<b>FetReg: Largescale Multi-centre Fetoscopy Placenta Dataset</b>

<p dir="ltr"><b>First publicly available largescale multi-centre dataset of in vivo fetoscopic videos with placental scene semantic annotations from the FetReg2021 – Endoscopic Vision challenge organised at MICCAI2021. </b></p><h3><b>Overview</b></h3><p dir="ltr">Fetoscopic Placental Vessel Segmentation and Registration (<a href="https://www.synapse.org/#!Synapse:syn25313156/wiki/609152" target="_blank">FetReg2021</a>) challenge was organized as part of the MICCAI2021 Endoscopic Vision (<a href="https://www.endovis.org" rel="noreferrer" target="_blank">EndoVis</a>) challenge. Through FetReg2021 challenge, we released the first large-scale multi-centre dataset of fetoscopy laser photocoagulation procedure. The dataset contains 2,718 pixel-wise annotated images (for background, vessel, fetus, tool classes) from 24 different in vivo TTTS fetoscopic surgeries and 24 unannotated video clips video clips containing 9,616 frames for training and testing. The dataset is useful for the development of generalized and robust semantic segmentation and video mosaicking algorithms for long duration fetoscopy videos.</p><p dir="ltr">Further details about this dataset are provided in our dataset description [<a href="https://arxiv.org/abs/2106.05923" target="_blank">Bano:arXiv2021</a>]and challenge analysis [<a href="https://www.sciencedirect.com/science/article/pii/S1361841523003262" rel="noreferrer" target="_blank">Bano:MedIA2024</a>] publications. Please visit the <a href="https://www.synapse.org/#!Synapse:syn25313156/wiki/609152" target="_blank">FetReg2021 challenge website</a> for more information about the challenge.</p><p dir="ltr">FetReg2021 challenge was featured as the <a href="https://www.rsipvision.com/ComputerVisionNews-2021June/22/" target="_blank">Challenge of the Month</a> in the <a href="https://www.rsipvision.com/computer-vision-news/" target="_blank">Computer Vision News</a> June 2021 issue.</p><h3><b>Citing the Dataset</b></h3><p dir="ltr">Cite [<a href="https://www.sciencedirect.com/science/article/pii/S1361841523003262" rel="noreferrer" target="_blank">Bano:MedIA2024</a>] and [<a href="https://arxiv.org/abs/2106.05923" target="_blank">Bano:arXiv2021</a>] whenever research making use of this dataset is reported in any academic publication or research report.</p>