Novel OCT mosaicking pipeline with Feature- and Pixel-based registration
This work addresses a domain-specific problem in ophthalmology for improving image analysis, but it is incremental as it builds on existing mosaicking techniques with hybrid methods.
The paper tackles the problem of stitching multiple overlapping OCT images to create a larger field of view, which is limited by noise and displacement, by proposing a pipeline that combines learning-based feature matching and pixel-based registration, resulting in superior accuracy and computational efficiency on in-house and public datasets.
High-resolution Optical Coherence Tomography (OCT) images are crucial for ophthalmology studies but are limited by their relatively narrow field of view (FoV). Image mosaicking is a technique for aligning multiple overlapping images to obtain a larger FoV. Current mosaicking pipelines often struggle with substantial noise and considerable displacement between the input sub-fields. In this paper, we propose a versatile pipeline for stitching multi-view OCT/OCTA \textit{en face} projection images. Our method combines the strengths of learning-based feature matching and robust pixel-based registration to align multiple images effectively. Furthermore, we advance the application of a trained foundational model, Segment Anything Model (SAM), to validate mosaicking results in an unsupervised manner. The efficacy of our pipeline is validated using an in-house dataset and a large public dataset, where our method shows superior performance in terms of both accuracy and computational efficiency. We also made our evaluation tool for image mosaicking and the corresponding pipeline publicly available at \url{https://github.com/MedICL-VU/OCT-mosaicking}.