The accuracy of additive manufactured medical constructs is limited by errors introduced during image segmentation. The aim of this study was to review the existing literature on different image segmentation methods used in medical additive manufacturing. Thirty-two publications that reported on the accuracy of bone segmentation based on computed tomography images were identified using PubMed, ScienceDirect, Scopus, and Google Scholar. The advantages and disadvantages of the different segmentation methods used in these studies were evaluated and reported accuracies were compared. The spread between the reported accuracies was large (0.04 mm - 1.9 mm). Global thresholding was the most commonly used segmentation method with accuracies under 0.6 mm. The disadvantage of this method is the extensive manual post-processing required. Advanced thresholding methods could improve the accuracy to under 0.38 mm. However, such methods are currently not included in commercial software packages. Statistical shape model methods resulted in accuracies from 0.25 mm to 1.9 mm but are only suitable for anatomical structures with moderate anatomical variations. Thresholding remains the most widely used segmentation method in medical additive manufacturing. To improve the accuracy and reduce the costs of patient-specific additive manufactured constructs, more advanced segmentation methods are required.

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.

Purpose: In order to attain anatomical models, surgical guides and implants for computer‐assisted surgery, accurate segmentation of bony structures in cone‐beam computed tomography (CBCT) scans is required. However, this image segmentation step is often impeded by metal artifacts. Therefore, this study aimed to develop a mixed‐scale dense convolutional neural network (MS‐D network) for bone segmentation in CBCT scans affected by metal artifacts.Method: Training data were acquired from 20 dental CBCT scans affected by metal artifacts. An experienced medical engineer segmented the bony structures in all CBCT scans using global thresholding and manually removed all remaining noise and metal artifacts. The resulting gold standard segmentations were used to train an MS‐D network comprising 100 convolutional layers using far fewer trainable parameters than alternative convolutional neural network (CNN) architectures. The bone segmentation performance of the MS‐D network was evaluated using a leave‐2‐out scheme and compared with a clinical snake evolution algorithm and two state‐of‐the‐art CNN architectures (U‐Net and ResNet). All segmented CBCT scans were subsequently converted into standard tessellation language (STL) models and geometrically compared with the gold standard.Results: CBCT scans segmented using the MS‐D network, U‐Net, ResNet and the snake evolution algorithm demonstrated mean Dice similarity coefficients of 0.87 ± 0.06, 0.87 ± 0.07, 0.86 ± 0.05, and 0.78 ± 0.07, respectively. The STL models acquired using the MS‐D network, U‐Net, ResNet and the snake evolution algorithm demonstrated mean absolute deviations of 0.44 mm ± 0.13 mm, 0.43 mm ± 0.16 mm, 0.40 mm ± 0.12 mm and 0.57 mm ± 0.22 mm, respectively. In contrast to the MS‐D network, the ResNet introduced wave‐like artifacts in the STL models, whereas the U‐Net incorrectly labeled background voxels as bone around the vertebrae in 4 of the 9 CBCT scans containing vertebrae.Conclusion: The MS‐D network was able to accurately segment bony structures in CBCT scans affected by metal artifacts.

The reconstruction of computed tomography (CT) images is an active area of research. Following the rise of deep learning methods, many data-driven models have been proposed in recent years. In this work, we present the results of a data challenge that we organized, bringing together algorithm experts from different institutes to jointly work on quantitative evaluation of several data-driven methods on two large, public datasets during a ten day sprint. We focus on two applications of CT, namely, low-dose CT and sparse-angle CT. This enables us to fairly compare different methods using standardized settings. As a general result, we observe that the deep learning-based methods are able to improve the reconstruction quality metrics in both CT applications while the top performing methods show only minor differences in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). We further discuss a number of other important criteria that should be taken into account when selecting a method, such as the availability of training data, the knowledge of the physical measurement model and the reconstruction speed.