Deep-Learning-based Fast and Accurate 3D CT Deformable Image Registration in Lung Cancer. (arXiv:2304.11135v1 [cs.CV])

Purpose: In some proton therapy facilities, patient alignment relies on two
2D orthogonal kV images, taken at fixed, oblique angles, as no 3D on-the-bed
imaging is available. The visibility of the tumor in kV images is limited since
the patient's 3D anatomy is projected onto a 2D plane, especially when the
tumor is behind high-density structures such as bones. This can lead to large
patient setup errors. A solution is to reconstruct the 3D CT image from the kV
images …

alignment arxiv cancer errors image images imaging lung cancer patient proton registration setup solution therapy treatment visibility