Subject	Information
Specific subject area	Computer Vision and Pattern Recognition
Type of data	Image
How data were acquired	The two datasets were adapted from a public head CT collection CQ500 with CC BY-NC-SA 4.0 license
Data format	Raw
Parameters for data collection	The selection of DICOM files from the CQ500 head CT collection was based on the image quality (e.g., slice thickness, fracture, scanning protocol)
Description of data collection	The datasets were adapted from the CQ500 CT data. The adaptation process involves pre-processing (data format conversion, selection, transformation, skull segmentation, post-processing (e.g., noise removal) artificial defect injection).
Data source location	The dataset was adapted from the public head CT collection CQ500 with CC BY-NC-SA 4.0 license. The SkullFix dataset was first released to participants of the AutoImplant (https://autoimplant.grand-challenge.org/) challenge.
Data accessibility	The SkullFix dataset can be downloaded from the AutoImplant challenge website at https://autoimplant.grand-challenge.org/. Besides, we also provided the direct download links for the two datasets: SkullBreak (https://www.fit.vutbr.cz/~ikodym/skullbreak_training.zip and https://www.fit.vutbr.cz/~ikodym/skullbreak_evaluation.zip). SkullFix (https://files.icg.tugraz.at/f/2c5f458e781a42c6a916/?dl=1).
Related research articles	Jianning Li, Antonio Pepe, Christina Gsaxner, Gord von Campe, and Jan Egger. title: A baseline approach for autoimplant: the miccai 2020 cranial implant design challenge, MICCAI CLIP 2020. DOI: https://doi.org/10.1007/978-3-030-60946-7_8. reference: [1]
	Oldřich Kodym, Michal Španěl, and Adam Herout. title: Skull shape reconstruction using cascaded convolutional networks. DOI: https://doi.org/10.1016/j.compbiomed.2020.103886. reference: [2]