其与 Galligas PET 通气图像进行比较。该机器学习方法的性能与之前研究 DIR 为基础的 CTVI 的基准研究相当，值得进一步开发和研究将机器学习应用于 CTVI。
