“…However these algorithms do not perform as well with FA sequences because they are designed to deal with changes of content appearance (e.g., due to different sensors imaging the same organs) but not with content changes, which occur throughout a FA sequence as different portions or the vascular structure are visible (perfused) in different frames, see Figure 1. A few registration algorithms for FA sequence have been reported, both estimating a single, global transformation, [6], [7] and performing deformable registration [8], [9]. All of them have been applied to sequences with fields of view typical of standard fundus cameras (around 45 degrees), which do not contain many of the challenges of UWFV FA: ciliar occlusions, peripheral blurring, irregular time intervals between frame acquisitions, fewer vessels in periphery to mention some.…”