Three-dimensional volumetric assessment of hard tissue alterations following horizontal guided bone regeneration using a split-thickness flap design: A case series.

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 mm3. An average of 238.48 ± 127.82 mm3 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 mm3/mm2. 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.

3D morphometric quantification of maxillae and defects for patients with unilateral cleft palate via deep learning-based CBCT image auto-segmentation.

OBJECTIVE: This study aimed to quantify the 3D asymmetry of the maxilla in patients with unilateral cleft lip and palate (UCP) and investigate the defect factors responsible for the variability of the maxilla on the cleft side using a deep-learning-based CBCT image segmentation protocol. SETTING AND SAMPLE POPULATION: Cone beam computed tomography (CBCT) images of 60 patients with UCP were acquired. The samples in this study consisted of 39 males and 21 females, with a mean age of 11.52 years (SD = 3.27 years; range of 8-18 years). MATERIALS AND METHODS: The deep-learning-based protocol was used to segment the maxilla and defect initially, followed by manual refinement. Paired t-tests were performed to characterize the maxillary asymmetry. A multiple linear regression was carried out to investigate the relationship between the defect parameters and those of the cleft side of the maxilla. RESULTS: The cleft side of the maxilla demonstrated a significant decrease in maxillary volume and length as well as alveolar length, anterior width, posterior width, anterior height and posterior height. A significant increase in maxillary anterior width was demonstrated on the cleft side of the maxilla. There was a close relationship between the defect parameters and those of the cleft side of the maxilla. CONCLUSIONS: Based on the 3D volumetric segmentations, significant hypoplasia of the maxilla on the cleft side existed in the pyriform aperture and alveolar crest area near the defect. The defect structures appeared to contribute to the variability of the maxilla on the cleft side.

Deep learning based direct segmentation assisted by deformable image registration for cone-beam CT based auto-segmentation for adaptive radiotherapy.

Cone-beam CT (CBCT)-based online adaptive radiotherapy calls for accurate auto-segmentation to reduce the time cost for physicians. However, deep learning (DL)-based direct segmentation of CBCT images is a challenging task, mainly due to the poor image quality and lack of well-labelled large training datasets. Deformable image registration (DIR) is often used to propagate the manual contours on the planning CT (pCT) of the same patient to CBCT. In this work, we undertake solving the problems mentioned above with the assistance of DIR. Our method consists of three main components. First, we use deformed pCT contours derived from multiple DIR methods between pCT and CBCT as pseudo labels for initial training of the DL-based direct segmentation model. Second, we use deformed pCT contours from another DIR algorithm as influencer volumes to define the region of interest for DL-based direct segmentation. Third, the initially trained DL model is further fine-tuned using a smaller set of true labels. Nine patients are used for model evaluation. We found that DL-based direct segmentation on CBCT without influencer volumes has much poorer performance compared to DIR-based segmentation. However, adding deformed pCT contours as influencer volumes in the direct segmentation network dramatically improves segmentation performance, reaching the accuracy level of DIR-based segmentation. The DL model with influencer volumes can be further improved through fine-tuning using a smaller set of true labels, achieving mean Dice similarity coefficient of 0.86, Hausdorff distance at the 95th percentile of 2.34 mm, and average surface distance of 0.56 mm. A DL-based direct CBCT segmentation model can be improved to outperform DIR-based segmentation models by using deformed pCT contours as pseudo labels and influencer volumes for initial training, and by using a smaller set of true labels for model fine tuning.

Automatic segmentation for plan-of-the-day selection in CBCT-guided adaptive radiation therapy of cervical cancer.

Objective.Plan-of-the-day (PoD) adaptive radiation therapy (ART) is based on a library of treatment plans, among which, at each treatment fraction, the PoD is selected using daily images. However, this strategy is limited by PoD selection uncertainties. This work aimed to propose and evaluate a workflow to automatically and quantitatively identify the PoD for cervix cancer ART based on daily CBCT images.Approach.The quantification was based on the segmentation of the main structures of interest in the CBCT images (clinical target volume [CTV], rectum, bladder, and bowel bag) using a deep learning model. Then, the PoD was selected from the treatment plan library according to the geometrical coverage of the CTV. For the evaluation, the resulting PoD was compared to the one obtained considering reference CBCT delineations.Main results.In experiments on a database of 23 patients with 272 CBCT images, the proposed method obtained an agreement between the reference PoD and the automatically identified PoD for 91.5% of treatment fractions (99.6% when considering a 5% margin on CTV coverage).Significance.The proposed automatic workflow automatically selected PoD for ART using deep-learning methods. The results showed the ability of the proposed process to identify the optimal PoD in a treatment plan library.

Utilizing a novel radiographic image segmentation method for the assessment of periodontal healing following regenerative surgical treatment.

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.

Deep cross-modality (MR-CT) educed distillation learning for cone beam CT lung tumor segmentation.

PURPOSE: Despite the widespread availability of in-treatment room cone beam computed tomography (CBCT) imaging, due to the lack of reliable segmentation methods, CBCT is only used for gross set up corrections in lung radiotherapies. Accurate and reliable auto-segmentation tools could potentiate volumetric response assessment and geometry-guided adaptive radiation therapies. Therefore, we developed a new deep learning CBCT lung tumor segmentation method. METHODS: The key idea of our approach called cross-modality educed distillation (CMEDL) is to use magnetic resonance imaging (MRI) to guide a CBCT segmentation network training to extract more informative features during training. We accomplish this by training an end-to-end network comprised of unpaired domain adaptation (UDA) and cross-domain segmentation distillation networks (SDNs) using unpaired CBCT and MRI datasets. UDA approach uses CBCT and MRI that are not aligned and may arise from different sets of patients. The UDA network synthesizes pseudo MRI from CBCT images. The SDN consists of teacher MRI and student CBCT segmentation networks. Feature distillation regularizes the student network to extract CBCT features that match the statistical distribution of MRI features extracted by the teacher network and obtain better differentiation of tumor from background. The UDA network was implemented with a cycleGAN improved with contextual losses separately on Unet and dense fully convolutional segmentation networks (DenseFCN). Performance comparisons were done against CBCT only using 2D and 3D networks. We also compared against an alternative framework that used UDA with MR segmentation network, whereby segmentation was done on the synthesized pseudo MRI representation. All networks were trained with 216 weekly CBCTs and 82 T2-weighted turbo spin echo MRI acquired from different patient cohorts. Validation was done on 20 weekly CBCTs from patients not used in training. Independent testing was done on 38 weekly CBCTs from patients not used in training or validation. Segmentation accuracy was measured using surface Dice similarity coefficient (SDSC) and Hausdroff distance at 95th percentile (HD95) metrics. RESULTS: The CMEDL approach significantly improved (p < 0.001) the accuracy of both Unet (SDSC of 0.83 ± 0.08; HD95 of 7.69 ± 7.86 mm) and DenseFCN (SDSC of 0.75 ± 0.13; HD95 of 11.42 ± 9.87 mm) over CBCT only 2DUnet (SDSC of 0.69 ± 0.11; HD95 of 21.70 ± 16.34 mm), 3D Unet (SDSC of 0.72 ± 0.20; HD95 15.01 ± 12.98 mm), and DenseFCN (SDSC of 0.66 ± 0.15; HD95 of 22.15 ± 17.19 mm) networks. The alternate framework using UDA with the MRI network was also more accurate than the CBCT only methods but less accurate the CMEDL approach. CONCLUSIONS: Our results demonstrate feasibility of the introduced CMEDL approach to produce reasonably accurate lung cancer segmentation from CBCT images. Further validation on larger datasets is necessary for clinical translation.