Dataset Information

A cone-beam X-ray computed tomography data collection designed for machine learning.

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.

SUBMITTER: Der Sarkissian H

PROVIDER: S-EPMC6805882 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A cone-beam X-ray computed tomography data collection designed for machine learning.

Der Sarkissian Henri H Lucka Felix F van Eijnatten Maureen M Colacicco Giulia G Coban Sophia Bethany SB Batenburg Kees Joost KJ

Scientific data 20191022 1

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 a ...[more]

PMID: 31641152

Similar Datasets

Project description:BackgroundMotion-compensated (MoCo) reconstruction shows great promise in improving four-dimensional cone-beam computed tomography (4D-CBCT) image quality. MoCo reconstruction for a 4D-CBCT could be more accurate using motion information at the CBCT imaging time than that obtained from previous 4D-CT scans. However, such data-driven approaches are hampered by the quality of initial 4D-CBCT images used for motion modeling.PurposeThis study aims to develop a deep-learning method to generate high-quality motion models for MoCo reconstruction to improve the quality of final 4D-CBCT images.MethodsA 3D artifact-reduction convolutional neural network (CNN) was proposed to improve conventional phase-correlated Feldkamp-Davis-Kress (PCF) reconstructions by reducing undersampling-induced streaking artifacts while maintaining motion information. The CNN-generated artifact-mitigated 4D-CBCT images (CNN enhanced) were then used to build a motion model which was used by MoCo reconstruction (CNN+MoCo). The proposed procedure was evaluated using in-vivo patient datasets, an extended cardiac-torso (XCAT) phantom, and the public SPARE challenge datasets. The quality of reconstructed images for XCAT phantom and SPARE datasets was quantitatively assessed using root-mean-square-error (RMSE) and normalized cross-correlation (NCC).ResultsThe trained CNN effectively reduced the streaking artifacts of PCF CBCT images for all datasets. More detailed structures can be recovered using the proposed CNN+MoCo reconstruction procedure. XCAT phantom experiments showed that the accuracy of estimated motion model using CNN enhanced images was greatly improved over PCF. CNN+MoCo showed lower RMSE and higher NCC compared to PCF, CNN enhanced and conventional MoCo. For the SPARE datasets, the average (± standard deviation) RMSE in mm-1 for body region of PCF, CNN enhanced, conventional MoCo and CNN+MoCo were 0.0040 ± 0.0009, 0.0029 ± 0.0002, 0.0024 ± 0.0003 and 0.0021 ± 0.0003. Corresponding NCC were 0.84 ± 0.05, 0.91 ± 0.05, 0.91 ± 0.05 and 0.93 ± 0.04.ConclusionsCNN-based artifact reduction can substantially reduce the artifacts in the initial 4D-CBCT images. The improved images could be used to enhance the motion modeling and ultimately improve the quality of the final 4D-CBCT images reconstructed using MoCo.

Project description:PurposeAnastomosis between posterior superior alveolar artery and infraorbital artery can go through bony canal in the lateral wall of the maxilla. This artery is called alveolar antral artery. It can complicate lateral sinus lift procedure by bleeding and hemosinus formation or bone graft wash out. The artery can also go in soft tissues where is not visible on cone beam computed tomography. In previous studies, the relation of this artery to sinus floor or alveolar process was measured. These structures are highly unstable during lifetime and after tooth loss. The aim of this study is to study presence and relations of bony canal in the lateral maxillary wall, to characterize the group of patients which is more likely to have bone canal in the lateral maxilla. The aim and the novelty of this study is the describing of the relationship of the bony canal to the more stable structure of hard palate and describing the relation of presence of bony canal on width of maxillary sinus, and to facilitate the prediction of presence of the alveolar antral artery.MaterialsThe cone beam computed tomography scans of the patients (251 in number) of the university hospital were examined for presence of alveolar antral artery (148 was fulfilled inclusion criteria), patient were characterized by gender, age, and sinus type (wide, average, narrow). The diameter of the bony canal and its relation to the level of sinus floor and hard palate were measured.ResultsThe cone beam computed tomography scans of 148 patients, out of it 55 man (37,2%) and 93 women (62,8%). Bony canal containing alveolar anastomosis was found in 69 cases (57,0%). Presence of the bony canal in the lateral wall of maxillae showed statistical probability depending on age with p = 0, 064 according to Mann-Whitney test. The older patients have more likely the bony canal. The presence of the alveolar antral artery was found more likely in the wide sinuses. The hard palate level can serve as a prediction point of alveolar antral artery only in first molar and second premolar region. In accordance with previous studies the width of bony canal is significantly higher in group of man (p = 0, 015). There was found a correlation between smaller distance of bony canal from sinus floor in the presence of teeth (p = 0, 067). After tooth loss the distance between sinus floor and bony canal increases, but the distance of bony canal to hard palate level stays constant. This can be explained hypothetically so that periodontal ligaments and root surface acts as a barrier for sinus pneumatization.ConclusionLateral sinus lifting in some cases can be unenviable, the knowledge about alveolar antral artery anatomy can reduce the risk of arterial bleeding. The cone-beam computed tomography is a routine examination prior to augmentation surgery and therefore the data obtained from it has an impact on clinical practice.

Dataset Information

A cone-beam X-ray computed tomography data collection designed for machine learning.

Publications

A cone-beam X-ray computed tomography data collection designed for machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets