Background and Objective Finite Element Analysis (FEA) is a powerful computational technique used to assess bone strength and fracture risk based on patient-specific anatomical data. However, the widespread clinical and research adoption of this technique is often hindered by the complex and labor-intensive preprocessing steps required to convert clinical imaging data into analysis-ready finite element models, including segmentation, mesh generation, material property mapping, and solver-specific file formatting. Methods To address this bottleneck, we developed BoneMesh, an automated meshing and material-mapping software module integrated into the open-source 3D Slicer platform. BoneMesh streamlines the generation of high-quality, patient-specific tetrahedral meshes directly from CT-based bone segmentations and efficiently assigns bone mineral density values derived from the imaging data. Results We verified the performance of BoneMesh against established commercial and freeware software (Abaqus, Simpleware and Bonemat) using CT-scans and segmentations from frequently analyzed human bones (Femur, Tibia, Lumbar vertebra, and Thoracic vertebra), demonstrating similar or superior performance in achieving targeted mesh quality parameters, including mesh edge length accuracy, element shape factors, and aspect ratios. Conclusion BoneMesh significantly reduces manual intervention, preprocessing time, and the potential for human errors, thus offering an open-source, accessible, reliable, and efficient pipeline for advancing patient-specific finite element simulations in clinical research and potentially in routine clinical assessments.

IntroductionGiven the high prevalence of vertebral fractures following radiotherapy in patients with metastatic spine disease, torso muscle segmentation is necessary for biomechanical modeling of vertebral loading, permitting individualized evaluation of fracture risk.MethodsIn this study, we developed and validated a deep-learning model for full volumetric segmentation of the thoracic and abdominal spinal musculature in cancer patients with metastatic spine disease from sparsely annotated clinical CT image data. We obtained CT data for 148 metastatic spine disease patients undergoing radiotherapy treatment, and an external set of randomly selected 30 subjects from the National Lung Screening Trial. We extracted 1924 axial CT images at the midpoint of each vertebral level (T4 to L4) and manually labeled the key extensor and flexor muscles (up to 8 muscles per side) at each level. We trained a 2D nnU-Net deep-learning (DL) model to segment each muscle and, using these sparse annotations, trained the model to segment each muscle’s 3D volume per spine. Two experienced radiologists independently and blindly evaluated the anatomical fidelity of the segmentations using a Likert scale, for 1) manual- and 2) DL-segmentation, 3) random test samples from the muscle’s 3D volume and 4) an external NLST CT data.ResultsThe DL method achieved comparable performance to manual segmentations with a mean Dice score above 0.769. Mann-Whitney test analysis showed that the radiologist ratings of DL-generated muscle segmentations were noninferior to the manual segmentation for each muscle.DiscussionDemonstrating excellent performance for rapid, high-anatomical fidelity 3D segmentation of the main flexor, extensor, and stabilizing thoracolumbar muscles, the DL model from clinical CT scans, this development holds significant potential for reducing the manual effort required to generate individualized musculoskeletal models in cancer patients.

BACKGROUND:The accurate assessment of infraosseous periodontal defects is crucial for effective diagnosis and treatment planning. Cone-beam computed tomography (CBCT) enables detailed imaging of these defects; however, to leverage their full potential, CBCT images must be reconstructed in 3 dimensions (3D). Manual and semi-automatic (SA) segmentation methods are time-consuming and prone to human error. This study aimed to evaluate the performance of a deep learning (DL) model in segmenting mandibular infraosseous periodontal defects on CBCT scans. METHODS:A multi-stage Segmentation Residual Network (SegResNet)-based DL model was used to segment CBCT scans from patients with stages III to IV periodontitis. Linear and volumetric measurements of infraosseous defects from DL-generated 3D models were compared to those obtained using SA segmentation. The depth (INFRA), width (WIDTH), angle (ANGLE), and volume of 48 infraosseous defects were assessed on both DL and SA segmentations. RESULTS:Measurements made on the DL and SA segmentations correlated strongly. The intraclass correlation coefficient (ICC) was 0.941 (p < 0.0001) for INFRA, 0.943 (p < 0.0001) for WIDTH, 0.889 (p < 0.0001) for ANGLE, and 0.948 (p < 0.0001) for defect volume. These results indicate high reliability of the DL model in capturing key characteristics of infraosseous periodontal defects. CONCLUSIONS:These findings support the use of DL-based CBCT segmentation as a valuable tool for enhancing periodontal diagnosis. However, as this study was limited to mandibular defects, applicability to maxillary cases remains to be validated.

Many approaches have been used to model chordae tendineae geometries in finite element simulations of atrioventricular heart valves. Unfortunately, current "functional" chordae tendineae geometries lack fidelity that would be helpful when informing clinical decisions. The objectives of this work are (i) to improve synthetic chordae tendineae geometry fidelity to consider branching and (ii) to define how the chordae tendineae geometry affects finite element simulations of valve closure. In this work, we develop an open-source method to construct synthetic chordae tendineae geometries in the SlicerHeart Extension of 3D Slicer. The generated geometries are then used in FEBio finite element simulations of atrioventricular valve function to evaluate how variations in chordae tendineae geometry influence valve behavior. Effects are evaluated using functional and mechanical metrics. Our findings demonstrated that altering the chordae tendineae geometry of a stereotypical mitral valve led to changes in clinically relevant valve metrics and valve mechanics. Specifically, cross sectional area had the most influence over valve closure metrics, followed by chordae tendineae density, length, radius and branches. We then used this information to showcase the flexibility of our new workflow by altering the chordae tendineae geometry of two additional geometries (mitral valve with annular dilation and tricuspid valve) to improve finite element predictions. This study presents a flexible, open-source method for generating synthetic chordae tendineae with realistic branching structures. Further, we establish relationships between the chordae tendineae geometry and valve functional/mechanical metrics. This research contribution helps enrich our open-source workflow and brings the finite element simulations closer to use in a patient-specific clinical setting.

OBJECTIVES:This study evaluated the performance of a multi-stage Segmentation Residual Network (SegResNet)-based deep learning (DL) model for the automatic segmentation of cone-beam computed tomography (CBCT) images of patients with stage III and IV periodontitis. METHODS:Seventy pre-processed CBCT scans from patients undergoing periodontal rehabilitation were used for training and validation. The model was tested on 10 CBCT scans independent from the training dataset by comparing results with semi-automatic (SA) segmentations. Segmentation accuracy was assessed using the Dice similarity coefficient (DSC), Intersection over Union (IoU), and Hausdorff distance 95th percentile (HD95). Linear periodontal measurements were performed on four tooth surfaces to assess the validity of the DL segmentation in the periodontal region. RESULTS:The DL model achieved a mean DSC of 0.9650 ± 0.0097, with an IoU of 0.9340 ± 0.0180 and HD95 of 0.4820 mm ± 0.1269 mm, showing strong agreement with SA segmentation. Linear measurements revealed high statistical correlations between the mesial, distal, and lingual surfaces, with intraclass correlation coefficients (ICC) of 0.9442 (p < 0.0001), 0.9232 (p < 0.0001), and 0.9598(p < 0.0001), respectively, while buccal measurements revealed lower consistency, with an ICC of 0.7481 (p < 0.0001). The DL method reduced the segmentation time by 47 times compared to the SA method. CONCLUSIONS:Acquired 3D models may enable precise treatment planning in cases where conventional diagnostic modalities are insufficient. However, the robustness of the model must be increased to improve its general reliability and consistency at the buccal aspect of the periodontal region. CLINICAL SIGNIFICANCE:This study presents a DL model for the CBCT-based segmentation of periodontal defects, demonstrating high accuracy and a 47-fold time reduction compared to SA methods, thus improving the feasibility of 3D diagnostics for advanced periodontitis.

Purpose:Given the high prevalence of vertebral fractures post-radiotherapy in patients with metastatic spine disease, accurate and rapid muscle segmentation could support efforts to quantify muscular changes due to disease or treatment and enable biomechanical modeling for assessments of vertebral loading to improve personalized evaluation of vertebral fracture risk. This study presents a deep-learning approach for segmenting the complete volume of the trunk muscles from clinical CT images trained using sparsely annotated data. Materials and Methods:we extracted 2,009 axial CT images at the midpoint of each vertebral level (T4 to L4) from clinical CT of 148 cancer patients. The key extensor and flexor muscles (up to 8 muscles per side) were manually contoured and labeled per image in the thoracic and lumbar regions. We first trained a 2D nnU-Net deep-learning model on these labels to segment key extensor and flexor muscles. Using these sparse annotations per spine, we trained the model to segment each muscle's entire 3D volume. Results:The proposed method achieved comparable performance to manual segmentations, as assessed by expert radiologists, with a mean Dice score above 0.769. Significantly, the model drastically reduced segmentation time, from 4.3-6.5 hours for manual segmentation of 14 single axial CT images to approximately 1 minute for segmenting the complete thoracic-abdominal 3D volume. Conclusion:The approach demonstrates high potential for automating 3D muscle segmentation, significantly reducing the manual intervention required for generating musculoskeletal models, and could be instrumental in enhancing clinical decision-making and patient care in radiation oncology.

BACKGROUND:Ductus arteriosus stenting (DAS) is used to palliate infants with ductal-dependent pulmonary blood flow (DD-PBF), however patent ductus arteriosus (PDA) anatomy can be complex and heterogenous. AIMS:We developed custom, open-source software to model and quantify PDA anatomy. METHODS:We retrospectively identified 33 neonates with DD-PBF with a CTA before DAS. A novel custom workflow was implemented in 3D Slicer and SlicerHeart to semi-automatically extract centerlines of the course of the PDA and surrounding vessels. 3D ductal length, diameter, curvature and tortuosity were automatically calculated (3D automatic) and compared to manually adjusted 3D measurements (3D semi-automatic), and manual measurements of PDA dimensions in 2D projectional angiograms before and after stent angioplasty. RESULTS:Ductal anatomy was successfully modeled and quantified in all subjects. 3D automatic and semi-automatic measurements of straight-line aortic to pulmonary artery length were not significantly different than 2D measurements. Semi-automatic 3D measurements were similar to 2D measurements of the total length. Minimum and maximum ductal diameters were not significantly different by 3D automatic and 2D measurements, however semi-automatic 3D diameters were significantly larger. Inter-reader reliability of ductal length and diameter was higher with manual adjustment of 3D centerlines compared to standard measurement of 2D angiograms. These differences were consistent across PGE doses between CTA and DAS. CONCLUSIONS:Automatic PDA modeling is feasible and efficient, enabling reproducible quantification of ductal anatomy for procedural planning of DAS in patients with DD-PBF. Further development is needed as well as investigation of whether 3D modeling-derived measurements influence procedural duration or outcome.

To investigate the performance of a deep learning (DL) model for segmenting cone-beam computed tomography (CBCT) scans taken before and after mandibular horizontal guided bone regeneration (GBR) to evaluate hard tissue changes. The proposed SegResNet-based DL model was trained on 70 CBCT scans. It was tested on 10 pairs of pre- and post-operative CBCT scans of patients who underwent mandibular horizontal GBR. DL segmentations were compared to semi-automated (SA) segmentations of the same scans. Augmented hard tissue segmentation performance was evaluated by spatially aligning pre- and post-operative CBCT scans and subtracting preoperative segmentations obtained by DL and SA segmentations from the respective postoperative segmentations. The performance of DL compared to SA segmentation was evaluated based on the Dice similarity coefficient (DSC), intersection over the union (IoU), Hausdorff distance (HD95), and volume comparison. The mean DSC and IoU between DL and SA segmentations were 0.96 ± 0.01 and 0.92 ± 0.02 in both pre- and post-operative CBCT scans. While HD95 values between DL and SA segmentations were 0.62 mm ± 0.16 mm and 0.77 mm ± 0.31 mm for pre- and post-operative CBCTs respectively. The DSC, IoU and HD95 averaged 0.85 ± 0.08; 0.78 ± 0.07 and 0.91 ± 0.92 mm for augmented hard tissue models respectively. Volumes mandible- and augmented hard tissue segmentations did not differ significantly between the DL and SA methods. The SegResNet-based DL model accurately segmented CBCT scans acquired before and after mandibular horizontal GBR. However, the training database must be further increased to increase the model’s robustness. Automated DL segmentation could aid treatment planning for GBR and subsequent implant placement procedures and in evaluating hard tissue changes.

Bevezetés: A ’cone-beam’ (kúpsugaras) számítógépes tomográfiás (CBCT) felvételek szegmentációja során a síkbeli képekből álló adatokat három dimenzióban (3D) rekonstruáljuk. A szájsebészetben és a parodontológiában a digitális adatfeldolgozás lehetővé teszi a műtéti beavatkozások 3D tervezését. A leggyakrabban alkalmazott határérték-alapú szegmentáció gyors, de pontatlan, míg a félautomatikus módszerek megfelelő pontosságúak, de rendkívül időigényesek. Az utóbbi években a mesterséges intelligencián alapuló technológiák elterjedésével azonban mostanra lehetőség van a CBCT-felvételek automatikus szegmentációjára. Célkitűzés: A klinikai gyakorlatból vett CBCT-felvételeken betanított mélytanulási szegmentációs modell bemutatása és hatékonyságának vizsgálata. Módszer: A vizsgálat három fő fázisa volt: a tanuló adatbázis felállítása, a mélytanulási modell betanítása és ezen architektúra pontosságának tesztelése. A tanuló adatbázis felállításához 70, részlegesen fogatlan páciens CBCT-felvételeit alkalmaztuk. A SegResNet hálózati architektúrára épülő szegmentációs modellt a MONAI rendszer segítségével fejlesztettük ki. A mélytanulási modell pontosságának ellenőrzéséhez 15 CBCT-felvételt használtunk. Ezeket a felvételeket a mélytanulási modell segítségével, valamint félautomatikus szegmentációval is feldolgoztuk, és összehasonlítottuk a két szegmentáció eredményét. Eredmények: A mélytanulásos szegmentáció és a félautomatikus szegmentáció közötti hasonlóság a Jaccard-index szerint átlagosan 0,91 ± 0,02, a Dice hasonlósági együttható átlagos értéke 0,95 ± 0,01, míg a két modell közötti átlagos Hausdorff- (95%) távolság 0,67 mm ± 0,22 mm volt. A mélytanulásos architektúra által szegmentált és a félautomatikus szegmentációval létrehozott 3D modellek térfogata nem mutatott statisztikailag szignifikáns különbséget (p = 0,31). Megbeszélés: A vizsgálatunkban használt mélytanulási modell az irodalomban található mesterségesintelligencia-rendszerekhez hasonló pontossággal végezte el a CBCT-felvételek szegmentációját, és mivel a CBCT-felvételek a rutin klinikai gyakorlatból származtak, a mélytanulási modell relatíve nagy megbízhatósággal szegmentálta a parodontalis csonttopográfiát és az alveolaris gerincdefektusokat. Következtetés: A mélytanulási modell nagy pontossággal szegmentálta az alsó állcsontot dentális CBCT-felvételeken. Ezek alapján megállapítható, hogy a mélytanulásos szegmentációval előállított 3D modell alkalmas lehet rekonstruktív szájsebészeti és parodontalis sebészeti beavatkozások digitális tervezésére. Orv Hetil. 2024; 165(32): 1242–1251.

This video guides the viewer over the process of how a segmentation created using ITK-Snap can be converted into a standard DICOM representation using dcmqi.

Introduction: The goal of segmentation is to reconstruct cone-beam computed tomography (CBCT) images in three dimensions (3D). In oral surgery and periodontology, digital data processing enables 3D planning of surgical interventions. Commonly used threshold-based segmentation is fast but inaccurate, whereas semi-automatic methods are sufficiently accurate but time-consuming. Recently, with artificial intelligence-based technologies, automatic segmentation of CBCT images has become feasible. Objective: To present a deep learning segmentation model trained on CBCT images derived from clinical practice and to evaluate its efficiency. Method: The study consisted of three phases: establishing the training dataset, training the deep learning model and testing its accuracy. CBCT images of 70, partially edentulous patients were used to establish the training dataset. The deep learning model, based on the SegResNet architecture, was developed within the MONAI framework. To verify the accuracy of the deep learning model, 15 CBCT scans were used processed using the deep learning-based segmentation and semi-automatic segmentation, and the results were compared. Results: The similarity between the two methods, based on intersection over union, was on average 0.91 +/- 0.02. The average Dice similarity coefficient was 0.95 +/- 0.01, and the average Hausdorff (95%) distance was 0.67 mm +/- 0.22 mm. There was no statistically significant difference in the volume of the 3D models segmented by the deep learning architecture compared to those created by semi-automatic segmentation (p = 0.31). Discussion: The deep learning model used in our study performed segmentation of CBCT images with accuracy comparable to other artificial intelligence-based systems reported in the literature. Since the CBCT images were sourced from routine clinical practice, the deep learning model segmented periodontal bone topography and alveolar ridge defects with relatively high reliability. Conclusion: The deep learning model accurately segmented the mandible in dental CBCT scans. Therefore, the deep learning-based 3D models could be suitable for digital planning of reconstructive oral and periodontal surgical interventions.

This video explains how to set up the environment, install related tools, and install dcmqi from Docker Hub.

This video guides the user over the steps how to visualize the DICOM segmentation objects and structured measurements using 3D Slicer platform.

Background and details about the functionality of the software that could not be included in the main manuscript due to the size constraints.

Objectives To analyze morphological, volumetric, and linear hard tissue changes following horizontal ridge augmentation using a three-dimensional radiographic method. Methods As part of a larger ongoing prospective study, 10 lower lateral surgical sites were selected for evaluation. Horizontal ridge deficiencies were treated with guided bone regeneration (GBR) using a split-thickness flap design and a resorbable collagen barrier membrane. Following the segmentation of baseline and 6-month follow-up cone-beam computed tomography scans, volumetric, linear, and morphological hard tissue changes and the efficacy of the augmentation were assessed (expressed by the volume-to-surface ratio). Results Volumetric hard tissue gain averaged 605.32 ± 380.68 mm 3 . An average of 238.48 ± 127.82 mm 3 hard tissue loss was also detected at the lingual aspect of the surgical area. Horizontal hard tissue gain averaged 3.00 ± 1.45 mm. Midcrestal vertical hard tissue loss averaged 1.18 ± 0.81 mm. The volume-to-surface ratio averaged 1.19 ± 0.52 mm 3 /mm 2 . The three-dimensional analysis showed slight lingual or crestal hard tissue resorption in all cases. In certain instances, the greatest extent of hard tissue gain was observed 2–3 mm apical to the initial level of the marginal crest. Conclusions With the applied method, previously unreported aspects of hard tissue changes following horizontal GBR could be examined. Midcrestal bone resorption was demonstrated, most likely caused by increased osteoclast activity following the elevation of the periosteum. The volume-to-surface ratio expressed the efficacy of the procedure independent of the size of the surgical area.

OBJECTIVE:The aim of the current article was to present a radiographic method to determine the surface area of newly formed periodontal attachment, as well as to analyze volumetric and morphologic changes after regenerative periodontal treatment.METHOD AND MATERIALS:In this retrospective study, 11 singular intrabony periodontal defects were selected for minimally invasive surgical treatment and 3D evaluation. 3D virtual models were acquired by the segmentation of pre- and postoperative CBCT scans. This study determined the surface area of baseline periodontal attachment (RSA-A) and defect-involved root surface (RSA-D) on the preoperative 3D models, and the surface area of new periodontal attachment (RSA-NA) on the postoperative models. Finally, cumulative change of periodontal attachment (∆RSA-A) was calculated and Boolean subtraction was applied on pre- and postoperative 3D models to demonstrate postoperative 3D hard tissue alterations.RESULTS:The average RSA-A was 84.39 ± 33.27 mm2, while the average RSA-D was 24.26 ± 11.94 mm2. The average surface area of RSA-NA after regenerative periodontal surgery was 17.68 ± 10.56 mm2. Additionally, ∆RSA-A was determined to assess the overall effects of ridge alterations on periodontal attachment, averaging 15.53 ± 12.47 mm2, which was found to be statistically significant (P = .00149). Lastly, the volumetric hard tissue gain was found to be 33.56 ± 19.35 mm3, whereas hard tissue resorption of 26.31 ± 38.39 mm3 occurred.CONCLUSION:The proposed 3D radiographic method provides a detailed understanding of new periodontal attachment formation and hard tissue alterations following regenerative surgical treatment of intrabony periodontal defects.

Our aim was to present a virtual surgical planning process in the regenerative treatment of intrabony periodontal defects and to evaluate volumetric and 3D morphological changes by the superimposition of pre- and post-operative cone-beam computed tomography (CBCT) datasets. Eight intrabony periodontal defects were enrolled in the present investigation. CBCT and intraoral scans (IOS) were taken prior to and 6 months after periodontal regenerative surgery. Utilizing a semi-automatic segmentation method 3D models were generated from CBCT scans using an open-source radiographic image processing software (3D Slicer). Hybrid models were acquired with the superimposition and subsequent free-form surface modeling of the segmented CBCT model and the IOS. Hybrid models visualizing all relevant anatomical structures separately (alveolar bone, teeth, soft tissues) were used to plan each step of the procedure virtually prior to surgery. Superimposition of the pre- and post-operative CBCT scans was performed to validate volumetric and 3D morphological alterations. Based on the hybrid models, periodontal defect morphology was visualized in 3D. Following healing, hard tissue fill averaged at 43.04 mm3 ± 24.47 mm3. Hard tissue resorption could be detected in three cases. Hybrid models acquired with the technique allowed a better understanding of the 3D defect morphology and therefore more precise surgical planning could be performed. With the spatial registration of pre- and post-operative CBCT scans volumetric and 3D morphological alterations could be visualized that provided a better understanding of the healing dynamics.

Abstract Objectives The aim of this study was to evaluate the effects of membrane exposure during vertical ridge augmentation (VRA) utilizing guided bone regeneration with a dense polytetrafluoroethylene (d-PTFE) membrane and a tent-pole space maintaining approach by registering radiographic volumetric, linear and morphological changes. Methods In 8 cases alveolar ridge defects were accessed utilizing a split-thickness flap design. Following flap elevation VRA was performed with tent-pole space maintaining approach utilizing the combination of a non-reinforced d-PTFE membrane and a composite graft (1:1 ratio of autogenous bone chips and bovine derived xenografts). Three-dimensional radiographic evaluation of hard tissue changes was carried out with the sequence of cone-beam computed tomography (CBCT) image segmentation, spatial registration and 3D subtraction analysis. Results Class I or class II membrane exposure was observed in four cases. Average hard tissue gain was found to be 0.70 cm3 ± 0.31 cm3 and 0.82 cm3 ± 0.40 cm3 with and without membrane exposure resulting in a 17% difference. Vertical hard tissue gain averaged 4.06 mm ± 0.56 mm and 3.55 mm ± 0.43 mm in case of submerged and open healing, respectively. Difference in this regard was 14% between the two groups. Horizontal ridge width at 9-month follow-up was 5.89 mm ± 0.51 mm and 5.61 mm ± 1.21 mm with and without a membrane exposure respectively, resulting in a 5% difference. Conclusions With the help of the currently reported 3D radiographic evaluation method, it can be concluded that exposure of the new-generation d-PTFE membrane had less negative impact on clinical results compared to literature data reporting on expanded polytetrafluoroethylene membranes.

Automatic segmentation of medical images is a key step for diagnostic and interventional tasks. However, achieving this requires large amounts of annotated volumes, which can be tedious and time-consuming task for expert annotators. In this paper, we introduce DeepEdit, a deep learning-based method for volumetric medical image annotation, that allows automatic and semi-automatic segmentation, and click-based refinement. DeepEdit combines the power of two methods: a non-interactive (i.e. automatic segmentation using nnU-Net, UNET or UNETR) and an interactive segmentation method (i.e. DeepGrow), into a single deep learning model. It allows easy integration of uncertainty-based ranking strategies (i.e. aleatoric and epistemic uncertainty computation) and active learning. We propose and implement a method for training DeepEdit by using standard training combined with user interaction simulation. Once trained, DeepEdit allows clinicians to quickly segment their datasets by using the algorithm in auto segmentation mode or by providing clicks via a user interface (i.e. 3D Slicer, OHIF). We show the value of DeepEdit through evaluation on the PROSTATEx dataset for prostate/prostatic lesions and the Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) dataset for abdominal CT segmentation, using state-of-the-art network architectures as baseline for comparison. DeepEdit could reduce the time and effort annotating 3D medical images compared to DeepGrow alone. Source code is available at https://github.com/Project-MONAI/MONAILabel