Abstract
Unlike previous works, this open data collection consists of X-ray cone-beam (CB) computed tomography (CT) datasets specifically designed for machine learning applications and high cone-angle artefact reduction. Forty-two walnuts were scanned with a laboratory X-ray set-up to provide not only data from a single object but from a class of objects with natural variability. For each walnut, CB projections on three different source orbits were acquired to provide CB data with different cone angles as well as being able to compute artefact-free, high-quality ground truth images from the combined data that can be used for supervised learning. We provide the complete image reconstruction pipeline: raw projection data, a description of the scanning geometry, pre-processing and reconstruction scripts using open software, and the reconstructed volumes. Due to this, the dataset can not only be used for high cone-angle artefact reduction but also for algorithm development and evaluation for other tasks, such as image reconstruction from limited or sparse-angle (low-dose) scanning, super resolution, or segmentation.
Highlights
Background & Summary Scientific contextX-ray computed tomography (CT) is a widely used projection-based imaging modality with a broad range of clinical, scientific and industrial applications
There is often a clear division between computational imaging groups with a background in mathematics and computer science, which focus on enhancing CT methodology on one side and experimental imaging groups using CT as a tool to conduct their scientific studies on the other
The latter typically uses commercial CT solutions coming with proprietary software which does not give full access to the raw projection data or the details of the experimental acquisition
Summary
Background & Summary Scientific contextX-ray computed tomography (CT) is a widely used projection-based imaging modality with a broad range of clinical, scientific and industrial applications. There is often a clear division between computational imaging groups with a background in mathematics and computer science, which focus on enhancing CT methodology on one side and experimental imaging groups using CT as a tool to conduct their scientific studies on the other. The latter typically uses commercial CT solutions coming with proprietary software which does not give full access to the raw projection data or the details of the experimental acquisition. This lack of suitable experimental data is a significant hurdle for the translation of innovative research into applications
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
