The fetoscopy placenta dataset is associated with our MICCAI2020 publication titled “Deep Placental Vessel Segmentation for Fetoscopic Mosaicking”. The dataset contains 483 frames with ground-truth vessel segmentation annotations taken from six different in vivo fetoscopic procedure videos. The dataset also includes six unannotated in vivo continuous fetoscopic video clips (950 frames) with predicted vessel segmentation maps obtained from the leave-one-out cross-validation of our method.
For ground-truth vessel annotation, we selected the non-occluded (no fetus or tool presence) frames through a separate frame-level fetoscopic event identification approach Bano:IJCARS2020. We annotate a binary mask for vessel segmentation using the Pixel Annotation Tool.