Virtual Reconstruction Research Articles

Radiomics Feature Stability in True and Virtual Non-Contrast Reconstructions from Cardiac Photon-Counting Detector CT Datasets

Radiomics Feature Stability in True and Virtual Non-Contrast Reconstructions from Cardiac Photon-Counting Detector CT Datasets

Underwater virtual exploration of the ancient port of Amathus

Underwater cultural heritage sites, spanning from submerged settlements to ancient ports and shipwrecks, captivate researchers and the public, providing insight into civilizations along coastlines and riverbanks. However, their accessibility and exploration are hindered by the sea’s physical barrier. Virtual Reality (VR) offers a transformative solution by providing digital accessibility to these underwater artifacts, enabling immersive exploration without physical limitations. VR enables people to embark on virtual tours of these sites, fostering a deeper appreciation of maritime archaeology and cultural heritage. Yet, fully realizing VR’s potential in underwater environments poses challenges, such as realistic virtual reconstruction and accurate simulation of marine life and coral reefs. Photogrammetry emerges as an effective technique for creating detailed 3D models, although underwater conditions often hinder quality outcomes. To address these challenges, our work focuses on digital underwater cultural heritage, presenting a gamified VR exploration of the ancient harbor of Amathus in Cyprus. Through photogrammetry, our VR environment enables users to explore and interact with the historic site seamlessly. Integrated guided tours, procedural generation, and machine learning algorithms enhance realism and user engagement. Evaluation through user studies demonstrates high-quality VR experiences with minimal discomfort, highlighting the efficacy and potential impact of our approach in enhancing underwater exploration and conservation efforts.

Histological assessment of the shared vascular wall in anomalous aortic origin of coronary arteries with an interarterial course

Abstract Background In anomalous aortic origin of a coronary artery (AAOCA) an intramural segment is present if the proximal AAOCA courses through the aortic wall. This is defined as a shared tunica media of the aorta and AAOCA in the ‘intramural septum’. This definition is based on autopsy studies of selected AAOCA patients who suffered sudden cardiac death and is difficult to apprehend on imaging modalities. Therefore, the aim was to identify the histological features and variants of the interarterial vascular wall in living adult patients, and correlate this to CT-angiography (CTA). Methods This prospective multicenter study included consecutive adult AAOCA patients who underwent surgical unroofing between 2021 to 2024. The excised interatrial vascular wall tissue was embedded, sectioned, and immunohistochemically stained for physiological components, e.g. smooth muscle cells and connective tissue, and pathological components such as fibrosis. Microscopic examination and quantification was performed by two independent observers and findings were correlated with CTA. Results Fifteen patients (mean age 42.9±14.0 years, 60% female) and 1 postmortem specimen were included. Fourteen (93%) had a right-AAOCA and 1 (7%) a left-AAOCA, with a mean intramural length of 8.4±4.1mm. Histopathologically, disorganized elastic lamellae with fragmentation, presence of fibrosis and loss of nuclei were observed. No vasa vasorum or nervi vasorum were identified. Post-sectioning virtual 3D reconstructions enhanced the spatial insight in correlation of histological sections with CTA. Conclusion This first study of the intramural septum in adults with AAOCA reveals the histological structure of the shared vascular wall between the aorta and AAOCA. Marked vascular wall abnormalities such as lack of vasa and nervi vasorum, fragmentation of elastic lamellae and fibrotic changes were observed. These findings support a propensity to local vascular wall pathology in patients with AAOCA. 3D reconstruction supported the translation of histological data to clinical imaging techniques.Central Figure

Validation of quantitative aortic valve calcification assessment by photon-counting computed tomography from contrast-enhanced data sets using virtual non-contrast reconstructions

Abstract Background The spectral information of photon-counting computed tomography (PCCT) permits the reconstruction of energy-selective images. Purpose We evaluated two methods for the reconstruction of virtual non-contrast-enhanced images from contrast-enhanced CT angiographic data sets regarding their ability to quantify aortic valve calcification. Results were validated by comparison to non-enhanced computed tomography. Methods A total of 100 subjects with severe aortic valve stenosis who underwent ECG-synchronized cardiac photon-counting CT for diagnostic workup prior to transcatheter aortic valve implantation (TAVI) were included in the current analysis. A standard true non-contrast acquisition was performed for aortic valve calcium quantification in each subject. In addition, two virtual non-enhanced data sets were reconstructed from contrast-enhanced CT angiographic data: a calcium-specific image ("pure calcium scan", PCS) and a virtual non-contrast (VNC) scan by subtraction of iodine. The PCS algorithm separates calcium and iodine in spectral PCCT images, creating a non-calcium mask for denoised spectral input and preserving calcium contrast in final material decomposition. Iodine extraction is achieved by measurement of the iodine content and its differentiation from native soft tissue attenuation. The Agatston Score was assessed in each of the three image data sets using semi-automated software. Results The mean age of the subjects was 78 ± 7 years, 66% were male. Mean EUROSCORE II was 4 ± 4%, mean STS Score for morbidity and mortality was 16 ± 11%. In the true non-contrast scan used for validation, the mean Agatston Score was 3028 ± 1820. The mean Agatston Score obtained from the PCS data set was 3004 ± 2042 and did not differ significantly from true non—contrast image sets (p=0.716). In the VNC data sets, the mean Agatston score was 1726 ± 1288, significantly lower than in the true non-contrast and the PCS data sets (both <0.001). Both, PCS and VNC data showed a significant correlation with true non-contrast scans (correlation coefficient PCS: 0.978, VNC scan: 0.975, both p<0.001). Conclusion In conclusion, the current results show the possibility to reliably quantify the Agatston Score of larger cardiac calcifications in virtual non-contrast data sets – however, there is substantial influence of the algorithm that is used so that validation of new techniques is of key importance.

Ultra-High-Resolution Photon-Counting Detector CT Benefits Visualization of Abdominal Arteries: A Comparison to Standard-Reconstruction.

This study aimedto investigate the potential benefit of ultra-high-resolution (UHR) photon-counting detector CT (PCD-CT) angiography in visualization of abdominal arteries in comparison to standard-reconstruction (SR) images of virtual monoenergetic images (VMI) at low kiloelectron volt (keV).We prospectively included 47 and 47 participants to undergo contrast-enhanced abdominal CT scans within UHR mode on a PCD-CT systemusing full-dose (FD) and low-dose (LD) protocols, respectively. The data were reconstructed into six series of images: FD_UHR_Br48, FD_UHR_Bv56, FD_UHR_Bv60, FD_SR_Bv40, LD_UHR_Bv48, and LD_SR_Bv40. The UHR reconstructions were performed with three kernels (Bv48, Bv56, and Bv60) within 0.2mm. The SR were virtual monoenergetic imaging reconstruction with Bv40 kernel at 40-keV within 1mm. Each series of axial images were reconstructed into coronal and volume-rendered images. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of seven arteries were measured. Three radiologists assessed the image quality, and visibility of nine arteries on all the images.SNR and CNR values of SR images were significantly higher than those of UHR images (P < 0.001). The SR images have higher ratings in image noise (P < 0.001), but the FD_UHR_Bv56 and FD_UHR_Bv60 images has higher rating in vessel sharpness (P < 0.001). The overall quality was not significantly different among FD_VMI_40keV, LD_VMI_40keV, FD_UHR_Bv48, and LD_UHR_Bv48 images (P > 0.05) but higher than those of FD_UHR_Bv56 and FD_UHR_Bv60 images (P < 0.001). There is no significant difference of nine abdominal arteries among six series of images of axial, coronal and volume-rendered images (P > 0.05).To conclude, 1-mm SR image of VMI at 40-keV is superior to 0.2-mm UHR regardless of which kernel is used to visualize abdominal arteries, while 0.2-mm UHR image using a relatively smooth kernel may allow similar image quality and artery visibility when thinner slice image is warranted.

The Megaliths of Mols Peninsula – a Case Study of Applied Digital Photogrammetry in a Survey of Neolithic Monuments in Denmark

Abstract This study presents a practical case analysis detailing the outcomes of a survey project conducted on Neolithic megalithic structures on the Mols Peninsula in East Jutland, Denmark. The survey methodology employed digital photogrammetry, utilizing consumer-grade drones and handheld digital cameras. This approach facilitated the merging of aerial perspectives of the local surroundings with terrestrial photographs specifically focusing on the densely clustered stone chambers. Subsequently, the gathered data underwent conversion into various forms, such as orthophotos, surface elevation models, 3D representations, hill shades, point clouds, and textured low-resolution models optimized for online visualization. Among the noteworthy findings, the study included an evaluation of 19th-century drawings, revealing their remarkable precision. However, it was also noted that one of the monuments underwent substantial alterations in 1943. Moreover, the study successfully generated 3D models of the capstones from two dolmens, allowing for their virtual reconstruction. Importantly, the research introduced an innovative technique for mapping burned flints on the field surface surrounding the dolmens by employing low-altitude vertical drone photography – a previously unexplored method.

Poliface: A Multi-pose Synchronous Imaging System

To enhance the accuracy of face recognition technology in real-world scenarios, it is necessary to train deep learning models on datasets that contain a large number of labeled human face images under multiple poses, lighting, and accessory variations. In this paper, we introduce a novel acquisition system named the Poliface. This system can capture multiple high-resolution images simultaneously around the human head. We designed this system with a well-built aluminum structure, control electronic circuits, and high-performing in-house software. The results demonstrate the precise operation and exceptional stability of this system. Using this Poliface system, we have collected over 6 million photos, which can be used to train and evaluate facial recognition models, and exploited for three-dimensional (3D) virtual face reconstruction.

A virtual scene reconstruction algorithm for 3D digital images based on machine learning

In order to obtain a better quality image of virtual scene reconstruction of three-dimensional digital image, a virtual scene reconstruction algorithm of three-dimensional digital image based on machine learning is proposed. Firstly, the state information and presentation instructions of the scene are analyzed to obtain the distribution position of the vertices of the mesh model of the image reconstruction. The global image is approximately calculated by the local coordinate method, and the local details are corrected to complete the rendering of the three-dimensional digital image. Then, the space and scale are used as feature points to build a window detection template on the image, and the classifier is applied to suppress discrete feature points and remove redundant features. Finally, the smoothed three-dimensional coordinates are obtained according to the fitting function method to reconstruct the three-dimensional surface, and the local two-dimensional triangle is segmented and mapped to the three-dimensional space to realize the reconstruction of the virtual scene of the three-dimensional digital image. The experimental results show that the algorithm has a fast convergence speed, the reconstructed image details and edge contours are complete, and the overall effect is good.

Auditory time travel: Acoustic notes on the virtual reality reconstruction of the Queen's theatre (Adelaide, 1841)

This paper presents the results of an international interdisciplinary effort to reconstruct the Queen's Theatre in Adelaide as it stood on its inaugural debut in 1841. Our collaborative approach brings together real actors, set and costume designers, architects, virtual reality (VR) developers, motion capture specialists, and acoustic engineers in order to reproduce, as realistically as possible, the opening night monologue by Mr Gustavus Arabin. By combining the modelled ambisonics room impulse responses with a proprietary algorithm, we achieved an authentic representation of the historical environment both visually and acoustically by allowing the user to immerse themselves in the space at several locations within the theatre. Central to our VR reconstruction is the ability of our software to combine auralisations from multiple sound sources simultaneously as well as allowing the user to upload user-generated anechoic files. The paper focuses on the acoustic nuances throughout the VR reconstruction, providing a comprehensive overview of collaborative endeavours and technological advancements enabling users to grasp and appreciate the acoustic intricacies of Queen's Theatre. Emphasising the acoustic dimension of the space underscores the potential of our virtual model to serve as a dynamic platform for historical exploration, research, and educational pursuits.

From an Engraving to a Virtual Reconstruction: The 3D Modelling of Maria Amalia of Saxony's Funerary Ceremony in the Cathedral of Barcelona (1761)

This article discusses a virtual reconstruction of the catafalque and the ephemeral decorations created for the funeral of Maria Amalia of Saxony in the Cathedral of Barcelona in 1761. A combination of a historical-artistic approach and a variety of 3D modelling techniques has made it possible to recreate an ephemeral piece of architecture that, being constructed only for the funerary ceremony, has not lasted over time, such that the work presented here constitutes a novel strategy to promote a better understanding of another element of our cultural legacy.

Nativity of the Virgin Mary Kozelshchynskyi Monastery in the Poltava Region: an assessment of architectural heritage and contemporary challenges

The challenge of preserving the architectural heritage of small towns in Ukraine is compounded by the lack of sufficient historical and architectural research, as well as numerous alterations to buildings during their use. This article presents the results of historical and architectural research on the architectural heritage of the Nativity of the Virgin Mary Kozelshchyna Monastery in the Poltava Region. It explores the historical stages of the monastery's formation and development and evaluates its historical and cultural significance. A virtual reconstruction of the monastery's original appearance was undertaken, and the historical boundaries of the monastery were established. The analysis of the current state enabled the identification of issues related to the monastery's functioning and the preservation of its cultural heritage. This research provides a scientific foundation for developing protection zones for the monastery and for restoration and adaptation projects of its buildings. It also establishes an information base for future project work and the monitoring of architectural heritage.

A computer-vision based framework for virtual 3D garment reconstruction

AbstractExisting 3D garment reconstruction methods are difficult to implement for online fashion design and e-commerce or special applications. This paper proposes a novel computer-vision framework for 3D garment digital reconstruction, which aims to reconstruct high-quality and realistic virtual 3D garments with fabric mechanic properties for 3D virtual try-on. The new segmentation scheme is proposed to separate the 3D garment point clouds from background points, which is suitable for 3D human shapes and is adaptive for different 3D garment models in different scenes. The new Statistical Outlier Removal algorithm and the learning-based method PointCleanNet are combined to remove noise and outliers in 3D garment point clouds, which provides high-fidelity and high-quality 3D garment point clouds. The 3D garment meshes are then reconstructed from their corresponding point clouds with a modified rolling ball algorithm. Finally, the meshes are improved and converted into physics-based virtual try-on 3D garments with fabric mechanic properties added, which enables the assessment of different body shapes with varied sizes for the same reconstructed 3D garment. Comparison experiments demonstrate that our framework achieves high-quality and realistic 3D garment reconstruction and accurate 3D virtual try-on from 2D garment images. We also demonstrate the proposed framework on a large range of various garments to show this approach has a great potential for garment future technology, such as online garment shopping, garment design and manufacturing.

Beyond Creating Collections

This paper aims to demonstrate how virtual reality (VR), augmented reality (AR), and 3D archaeological reconstructions have been employed to immerse viewers into historical places with the inclusion or exclusion of digital narratives in the heritage and tourism sectors. Countless galleries, libraries, archives, and museums have included digitally re-created objects and re-imagined scenes in situ through theatrical sets and live historical re-enactments to help visitors see and contextualise objects from history. What if these techniques were applied to 3D virtual narrative experiences? This scoping review focuses primarily on selected studies that create 3D models for archaeology, VR, and AR that utilise 3D models, and virtual heritage ‘edutainment’ experiences published within the last five years (i.e., 2018-2023). It gives an overview of the current methods and technologies used to create 3D heritage productions for scientific studies, heritage preservation and tourism, and educational applications. Ultimately, this paper discusses possibilities for future work on how extended reality and 3D models could be included in narrative experiences based on gaps in the existing research.

The reliability of virtual non-contrast reconstructions of photon-counting detector CT scans in assessing abdominal organs

BackgroundSpectral imaging of photon-counting detector CT (PCD-CT) scanners allows for generating virtual non-contrast (VNC) reconstruction. By analyzing 12 abdominal organs, we aimed to test the reliability of VNC reconstructions in preserving HU values compared to real unenhanced CT images.MethodsOur study included 34 patients with pancreatic cystic neoplasm (PCN). The VNC reconstructions were generated from unenhanced, arterial, portal, and venous phase PCD-CT scans using the Liver-VNC algorithm. The observed 11 abdominal organs were segmented by the TotalSegmentator algorithm, the PCNs were segmented manually. Average densities were extracted from unenhanced scans (HUunenhanced), postcontrast (HUpostcontrast) scans, and VNC reconstructions (HUVNC). The error was calculated as HUerror=HUVNC–HUunenhanced. Pearson’s or Spearman’s correlation was used to assess the association. Reproducibility was evaluated by intraclass correlation coefficients (ICC).ResultsSignificant differences between HUunenhanced and HUVNC[unenhanced] were found in vertebrae, paraspinal muscles, liver, and spleen. HUVNC[unenhanced] showed a strong correlation with HUunenhanced in all organs except spleen (r = 0.45) and kidneys (r = 0.78 and 0.73). In all postcontrast phases, the HUVNC had strong correlations with HUunenhanced in all organs except the spleen and kidneys. The HUerror had significant correlations with HUunenhanced in the muscles and vertebrae; and with HUpostcontrast in the spleen, vertebrae, and paraspinal muscles in all postcontrast phases. All organs had at least one postcontrast VNC reconstruction that showed good-to-excellent agreement with HUunenhanced during ICC analysis except the vertebrae (ICC: 0.17), paraspinal muscles (ICC: 0.64–0.79), spleen (ICC: 0.21–0.47), and kidneys (ICC: 0.10–0.31).ConclusionsVNC reconstructions are reliable in at least one postcontrast phase for most organs, but further improvement is needed before VNC can be utilized to examine the spleen, kidneys, and vertebrae.

The virtual reconstruction of Cervara di Roma fortress: methods and tools for the dissemination of the past

Three-dimensional (3D) technologies play a crucial role in the philological reconstruction of archaeological contexts. The integration of technology and archaeological evidence has made it possible to develop 3D virtual reconstructions, providing valuable insights into the temporal evolution of archaeological sites. This innovation serves as a significant research and analytical resource, enabling the visualisation of possible scenarios related to archaeological contexts that have significantly changed over time. Moreover, understanding these changes, the past and its relevance to the current context could pose a challenge to the general public. This work aims to illustrate a scalable rendering system using open-source Web3D apps and platforms, allowing access to information, 3D models, and descriptions to enhance the experience of artworks.

Registration accuracy comparing different rendering techniques on local vs external virtual 3D liver model reconstruction for vascular landmark setting by intraoperative ultrasound in augmented reality navigated liver resection

PurposeAugmented reality navigation in liver surgery still faces technical challenges like insufficient registration accuracy. This study compared registration accuracy between local and external virtual 3D liver models (vir3DLivers) generated with different rendering techniques and the use of the left vs right main portal vein branch (LPV vs RPV) for landmark setting. The study should further examine how registration accuracy behaves with increasing distance from the ROI.MethodsRetrospective registration accuracy analysis of an optical intraoperative 3D navigation system, used in 13 liver tumor patients undergoing liver resection/thermal ablation.Results109 measurements in 13 patients were performed. Registration accuracy with local and external vir3DLivers was comparable (8.76 ± 0.9 mm vs 7.85 ± 0.9 mm; 95% CI = -0.73 to 2.55 mm; p = 0.272). Registrations via the LPV demonstrated significantly higher accuracy than via the RPV (6.2 ± 0.85 mm vs 10.41 ± 0.99 mm, 95% CI = 2.39 to 6.03 mm, p < 0.001). There was a statistically significant positive but weak correlation between the accuracy (dFeature) and the distance from the ROI (dROI) (r = 0.298; p = 0.002).ConclusionDespite basing on different rendering techniques both local and external vir3DLivers have comparable registration accuracy, while LPV-based registrations significantly outperform RPV-based ones in accuracy. Higher accuracy can be assumed within distances of up to a few centimeters around the ROI.

Gathering up the Fragments of a Dismembered Timurid Masterpiece

Abstract: The Rasāyil, a sumptuous manuscript produced at the royal library of the Timurid prince Bāysunghur in Herat in 1427, contains seven rare treatises copied by the renowned calligrapher Shams al-Sulṭānī. This article discusses the manuscript’s literary content and artistic features and presents the intriguing discovery that the anthology, acquired by Bernard Berenson in 1910, is not the complete codex and indeed, bears signs of mutilation. It also identifies most of the lost components as extant and housed in three other collections. These discoveries enable a virtual reconstruction of the codex in the form produced for the prince.

A virtual reconstruction method for corridor gable buildings based on the knowledge of structural dynamics: taking Leiyin Cave as an example

Virtual reconstruction of ancient buildings often has incomplete records of the original design and construction details, and can only be reconstructed based on limited data, drawings and photography, which is different from the actual conditions. The unique overhanging structure of the corridor gable building makes it vulnerable to damage in extreme weather conditions. In order to ensure that the virtual reconstruction results can not only reproduce the original appearance of history, but also ensure that the reconstructed model maintains structural stability in the long term. This paper proposes a reconstruction method of the original appearance of the corridor gable building remains based on structural dynamics analysis. This method comprehensively uses three-dimensional reconstruction, structural engineering, dynamic analysis, and computer simulation technology to ensure the structural accuracy and historical authenticity of the virtually reconstructed corridor gable building. First, through data collection and analysis, combined with ancient architectural construction techniques, a preliminary three-dimensional model was created, which included all structural elements and details. Several groups of reconstruction schemes are determined based on material properties. Then, using finite element analysis software, perform dynamic analysis on the three-dimensional model. Evaluate the stability of the reconstructed structure and optimize the material selection plan to ensure the feasibility and accuracy of the virtual reconstruction. Taking the virtual reconstruction of the eaves in front of Leiyin Cave as an example, it shows that this method is effective and feasible to achieve the virtual reconstruction of corridor gable buildings. It provides new ideas for virtual reconstruction of ancient buildings and has important practical application value.

Accuracy of ultra-high resolution and virtual non-calcium reconstruction algorithm for stenosis evaluation with photon-counting CT: results from a dynamic phantom study

BackgroundWe compared ultra-high resolution (UHR), standard resolution (SR), and virtual non-calcium (VNCa) reconstruction for coronary artery stenosis evaluation using photon-counting computed tomography (PC-CT).MethodsOne vessel phantom (4-mm diameter) containing solid calcified lesions with 25% and 50% stenoses inside a thorax phantom with motion simulation underwent PC-CT using UHR (0.2-mm slice thickness) and SR (0.6-mm slice thickness) at heart rates of 60 beats per minute (bpm), 80 bpm, and 100 bpm. A paired t-test or Wilcoxon test with Bonferroni correction was used.ResultsFor 50% stenosis, differences in percent mean diameter stenosis between UHR and SR at 60 bpm (51.0 vs 60.3), 80 bpm (51.7 vs 59.6), and 100 bpm (53.7 vs 59.0) (p ≤ 0.011), as well as between VNCa and SR at 60 bpm (50.6 vs 60.3), 80 bpm (51.5 vs 59.6), and 100 bpm (53.7 vs 59.0) were significant (p ≤ 0.011), while differences between UHR and VNCa at all heart rates (p ≥ 0.327) were not significant. For 25% stenosis, differences between UHR and SR at 60 bpm (28.0 vs 33.7), 80 bpm (28.4 vs 34.3), and VNCa vs SR at 60 bpm (29.1 vs 33.7) were significant (p ≤ 0.015), while differences for UHR vs SR at 100 bpm (29.9 vs 34.0), as well as for VNCa vs SR at 80 bpm (30.7 vs 34.3) and 100 bpm (33.1 vs 34.0) were not significant (p ≥ 0.028).ConclusionStenosis quantification accuracy with PC-CT improved using either UHR acquisition or VNCa reconstruction.Relevance statementPC-CT offers to scan with UHR mode and the reconstruction of VNCa images both of them could provide improved coronary stenosis quantification at increased heart rates, allowing a more accurate stenosis grading at low and high heart rates compared to SR.Key PointsEvaluation of coronary stenosis with conventional CT is challenging at high heart rates.PC-CT allows for scanning with ECG-gated UHR and SR modes.UHR and VNCa images were compared in a dynamic phantom.UHR improves stenosis quantification up to 100 bpm.VNCa reconstruction improves stenosis evaluation up to 80 bpm.Graphical

Automatic virtual reconstruction of acetabular fractures using a statistical shape model.

Automatic virtual reconstruction of complex fractures would be helpful for pre-operative surgical planning. We developed a statistical shape model (SSM) which contains data of 200 intact 3D hemipelves. It allows for quantification of shape differences and is able to reconstruct abnormal shaped pelvises. We applied our SSM to reconstruct elementary and associate type acetabular fractures and assessed the reconstruction performance of the SSM, by comparing the reconstructed shape with the intact contralateral hemipelvis. In this retrospective diagnostic imaging study, we used our SSM to virtually reconstruct fractured hemipelves of eighty-three patients with an acetabular fracture. A root mean square error (RMSE) was computed between the reconstructed shape and intact contralateral shape for the whole hemipelvis and for regions relevant for plate-fitting. These plate-fitting relevant regions were defined as: (1) Iliopectineal line length and radius; (2) ischial body line length and radius; (3) acetabular diameter, (4) quadrilateral slope and (5) weight-bearing acetabular dome. The median RMSE of the whole hemipelvis of the elementary type fractures was 2.2 (1.7-2.5) mm versus 3.2 (2.2-3.9) mm for the associate type fractures (p < 0.001). The median RMSE for the plate-fitting regions of elementary type fractures was 1.7 (1.4-2.1) mm versus 2.7 (2.0-4.1) mm for associate type fractures (p < 0.001). Using a statistical shape model allows for accurate virtual reconstructions of elementary and associate type acetabular fractures within a clinically acceptable range, especially within regions important for plate-fitting. SSM-based reconstructions can serve as a valuable tool for pre-operative planning in clinical practice, when a template of the contralateral hemipelvis is unavailable.