From Perspective X-ray Imaging to Parallax-Robust Orthographic Stitching
This work addresses the challenge of holistic patient anatomy analysis in medical imaging by enabling parallax-free stitching, though it is incremental as it builds on existing stitching methods with domain-specific adaptations.
The paper tackled the problem of stitching medical X-ray images with parallax distortion by using the Fourier slice theorem and a novel deep learning strategy, resulting in orthographic reconstructions that enable metric measurements directly on the 2D image plane.
Stitching images acquired under perspective projective geometry is a relevant topic in computer vision with multiple applications ranging from smartphone panoramas to the construction of digital maps. Image stitching is an equally prominent challenge in medical imaging, where the limited field-of-view captured by single images prohibits holistic analysis of patient anatomy. The barrier that prevents straight-forward mosaicing of 2D images is depth mismatch due to parallax. In this work, we leverage the Fourier slice theorem to aggregate information from multiple transmission images in parallax-free domains using fundamental principles of X-ray image formation. The semantics of the stitched image are restored using a novel deep learning strategy that exploits similarity measures designed around frequency, as well as dense and sparse spatial image content. Our pipeline, not only stitches images, but also provides orthographic reconstruction that enables metric measurements of clinically relevant quantities directly on the 2D image plane.