Objective This study introduced a novel approach for constructing a proxy 3D (P-3D) periodontal model to improve periodontal diagnosis without relying on cone-beam computed tomography (CBCT). Methods This concept integrated intraoral scanning (IOS), orthopantomography (OPG), and periodontal probing pocket depth (PPD) to generate a P-3D representation of the periodontally involved dentition. IOS are partitioned into crown and soft-tissue components. The alveolar bone model was generated from the soft-tissue component based on average supracrestal soft-tissue dimensions. Teeth were segmented from OPG images and reconstructed into 3D models. Thereafter, segmented tooth models were aligned with IOS-derived crowns to reconstruct the tooth structure. 3D topography of periodontal defects was virtually modeled based on PPD data. Final P-3D representation was obtained by subtracting tooth- a periodontal defect models from the alveolar bone model. Model trueness was assessed by comparing linear measurements taken on the P-3D and a reference CBCT-derived 3D model. Results In the current pilot, a single mandibular P-3D model was obtained. Linear measurements registered at four aspects averaged 13.86±3.33 mm on P3D models, compared to 14.54±2.80 mm on CBCT models, with high correlation (intraclass correlation coefficient, 0.81; p<0.0001). Conclusions The method successfully visualized defect morphologies. The P-3D modeling approach offers a clinically viable interim solution for 3D periodontal diagnostics without the need for CBCT scans or other alternative volumetric imaging modalities. However, further automation and validation is necessary.

BACKGROUND:The European Federation of Periodontology (EFP) has developed Clinical Practice Guidelines (CPGs) for the treatment of periodontitis and for the management of peri-implant diseases. In accordance with the 2018 Classification, acute periodontal conditions are characterised by rapid-onset pain or discomfort, tissue destruction and infection. Therefore, the development of a CPG to guide patients and clinicians in their management is justified. AIM:To develop an S2k-level CPG for the management of acute periodontal conditions, necrotising periodontal diseases, periodontal abscesses and acute manifestations of endodontic-periodontal lesions. METHODS:This S2k-level CPG was developed by the EFP, following methodological guidance from the Association of Scientific Medical Societies in Germany and the Grading of Recommendations, Assessment, Development and Evaluation (GRADE) process. A rigorous and transparent process included synthesis of relevant research in two commissioned systematic reviews, evaluation of the quality and strength of evidence, formulation of specific recommendations and a structured consensus process involving leading experts and a broad base of stakeholders. Recommendations were based on the best available evidence, combined with structured expert consensus, particularly in areas where direct evidence remains scarce. RESULTS:The S2k-level CPG for the management of acute periodontal conditions presents a structured approach, grouping the recommendations in three successive steps: (1) confirming diagnosis, following the case definitions of the 2018 classification; (2) initial treatment, to control the acute condition including pain and active tissue destruction; and (3) subsequent treatments, to manage the pre-existing conditions and prevent the risk of disease recurrence and/or control the potential sequelae. CONCLUSION:The present S2k-level CPG informs clinical practice, health systems, policymakers and, indirectly, the public on the available and most effective interventions in the management of acute periodontal conditions.

OBJECTIVES:To evaluate the effects of submarginal instrumentation (SI) with or without adjunctive delivery of sodium hypochlorite (NaOCl)/amino acids and cross-linked hyaluronic acid (xHyA) gel in the treatment of peri-implant mucositis (PM). MATERIAL AND METHODS:Forty implants supporting single-unit crowns diagnosed with PM in 40 patients were randomly assigned to test (SI + NaOCl/amino acids and xHyA) or control group (SI alone). The primary outcome was mean BoP change. Full-Mouth Plaque Score (FMPS), Full-Mouth Bleeding Score (FMBS), modified plaque index (mPlI), and probing depth (PD) were assessed as secondary outcomes. Clinical parameters were assessed at baseline, 3 and 6 months. Disease resolution was also recorded. RESULTS:Two patients were lost during follow-up while 38 patients completed the study without adverse effects. After 6 months, all clinical parameters improved statistically significantly in both groups (p < 0.05). The change in mean BoP at 1, 3, and 6 months was 72.2% ± 24.3%, 70.4% ± 24.3%, and 63.0% ± 24.6% for test group and 70.0% ± 19.9%, 66.7% ± 24.8%, and 56.7% ± 30.8% for control group. The mean BoP change in experimental procedure was statistically significant at all investigation time points (p < 0.05). Regarding disease resolution, implants with initial PD ≤ 4 mm did not show differences among groups (p > 0.05); conversely, an initial PD = 5 mm yielded a statistically significant difference (p < 0.05). Disease resolution correlation with test group was statistically significant with a 3.77 odds ratio. CONCLUSION:Within the limitations of the present study, adjunctive delivery of NaOCl/amino acids and xHyA to SI yielded superior clinical outcomes compared with SI alone in the treatment of PM. TRIAL REGISTRATION:ClinicalTrials.gov: NCT05926297.

Reconstruction of advanced vertical and combined alveolar ridge defects still remains a challenge in implant dentistry. Digital technologies and virtual planning may potentially improve the predictability of guided bone regeneration (GBR). This study aimed to evaluate a fully digital, reverse-planning workflow for vertical ridge augmentation using membrane-cutting guides. This retrospective case series included 15 surgical sites presenting with vertical or combined alveolar ridge defects. A digital workflow integrating cone-beam computed tomography (CBCT), intraoral scanning, and virtual prosthetic planning was used to simulate ideal implant positions and corresponding hard tissue augmentation. Membrane-cutting guides were designed and fabricated using additive manufacturing to shape dense polytetrafluoroethylene membranes. Vertical GBR was performed using a split-thickness flap design and a tent-pole approach. Linear and volumetric hard tissue changes were assessed by comparing baseline and 9-month postoperative CBCT scans. Significant vertical bone gain was observed at all measurement points (p = 0.007), with mean increases from 15.70 mm ± 4.34 mm to 19.96 mm ± 3.83 mm at the central site. The mean volumetric hard tissue gain was 755.33 mm3 ± 411.22 mm3, closely matching the planned volume (757.50 mm3 ± 417.78 mm³), with no significant difference (p = 0.649). Using Spearman’s correlation, a strong positive correlation was found between planned and achieved volumes (Spearman’s ρ = 0.825, p = 0.0004). The mean augmentation efficacy was 20.13 ± 15.21 mm3/mm. The proposed 3D-driven reverse-planning workflow enabled predictable vertical ridge augmentation with high agreement between planned and achieved outcomes. This approach represents a feasible and accessible alternative to fully customized systems; however, further prospective controlled studies are required to validate these findings.

BACKGROUND:Recession Type 1 (RT1) multiple adjacent gingival recessions (MAGR) represent a clinically relevant condition and may compromise esthetics and function. Connective tissue grafts (CTG) remain the reference treatment but involve donor-site morbidity. Porcine acellular dermal matrices (PADM) have been proposed as substitutes. This prospective exploratory case series evaluated the clinical performance of the modified coronally advanced tunnel (MCAT) combined with a PADM, while also exploring microcirculatory behavior assessed by laser speckle contrast imaging (LSCI) and volumetric soft tissue changes. METHODS:Fifteen patients with 92 RT1 recession defects were treated using MCAT and a PADM (NovoMatrix®) in this prospective, single-center exploratory case series. The primary clinical outcome was site-level mean root coverage (MRC) at 6 months and 1 year, with recession sites clustered within patients. Key secondary outcomes were microcirculatory perfusion assessed by laser speckle contrast imaging (LSCI) in 53 sites, volumetric soft tissue change, and complete root coverage (CRC). RESULTS:At 6 months and 1 year, MRC was 73.2%, and CRC was achieved at 52.2% of sites. Recession depth and width decreased significantly (p < 0.001), while keratinized tissue width remained stable. Volumetric gain averaged 71.0 ± 37.4 mm³ at 6 months and 46.2 ± 23.5 mm³ at 1 year; values remained significantly above baseline at both time points, while volumetric gain decreased significantly from 6 months to 1 year (p < 0.001). Microcirculatory measurements showed an early reduction in perfusion followed by partial recovery over time, although some regions remained below baseline at later follow-up time points. Modest but significant site-level correlations were observed between day-30 perfusion and MRC at 6 months and 1 year. CONCLUSIONS:Within the limitations of this prospective exploratory case series, MCAT with PADM was associated with clinically relevant root coverage and supportive volumetric and microcirculatory findings in RT1 MAGRs.

AIM:To clinically and radiologically evaluate the healing capacity of intrabony periodontal defects treated with guided tissue regeneration (GTR) with or without the combination of orthodontic tooth movement (OTM). MATERIALS AND METHODS:Thirty-four individuals presenting with periodontal intrabony defects (IDs) and pathological tooth migration (PTM) were included in this randomised controlled clinical trial. Extended, coronally advanced flaps and GTR (collagen membrane and bovine bone mineral) were used to treat IDs. After surgery, patients were randomly allocated to either the test group (n = 17) with an early (1 week postoperatively) initiation of OTM or the control group (n = 17) without any tooth movement. Outcome variables comprised changes in clinical attachment level (CAL), probing pocket depth (PPD), gingival recession (GR), probing bone level and intrabony component (IC). RESULTS:Both groups yielded statistically significant CAL gain (4.0 ± 2.0 mm in the test group and 4.4 ± 1.3 mm in the control group) and PPD reduction (3.9 ± 1.4 and 4.9 ± 1.7 mm, respectively) as well as IC reduction. However, only the control group showed a significant increase in GR and crestal bone loss from baseline to the endpoint. The change in IC was -4.3 ± 2.0 mm in the test group and -4.6 ± 1.8 mm in the control group, corresponding to 66% and 64.5% intrabony fill, respectively. All evaluated parameters showed comparable changes between the two groups, with no evidence of clinically meaningful differences. CONCLUSIONS:GTR combined with OTM resulted in similar clinical endpoint parameters after 9 months of healing compared with GTR alone. This clinical result confirms the histological findings (Part I article) that early initiation of OTM is feasible.

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.

Background Traditional cigarette consumption is decreasing because of global prohibitions, while heated tobacco products are increasing in popularity, particularly among younger generations. The objective of our study was to examine the clinical and radiographic periodontal parameters and gingival crevicular fluid (GCF) levels of traditional cigarette smokers (CS), heated tobacco product users (HTP), and non-smokers (NS). Methods Demographic data of 90 patients were collected using a questionnaire that included age, gender, education, oral hygiene habits, duration, and daily frequency of smoking. Clinical parameters (full mouth plaque index (PI), bleeding on probing (BOP), probing pocket depth (PPD) were recorded during a clinical examination. Marginal bone loss (MBL) was evaluated using digital periapical radiographs. GCF volume was assessed with Periotron 8000. Results There was no clinically relevant MBL in either of the groups. CS had significantly higher PI compared to NS (p = 0.0018). While no significant differences were found in the mean percentage of BOP (p = 0.28) or the mean PPD, CS and HTP had significantly higher numbers of pockets with PPD ≥ 4 mm, PPD ≥ 4 mm and BOP + and PPD = 3 mm and BOP+ than NS (p < 0.05). HTP had significantly higher GCF volume than NS (p = 0.0138). Conclusions The periodontal parameters of HTP were comparable to those of CS, whereas NS exhibited the most favourable parameters. Longitudinal studies are required in future research to evaluate the impact of HTPs on periodontal health.

AIM:To histologically evaluate the healing of intrabony periodontal defects treated with guided tissue regeneration (GTR), if it is combined with orthodontic tooth movement (OTM) or used as a sole treatment. MATERIALS AND METHODS:Twenty subjects requiring regenerative periodontal therapy and OTM were treated with the use of extended, coronally advanced flaps according to the GTR techniques with the utilization of deproteinized bovine bone mineral (DBBM) particles. Patients either received early initiation of OTM (test) or had their teeth splinted (control) after the surgical intervention. Re-entry procedures were scheduled 9 months postoperatively to obtain a biopsy from the previous defect sites. The primary outcome variable comprised histological and histomorphometric analysis. RESULTS:Control group cases (n = 9) revealed nice embedding of graft particles into newly formed bone, which were predominantly present in the central and apical third of the biopsy samples. The coronally located DBBM was more often encapsulated in the connective tissue. Test samples (n = 10), both at the tension and pressure sites, demonstrated incorporation of a reduced graft ratio into newly formed bone. Ongoing bone formation and the presumably orthodontic-induced remodeling also interfered with the bone substitute material. Histomorphometry showed a distribution of 17.4% versus 33.9% new bone (p = 0.011), 33.2% versus 16.3% graft ratio (p = 0.001) and 49.4% versus 49.7% soft tissue components (p = 0.74) in the control versus test groups, respectively. CONCLUSIONS:Early initiation of tooth movement does not appear to adversely affect periodontal bone healing. A pronounced graft reduction and new bone formation in test patients, compared to those in controls, occurred presumably due to the effects of orthodontic-induced bone remodeling.

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.

BACKGROUND:This Consensus Workshop dealt with diagnostic methodologies in the context of surveillance, screening, assessment of stage and grade, prognosis, monitoring and prediction of periodontal status. Several elements provided the impetus for the workshop, including the limited quality of available research on diagnostic tests, the rapid development of new technologies, the implementation of the 2018 classification and the declarations of the World Health Organisation on diagnosis and oral health. AIM:To update and evaluate the evidence on diagnostic methods, considering recent advances in knowledge and the implementation of the 2018 classification. METHODS:The European Workshop Committee of the European Federation of Periodontology guided the development of a consensus report after commissioning eight systematic reviews within three working groups. The reviews were discussed during the in-person consensus meeting involving 70 participants from 21 different countries. RESULTS:Working Group 1 discussed innovations in traditional diagnostic approaches, justified manual probing as the reference standard and assessed the value of image-based methods. Working Group 2 analysed diagnostic tests based on microbial and host biomarkers and genetic diagnostic tests. Working Group 3 covered emerging technologies to be used within dental and non-dental clinical settings, focusing principally on the impact of questionnaire-based assessments and artificial intelligence systems (AIS) in interpreting different data modalities. CONCLUSION:Although manual periodontal probing is firmly established as the reference standard, additional approaches based on imaging, biomarkers, host genetics, questionnaires and the development of emerging applied data science methods (e.g., AIS) are increasingly integrated in periodontal diagnostics.

Background: Ensuring a minimum peri-implant keratinized mucosa width (PIKM-W) is critical for maintaining dental implant health, as inadequate PIKM-W is associated with increased risks of plaque accumulation, mucosal inflammation, and peri-implantitis. While epithelialized connective tissue grafts (ECTGs) are considered the gold standard for soft tissue augmentation, they often lead to significant patient morbidity. Xenogeneic dermal matrices (XDMs) offer a less invasive alternative, but are prone to shrinkage, particularly in the mandible. The aim of this study was to evaluate a new surgical method to overcome these limitations with the combination of a narrow band of ECTG (autogenous strip graft, ASG) and an XDM to augment the PIKM-W in the posterior mandible. Methods: Twelve patients with a PIKM-W of less than 2 mm in the mandible underwent peri-implant soft tissue augmentation using this combined approach. Changes in the PIKM-W were measured preoperatively; immediately postoperatively; and at 1, 3, 6, 9, and 12 months. Graft remodeling (shrinkage or contraction) and PIKM thickness (PIKM-T) were also evaluated over time. Results: Preoperatively, the mean PIKM-W was 0.39 ± 0.40 mm and the PIKM-T was 1.36 ± 0.43 mm. At 6 months, the mean PIKM-W was 4.93 ± 0.98 mm and the PIKM-T was 2.88 ± 0.80 mm, with shrinkage of 39.2 ± 14.1%. By 12 months, the mean PIKM-W stabilized at 4.58 ± 1.28 mm and the PIKM-T stabilized at 2.83 ± 0.65 mm, with shrinkage of 42.2% ± 16.8%. Conclusions: There were statistically significant differences in clinical parameters between the baseline and 6 and 12 months (p < 0.05). This technique demonstrated the potential for stable augmentation of PIKM-W and PIKM-T over time, with manageable shrinkage. However, further studies with larger sample sizes are needed to confirm its clinical efficacy as an alternative for mandibular keratinized mucosa augmentation around implants.

Background: The predictability of regenerative outcomes in non-contained intrabony periodontal defects remains limited. Autogenous tooth bone grafts (ATB) may represent a biologically active and osteoconductive scaffold with minimal residual graft material. This study evaluated the clinical and radiographic outcomes of ATB combined with enamel matrix derivative (EMD) in intrabony defects. Methods: Nine systemically healthy patients (15 defects) were treated with ATB + EMD in a retrospective proof-of-concept design. Clinical parameters-probing pocket depth (PPD), clinical attachment level (CAL), and gingival recession (GR)-were recorded at baseline and 6 months. Radiographic changes in defect depth and width were also assessed. Statistical significance was set at p < 0.05. Results: Mean PPD decreased from 7.73 ± 0.96 mm to 3.87 ± 0.74 mm (p < 0.001), and CAL improved from 9.20 ± 1.47 mm to 5.53 ± 1.36 mm (p < 0.001). GR changes were not significant. Radiographically, mean defect depth and width were reduced from 3.81 ± 1.59 mm and 2.56 ± 0.75 mm to 0.72 ± 1.08 mm and 0.44 ± 0.70 mm, respectively (p < 0.001). Conclusions: The combination of ATB and EMD yielded substantial clinical and radiographic improvements in intrabony periodontal defects. These findings suggest that autogenous tooth bone grafts may serve as a reliable biologically active scaffold for regenerative periodontal surgery. This is the first study evaluating the combination of EMD and ATB. Within the study limitations, ATB + EMD demonstrated promising regenerative potential, warranting future controlled clinical trials.

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.

Objectives: This case series aimed to assess the efficacy of a novel horizontal ridge augmentation modality using histology. Combinations of "sticky bone" and tenting screws without autologous bone were used as augmentative materials. Method and materials: Five individuals presenting healed, atrophic, partially edentulous sites that required horizontal bone augmentation before implant placement were enrolled. Patients underwent the same augmentation type and 5 months of postoperative reentry procedures. The first surgery served as implant site development, whereas the biopsy and corresponding implant placement were performed during reentry. The bone was qualitatively analyzed using histology and histomorphometry and quantitatively evaluated using CBCT. Results: Four individuals healed uneventfully. Early wound dehiscence occurred in one case. Histology showed favorable bone substitute incorporation into the newly formed bone and intimate contact between de novo bone and graft material in most cases. Histomorphometry revealed an average of 48 +/- 28% newly formed bone, 19 +/- 13% graft material, and 33 +/- 26% soft tissue components. The CBCTbased mean alveolar ridge horizontal increase was 3.9 +/- 0.6 mm at 5 months postoperatively. Conclusions: The described augmentation method appears suitable for implant site development resulting in favorable bone quality according to histology. However, clinicians must accommodate 1 to 2 mm of resorption in augmentative material width at the buccal aspect. (Quintessence Int2024;55:314-326; doi:10.3290/j.gi.b5104947)

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.

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.

Reconstruction of sufficient buccal peri-implant keratinised mucosa width (PIKM-W) is reported to reduce the symptoms of peri-implantitis. In order to reduce the drawbacks of autogenous graft harvesting, we investigated a novel porcine dermal matrix (XDM, mucoderm®) using a modified surgical technique for augmentation of PIKM-W. Twenty-four patients were recruited with insufficient (<2 mm) PIKM-W. After split thickness flap preparation, the XDM was trimmed, rehydrated and tightly attached to the recipient periosteal bed using modified internal/external horizontal periosteal mattress sutures via secondary wound healing. Change of the PIKM-W and dimension of the graft remodelling were evaluated at 6 and 12 months postoperatively. The mean PIKM-W changed from 0.42 ± 0.47 to 3.17 ± 1.21 mm at 6 M and to 2.36 ± 1.34 mm at 12 M in the maxilla and from 0.29 ± 0.45 mm to 1.58 ± 1.44 mm at 6 M and to 1.08 ± 1.07 mm at 12 M in the mandible. Graft dimensions decreased by 67.7 ± 11.8% and 81.6 ± 16.6% at 6 M, and continued to 75.9 ± 13.9% and 87.4 ± 12.3% at 12 M, in the maxilla and mandible, respectively. Clinical parameters showed statistically significant intra- and intergroup differences between the baseline and 6 and 12 months (p < 0.05). The present technique using the XDM was safe and successfully reconstructed PIKM-W in both arches. The XDM alone seems to be a suitable alternative to autograft for PIKM-W augmentation in the maxilla.

Guided bone regeneration (GBR) requires a tension-free flap without damaging the collateral circulation in order to secure better surgical outcomes. Topographic knowledge regarding the neurovascular bundles in the posterior aspect of the mandible can prevent complications during lingual flap design. The lingual branch (LB) of the inferior alveolar or maxillary arteries is not sufficiently illustrated or described in the literature. Nevertheless, it has an intimate relationship with the lingual nerve (LN) during ridge augmentation and implant-related posterior mandible surgery. Therefore, this study aimed to clarify the morphology and topography of the LB related to GBR surgeries. In the present human cadaveric study, the LB was analyzed in 12 hemimandibles using latex injection and corrosion casting. Two types of LB were identified based on their origin and course. The LB was found in a common connective tissue sheath close to the LN. The LB assembled several anastomoses on the posterior lingual aspect of the mandible and retromolar area. The LB acted as an anatomical landmark in identifying LN at the posterior lingual aspect of the mandible.

Abstract Background Peri-implant soft tissue corrections are often indicated following alveolar ridge augmentation, due to the distortion of the keratinized mucosa at the area of augmentation. The objective of the current study was to evaluate the dimensional soft tissue changes following horizontal guided bone regeneration (GBR) utilizing 3D digital data. Methods 8 mandibular surgical sites with horizontal alveolar ridge deficiencies were treated utilizing a resorbable collagen membrane and a split-thickness flap design. Baseline and 6-month follow-up cone-beam computed tomography (CBCT) scans were reconstructed as 3D virtual models and were superimposed with the corresponding intraoral scan. Linear changes of supracrestal vertical- horizontal soft tissue alterations were measured in relation to the alveolar crest at the mesial- middle- and distal aspect of the surgical area. Soft tissue dimensions were measured at baseline and at 6-month follow-up. Results Preoperative supracrestal soft tissue height measured midcrestally averaged at 2.37 mm ± 0.68 mm, 2.37 mm ± 0.71 mm and 2.64 mm ± 0.87 mm at the mesial-, middle- and distal planes. Whereas postoperative supracrestal soft tissue height was measured at 2.62 mm ± 0.72 mm, 2.67 mm ± 0.67 mm and 3.69 mm ± 1.02 mm at the mesial, middle and distal planes, respectively. Supracrestal soft tissue width changed from 2.14 mm ± 0.72 mm to 2.47 mm ± 0.46 mm at the mesial, from 1.72 mm ± 0.44 mm to 2.07 mm ± 0.67 mm and from 2.15 mm ± 0.36 mm to 2.36 mm ± 0.59 mm at the mesial, middle and distal planes, respectively. Additionally the buccal horizontal displacement of supracrestal soft tissues could be observed. Conclusions The current study did not report significant supracrestal soft tissue reduction following horizontal GBR with a split-thickness flap. Even though there was a slight increase in both vertical and horizontal dimensions, differences are clinically negligible. Trail registration The trail was approved by the U.S. National Library of Medicine (www.clinicaltrials.gov); trial registration number: NCT05538715; registration date: 09/09/2022.