A U-Net Approach to Apical Lesion Segmentation on Panoramic Radiographs

The purpose of the paper was the assessment of the success of an artificial intelligence (AI) algorithm formed on a deep-convolutional neural network (D-CNN) model for the segmentation of apical lesions on dental panoramic radiographs. A total of 470 anonymized panoramic radiographs were used to progress the D-CNN AI model based on the U-Net algorithm (CranioCatch, Eskisehir, Turkey) for the segmentation of apical lesions. The radiographs were obtained from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Eskisehir Osmangazi University. A U-Net implemented with PyTorch model (version 1.4.0) was used for the segmentation of apical lesions. In the test data set, the AI model segmented 63 periapical lesions on 47 panoramic radiographs. The sensitivity, precision, and F1-score for segmentation of periapical lesions at 70% IoU values were 0.92, 0.84, and 0.88, respectively. AI systems have the potential to overcome clinical problems. AI may facilitate the assessment of periapical pathology based on panoramic radiographs.

Convolutional Neural Networks For Apical Lesion Segmentation From Panoramic Radiographs

Convolutional neural networks (CNNs) have rapidly emerged as one of the most promising next-generation artificial intelligence (AI) in the field of medical and dental researches, which can further provide an effective diagnostic methodology allowing for detection of diseases at early age. This study was, thus, aimed to evaluate performances for apical lesion segmentation from panoramic radiographs using two CNN algorithms including U-Net and FPN. A total of 1000 panoramic radiographs showing apical lesions were separated into training (n = 800, 80%), validation (n = 100, 10%), and test (n = 100, 10%) dataset, respectively. These datasets were further incorporated to construct CNN models using two algorithms, respectively. The performances of identifying apical lesions were evaluated after calculating precision, recall, and F1-score from both CNN models. Both U-Net and FPN algorithms provided considerably good performances in identifying apical lesions in panoramic radiographs.

Effectiveness of MTA apical plug in dens evaginatus with open apices

Background The present study aims to evaluate the effectiveness of mineral trioxide aggregate (MTA) application in treating dens evaginatus affected teeth with apical lesions and open apices using haemostatic collagen membrane to prevent the apical extrusion of MTA. Methods Twelve patients with 14 dens evaginatus affected teeth with apical lesions and open apices were treated with MTA apical plug and haemostatic collagen membrane. Clinical symptoms of subjective pain, pain of palpation, percussion, sinus tract, and the apical lesions' radiographic parameter were recorded at every 3-month interval up to 9 months after treatment. Paired t-test or Wilcoxon signed-rank test was used for statistical analysis with P < 0.05 as the threshold for considering results to be statistically significant. Results No patient experienced clinical symptoms 3 months after endodontic treatment. In addition, there was a significant difference in the dimensions of the apical lesions' before compared to 3 months after endodontic treatment. Conclusions The combination of MTA apical plug and haemostatic collagen membrane effectively treated dens evaginatus affected teeth with apical lesions, and open apices.

Detection of Dental Apical Lesions Using CNNs on Periapical Radiograph

Apical lesions, the general term for chronic infectious diseases, are very common dental diseases in modern life, and are caused by various factors. The current prevailing endodontic treatment makes use of X-ray photography taken from patients where the lesion area is marked manually, which is therefore time consuming. Additionally, for some images the significant details might not be recognizable due to the different shooting angles or doses. To make the diagnosis process shorter and efficient, repetitive tasks should be performed automatically to allow the dentists to focus more on the technical and medical diagnosis, such as treatment, tooth cleaning, or medical communication. To realize the automatic diagnosis, this article proposes and establishes a lesion area analysis model based on convolutional neural networks (CNN). For establishing a standardized database for clinical application, the Institutional Review Board (IRB) with application number 202002030B0 has been approved with the database established by dentists who provided the practical clinical data. In this study, the image data is preprocessed by a Gaussian high-pass filter. Then, an iterative thresholding is applied to slice the X-ray image into several individual tooth sample images. The collection of individual tooth images that comprises the image database are used as input into the CNN migration learning model for training. Seventy percent (70%) of the image database is used for training and validating the model while the remaining 30% is used for testing and estimating the accuracy of the model. The practical diagnosis accuracy of the proposed CNN model is 92.5%. The proposed model successfully facilitated the automatic diagnosis of the apical lesion.

Evaluation of the effect of periapical lesions and other odontogenic conditions on maxillary sinus mucosal thickness characteristics and mucosal appearance: A CBCT study

Background. This retrospective study aimed to investigate the effect of various dental and maxillary sinus variables on maxillary sinus mucosal thickness (MT). The variables included periodontal bone loss (PBL), periapical status, dental restorations of posterior maxillary teeth, and the distance from the root apices to the sinus mucosa. Methods. Cone-beam computed tomography (CBCT) images of the maxillary sinuses (n=600) in 300 patients were examined. The sinus MT and the distance of the roots from maxillary sinuses were measured. Apical lesions of the roots, PBL, and situations of adjacent teeth were recorded. The relationships between these conditions and MT and characterization of MT were evaluated. The Kruskal–Wallis H test was used to compare groups due to the non-normal distribution of the data. The relationship between categorical variables was analyzed using chi-squared test. Results. There was a significant correlation between maxillary sinus MT and periapical lesions, PBL, and restorations (P<0.05). MT increased as the apical lesions of premolar teeth enlarged (P<0.05, P=0.022). MT increased in cases of mild PBL of molar teeth (P=0.041). Conclusion. In this retrospective study, the MT significantly increased in patients with periapical lesions, inadequate endodontic treatment, increased PBL, and inadequate dental restorations.

Nonsurgical Treatment Outcomes and Prognostic Factors for Cases with Lesions of Endodontic Origin in a Private Practice

Aim: The prognosis of the healing of an apical lesion is extremely important for the treatment decision for tooth retention or implantation. In several studies, the presence of an apical lesion was shown to be a significant factor in both primary treatment and non-surgical retreatment. The aim of the present study was the retrospective investigation of the prognosis of the healing of bony apical lesions of teeth, which were treated endodontically. The evaluation contained various clinical parameters that can influence the success of the root canal treatment. Materials and Method: 62 teeth were treated in 52 patients during the study period. The treatment was carried out by a specialist in endodontics with the aid of the dental surgical microscope and a two-stage procedure. Two certified examiners assessed the radiological results after three to 72 months. Preoperative and postoperative information related to potential prognostic factors was evaluated. Results: Results of the 62 apical lesions, 82.3% (examiner 1) - 88.75% (examiner 2) were classified as healed. Of all the prognostic factors analyzed, none showed a significant influence on the treatment success. The success rate of the present study was in the range of comparable studies. Conclusions: The apical lesion can be treated with relatively high success rates if general micro-endodontic procedures are followed.

Systemic and Extraradicular Bacterial Translocation in Apical Periodontitis

Apical periodontitis is an inflammatory disease of microbial etiology. It has been suggested that endodontic bacterial DNA might translocate to distant organs via blood vessels, but no studies have been conducted. We aimed first to explore overall extraradicular infection, as well as specifically by Porphyromonas spp; and their potential to translocate from infected root canals to blood through peripheral blood mononuclear cells. In this cross-sectional study, healthy individuals with and without a diagnosis of apical periodontitis with an associated apical lesion of endodontic origin (both, symptomatic and asymptomatic) were included. Apical lesions (N=64) were collected from volunteers with an indication of tooth extraction. Intracanal samples (N=39) and respective peripheral blood mononuclear cells from apical periodontitis (n=14) individuals with an indication of endodontic treatment, as well as from healthy individuals (n=14) were collected. The detection frequencies and loads (DNA copies/mg or DNA copies/μL) of total bacteria, Porphyromonas endodontalis and Porphyromonas gingivalis were measured by qPCR. In apical lesions, the detection frequencies (%) and median bacterial loads (DNA copies/mg) respectively were 70.8% and 4521.6 for total bacteria; 21.5% and 1789.7 for Porphyromonas endodontalis; and 18.4% and 1493.9 for Porphyromonas gingivalis. In intracanal exudates, the detection frequencies and median bacterial loads respectively were 100% and 21089.2 (DNA copies/μL) for total bacteria, 41% and 8263.9 for Porphyromonas endodontalis; and 20.5%, median 12538.9 for Porphyromonas gingivalis. Finally, bacteria were detected in all samples of peripheral blood mononuclear cells including apical periodontitis and healthy groups, though total bacterial loads (median DNA copies/μL) were significantly higher in apical periodontitis (953.6) compared to controls (300.7), p&lt;0.05. Porphyromonas endodontalis was equally detected in both groups (50%), but its bacterial load tended to be higher in apical periodontitis (262.3) than controls (158.8), p&gt;0.05; Porphyromonas gingivalis was not detected. Bacteria and specifically Porphyromonas spp. were frequently detected in endodontic canals and apical lesions. Also, total bacteria and Porphyromonas endodontalis DNA were detected in peripheral blood mononuclear cells, supporting their plausible role in bacterial systemic translocation.

Association between Maxillary Posterior Teeth Periapical Odontogenic Lesions and Maxillary Sinus Mucosal Thickening: A 3D Volumetric Computed Tomography Analysis

Background: The detailed relationship between apical periodontitis and maxillary sinus mucosal thickening is still unknown. The aim of this study was to evaluate the association between maxillary posterior teeth periapical odontogenic lesions and maxillary sinus mucosal (MSM) thickening by using volumetric 3D CT analysis. Methods: A total of 83 subjects with apical periodontitis around maxillary posterior teeth and maxillary sinus mucosal thickening were selected. 3D models of maxillary sinus mucosa and apical lesions were reconstructed from CT, and their volume, mean diameter were calculated. Results: Mean MSM thickening was 8.81 ± 12.59 mm with an average volume of 5092.58 ± 7435.38 mm3. Men had higher MSM thickening than women. Mean diameter of apical lesion was 5.94 ± 2.68 mm; average volume was 200.5 ± 197.29 mm3. Mean distance between MSM and apical lesion was 1.83 ± 2.07 mm. Mucosal volume was the highest in the S1 and D1 configuration and the lowest in R3. Reducing the distance between apical lesion and MSM by each millimetre, the volume of MSM increases by 759.99 mm3. Conclusions: Volumetric CT analysis is a circumstantial method to evaluate the association between maxillary posterior teeth apical periodontitis and MSM thickening. This relationship is not related to the size of the apical lesion but depends on their anatomical position and the distance from the maxillary sinus mucosa.

Persistent Apical Periodontitis: Bacterial Taxonomic Analysis and Treatment Through Intentional Replantation

Introduction: The microorganisms own different resistance mechanisms that allow them to resist the chemo-mechanical cleanliness of root canal and antibiotic therapies causing the persistence of apical lesions. Methods: This clinical case describes a male patient diagnosed with pulp necrosis in the right lower central incisor due to trauma, which developed apical periodontitis manifesting itself extra orally. Root canal treatment along with antibiotic therapy was performed, but because the infectious process persisted, endodontic retreatment and a new antibiotic therapy were carried out, however, the clinical evolution was not favorable. For this reason, the intentional replantation was chosen as the outright treatment, performing apicectomy and curettage of the periapical lesion, from which the isolation and taxonomic study of microorganisms were carried out, with the respective antibiogram. Results: In the 10-day clinical follow-up, the extraoral infectious process disappeared almost completely and 6 months later, a complete repair of the bone tissue was observed on the tomography. Conclusion: A better understanding of the persistence of apical periodontitis was achieved by taxonomic identification of bacteria and the intentional replantation allowed to remove the apical biofilm gaining an excellent wound healing.