Panoramic Radiographs Research Articles

AI-aided diagnosis of periodontitis in oral X-ray images

This study explored the construction and application of efficient deep-learning models to assist the diagnosis of periodontitis in panoramic radiographs. A periodontitis auxiliary diagnosis dataset was constructed in collaboration with the Peking University School of Stomatology. The dataset included 238 panoramic images, covering different stages of healthy teeth and periodontitis. The Labelme annotation tool was used to label tooth instances, alveolar bone contours, and the cemento-enamel junction. A Mask R-CNN model was developed for tooth segmentation, and a U-Net model was developed for segmenting alveolar bone contours and cemento-enamel junctions. Based on the results of tooth instance segmentation, principal component analysis was utilized to fit the direction of the dental long axis. The minimal bounding rectangle of the tooth prediction mask was used to determine the length of the tooth axis. The proportion of alveolar bone loss was calculated based on the distance of the cemento-enamel junction and the alveolar bone level along the dental long axis. An evaluation was conducted on 20 panoramic images comprising 496 teeth. The study achieved an accuracy rate of 90.73% in the staging of periodontitis.

Oral foci of infection and their relationship with hospital stay after haematopoietic cell transplantation

PurposeOral focus screening is recommended before HCT (haematopoietic cell transplantation). Acute foci are generally treated pre-HCT. However, it is unclear whether chronic foci should be treated pre-HCT. This study aimed to evaluate the association between number of foci and early post-HCT morbidity and mortality.MethodsPatients who received an oral screening pre-HCT at Radboudumc between 2013 and 2023, with a recent panoramic radiograph, were included. Foci were defined as teeth or implants with deep pockets, furcation radiolucencies, periapical radiolucencies, deep caries, partial eruption or retained roots. Dental interventions were provided pre-HCT if deemed necessary and possible. Hospital length of stay (LOS), mortality and oral exacerbations were assessed in the first hundred days post-HCT. Hospital LOS was log-transformed to normalize its skewed distribution. Multivariate regression analyses were performed.ResultsFive hundred patients were included (median age 58 years, 37% female, 56% allogeneic). Four acute foci in two patients remained untreated pre-HCT. Forty-eight percent had at least one untreated chronic focus pre-HCT (mostly furcation radiolucencies and post-endodontic periapical lesions). Mean LOS was 22 days; 20 patients died, and four patients had an oral exacerbation before HCT day + 100. After adjustment for conditioning intensity, age, socioeconomic status and number of teeth, HCT recipients with ≥ 3 foci had five additional days in the hospital compared to those without foci (ratio of means 1.21; 95% CI 1.00 – 1.46). The number of foci was not associated with early post-HCT mortality.ConclusionThe presence of ≥ 3 oral foci is associated with extended hospital LOS in the first hundred days post-HCT.

Carotid calcifications in panoramic radiographs can predict vascular risk.

Carotid artery calcification (CAC) is occasionally detected in panoramic radiographs (PR). Bilateral vessel-outlining (BVO) CACs are independent risk markers for future vascular events and have been associated with large plaque area. If accounting for plaque area, BVO CACs may no longer be an independent risk marker for vascular events. The aim of this study was to explore the association between BVO CACs and vascular events and its relationship with carotid ultrasound plaque area. In this cohort study we prospectively included 212 consecutive participants with CACs detected in PR that were performed to plan and evaluate odontologic treatment. Of these 212, 43 (20%) had BVO CACs. Plaque area was assessed with ultrasound at baseline. Primary outcome was major adverse cardiovascular events (MACE) during follow-up. Vessel-outlining CAC was associated with larger plaque area on the same side (p = 0.03) and BVO CACs were associated with larger total plaque area (both sides summed) than other CAC features (p = 0.004). Mean follow-up was 7.0 years and 72 (34%) participants had more than one MACE. In bivariable analyses, both BVO CACs (HR 2.5, p < 0.001) and total plaque area (HR 1.8 per cm2, p = 0.008) were associated with MACE. When entering BVO CACs, plaque area and other relevant co-variates in a multivariable model, BVO CACs were virtually unchanged (HR 2.4, p = 0.001), but total plaque area was no longer significant (HR 1.0, p = 0.92). Present results support the contention that BVO CACs are a stronger predictor for future vascular events than carotid ultrasound plaque area.

Congenitally missing permanent canines in a sample of Chinese population: a retrospective study

BackgroundCongenitally missing permanent canines (CMPC) have a significant impact on function and aesthetics. The prevalence is low, and the availability of rigorous studies on this issue in China is limited. This study was designed to investigate the prevalence and distribution of CMPC in patients and concomitant anomalies. Additionally, we aimed to compare the prevalence of CMPC between two age groups.MethodsA total of 10,447 patient’s panoramic radiograph (PR) images from August 2021 to December 2023 were reviewed and data regarding the location and number of CMPCs were recorded. Age and gender were obtained from the clinical records. Additionally, concomitant anomalies such as persistent primary canines, congenitally missing other permanent teeth, supernumerary teeth and microdontia were also recorded in patients with CMPC. 10,447 patients were divided into two groups: group A (< 121 months of age) and group B (≥ 121 months of age) to record the number of patients with CMPC. The data were presented as counts (n) and percentages (%), and statistically analysed using the Chi-square test.ResultsThe average age of patients with CMPC was 9.2 years, with a prevalence of 0.69% (n = 72). The difference between genders was not statistically significant (p = 0.950). The prevalence of CMPC in group B (1.08%, 26/2400) was significantly greater than that in group A (0.57%, 46/8047) (p = 0.008). 89.42% (93/104) of the missing permanent canines had visible primary canines in patients. CMPC were more likely to occur in the maxilla (91.67%) than in the mandible (6.94%) (p<0.001). No significant difference was found between the left and right sides (p = 0.844). With respect to concomitant anomalies among those with CMPC, 22 patients had 58 congenitally other permanent teeth missing, 3 patients had 3 supernumerary teeth, and 12 maxillary lateral incisors from 7 patients presented with microdontia.ConclusionsThe prevalence of CMPC was 0.69%. CMPC were more likely to occur in the maxilla in the presence of persistent primary canines and were not influenced by gender or side. Early panoramic radiographs can improve the detection rate of CMPC, thereby facilitating prompt intervention and timely management.

Mandibular Actinomyces Osteitis Associated with Florid Cemento-Osseous Dysplasia

Introduction: Actinomycosis is a rare chronic suppurative granulomatous infection caused by actinomyces. The Florid cemento-osseous dysplasia (FCOD) is a benign fibro-osseous lesion. We report a case of simultaneous association of these two entities with the use of PRF for the first time in this context. Case Report: A 59-year-old female with no medical history was received in our clinic for painful swelling on the right mandible. On clinical examination, we noticed a facial asymmetry caused by the swelling and bone exposure with pus on the right mandibular ridge. The panoramic radiography showed right and left posterior mandibular opacities. On the cone beam reconstructions, we noted a hyperdense posterior right mandibular image surrounded by a hypodense border and a hyperdense posterior left mandibular image surrounded by a hypodense border, in contact with the apices of tooth 36. Based on the clinical, radiographic and pathological findings, the present case was diagnosed as mandibular actinomyces osteitis associated with florid cemento-osseous dysplasia. The treatment consisted of surgical excision of the lesion, filling of the defect with PRF and prescription of antibiotics. Conclusion: Despite its rarity, practitioners should be aware of the possibility of the coexistence of these two entities simultaneously. Thus, they can initiate the appropriate treatment.

Detection of C-shaped mandibular second molars on panoramic radiographs using deep convolutional neural networks.

The C-shaped mandibular second molars (MSMs) may pose an endodontic challenge. The aim of this study was to develop a convolutional neural network (CNN)-based deep learning system for the diagnosis of C-shaped MSMs on panoramic radiographs. Panoramic radiographs and cone beam computed tomographic (CBCT) images were collected from a hospital in China and subsequently divided into two groups. In Group A, conventional panoramic images and CBCT images were derived from the same patients (n = 730 individuals), and the dataset consisted of conventional panoramic image patches of 1453 MSMs. In Group B (n = 610 individuals), the patients underwent CBCT examinations in the absence of available panoramic images; CBCT images were acquired and utilized to generate simulated panoramic images, and the dataset consisted of image patches of 1211 MSMs. Five pretrained CNN networks (ResNet-101 and - 50, DenseNet-121 and - 161, and Inception-V3) were utilized for the classification of C-shaped and non-C-shaped MSMs. Finally, the networks trained on the Group B dataset were tested on the Group A dataset. The diagnostic performance of each model was evaluated using receiver operating characteristic (ROC) curve analysis, and the CBCT images were taken as the gold standard. The results were compared with those achieved by three dental professionals. In Group A, all five networks exhibited satisfactory diagnostic performance, with AUC values ranging from 0.875 to 0.916 and accuracies ranging from 81.8 to 86.7%. No statistical differences were detected among the five CNNs. Notably, the models trained with Group B dataset (CBCT-generated panoramic images) achieved enhanced performance as tested on Group A dataset. The AUC values reached 0.984-0.996, and the accuracies ranged between 94.5% and 98.1%. CNNs outperformed dental professionals in classification performance, and the AUC values achieved by dental specialist, novice dentist, and dental graduate student were only 0.806, 0.767 and 0.730, respectively. CNN-based deep learning system demonstrated higher accuracy in the detection of C-shaped MSMs on panoramic radiographs compared to dental professionals. CBCT-generated panoramic images can serve as a substitute for conventional panoramic images in the training of CNN models when the quantity and quality of conventional panoramic image dataset is insufficient. CNN-based deep learning models have demonstrated significant potential in assisting dentists with the identification of C-shaped MSMs on panoramic radiographs, which facilitating more effective, efficient and safer dental treatment.

The Occurrence and Outcomes of Cemento-Osseous Dysplasias (COD) in the Jaw Bones of the Population of Lower Silesia, Poland.

Background: Cemento-osseous dysplasias (CODs) are rare lesions of the jawbone. Their occurrence, localization, type, size, and shape can vary between cases. This fibro-osseous lesion is typically found in the jaw near tooth-bearing areas and is often asymptomatic, discovered incidentally, and may be associated with the periapical region of the teeth. In rare cases, COD can lead to secondary bone osteomyelitis. Currently, there is limited information in the literature on the occurrence and characteristics of COD. This paper's main aim was to focus on the authors' COD experience in the lower Silesian area. Methods: A retrospective evaluation of radiographies (RTG-Panx, cone-beam computed tomography (CBCT)) was conducted on patients treated, diagnosed, or consulted by the authors. A statistical correlation analysis was made to establish any relationship within the gathered data. Results: COD is predominantly an incidental finding in the mandibular bone near tooth apices. It is most commonly diagnosed in females. Both CBCT and panoramic radiographies are generally sufficient for diagnosing the lesion. COD rarely requires treatment. Conclusions: COD lesions are mostly discovered incidentally during routine radiographies or cone-beam computed tomography (CBCT) scans. In most cases, clinical and radiological monitoring is sufficient, along with evaluating the teeth's response to cold stimuli and assessing the surrounding bone structures. Biopsies or tooth extractions are seldom necessary. When oral hygiene is well-maintained and no periapical inflammation is present, COD lesions typically remain asymptomatic.

Radiographic Assessment of Root/Crown Ratio and Short Root Anomaly: A Retrospective Study in Chinese Population.

Research suggested that racial and gender differences may exist in tooth root development and the prevalence of short root anomaly (SRA). However, data on Asian and specifically Chinese populations were limited. This retrospective study aimed to evaluate the prevalence of SRA and the characteristics of the root-to-crown ratio (R/C ratio) within the Chinese population. Modified Lind's criteria were used to measure the crown and root lengths in permanent dentition. A total of 27 142 teeth from 1000 subjects were evaluated using panoramic radiographs. Fisher's exact test was employed to analyse gender differences in SRA. Paired-sample and independent-sample t tests were used to assess the characteristics of R/C ratios. SRA was observed in 27 patients, with a prevalence of 2.7% and a tooth prevalence of 0.309%. Females had a significantly higher prevalence of SRA compared to males (p < 0.01). SRA was found exclusively in incisors (83.72%) and premolars (16.28%), with the maxillary central incisor being the most commonly affected tooth. Additionally, there were statistical differences in the R/C ratio based on gender and jaw position in the normal groups. The highest R/C ratios were observed in the mandibular second premolars, while the maxillary central incisors had the lowest ratios. SRA was relatively common in the Chinese population, and clinicians should be aware of its presence. It was more frequently observed in females and shows specificity in tooth position, with the maxillary central incisor being the most commonly affected tooth. Our study provides valuable insights for the early diagnosis and treatment of SRA in the Chinese population.

The agreement of panoramic radiography with cone-beam computed tomography in classifying impacted lower third molars: a systematic review

The agreement of panoramic radiography with cone-beam computed tomography in classifying impacted lower third molars: a systematic review

Prevalence of Elongated Styloid Process in 1,000 Panoramic Radiographs of a Brazilian Population

The aim of this study was to evaluate the elongation of the styloid process’ prevalence in a population from the outback of Paraíba state, using digital panoramic radiographs, and to identify differences related to side, gender and age. This was a retrospective observational study in which 1,000 panoramic radiographs of patients over the age of 18 who met the research inclusion criteria were evaluated. The styloid process was measured from its origin, where it leaves the tympanic plate, to its Apex, being considered short when it was less than 20 mm long, normal when it was between 20–30 mm long and elongated when it was longer than 30 mm. A 32% prevalence was found, with a progressive increase related to age, greater length in males and bilateral involvement. It was concluded that around 1/3 of the population studied had an elongated styloid process. Further studies are needed to correlate the elongation of the styloid process and clinical manifestations.

An investigation of the validity of the Bedek models and Cameriere-European formula used in dental age prediction in Turkish children

BackgroundDental age estimation is one of the most reliable methods for determining age, commonly used for forensic, criminal, and anthropological purposes. The purpose of this study was to assess and compare the precision of the Bedek models and the Cameriere-European Formula (CF) in determinating dental age in a sample of Turkish individuals.MethodsRetrospective panoramic radiographs of 1018 subjects (497 boys and 521 girls) aged 5–14 years were evaluated using the Bedek models and the CF. The differences between calculated dental age (DA) and chronological age (CA) for each sex and age group were analyzed using the paired sample t-test and the Wilcoxon signed-rank test. The accuracy of the methods used to estimate dental age was determined by calculating the mean absolute error (MAE) based on the proximity of the dental age to the chronological age.ResultsThe CF method overestimated CA by 0.1 year in the entire sample. Conversely, the Bedek models tended to overestimate CA, with the three-, four-, and seven-tooth models exhibiting the most significant difference. There was a statistically significant difference between boys and girls in the DA-CA calculation using the CF method in the entire sample. Among the Bedek models, the three- and four-tooth models had the lowest MAE in the entire sample, while the single-tooth model had the highest MAE.ConclusionThe CF method showed higher accuracy in predicting the age of children living in eastern Turkey compared to the Bedek Models.

ResNet-Transformer deep learning model-aided detection of dens evaginatus.

Dens evaginatus is a dental morphological developmental anomaly. Failing to detect it may lead to tubercles fracture and pulpal/periapical disease. Consequently, early detection and intervention of dens evaginatus are significant to preserve vital pulp. This study aimed to develop a deep learning model to assist dentists in early diagnosing dens evaginatus, thereby supporting early intervention and mitigating the risk of severe consequences. In this study, a deep learning model was developed utilizing panoramic radiograph images sourced from 1410 patients aged 3-16 years, with high-quality annotations to enable the automatic detection of dens evaginatus. Model performance and model's efficacy in aiding dentists were evaluated. The findings indicated that the current deep learning model demonstrated commendable sensitivity (0.8600) and specificity (0.9200), outperforming dentists in detecting dens evaginatus with an F1-score of 0.8866 compared to their average F1-score of 0.8780, indicating that the model could detect dens evaginatus with greater precision. Furthermore, with its support, young dentists heightened their focus on dens evaginatus in tooth germs and achieved improved diagnostic accuracy. Based on these results, the integration of deep learning for dens evaginatus detection holds significance and can augment dentists' proficiency in identifying such anomaly.

Dental dysplasia in childhood cancer survivors: a case series of permanent tooth abnormalities.

This study was performed to investigate the association of dental dysplasia with childhood cancer. We examined the occurrence of agenesis, microdontia, and enamel changes of permanent teeth in pediatric cancer survivors. Seventy-six patients with pediatric cancer and hematologic diseases were referred to our department for the first time from October 2005 to December 2019. Of these, 17 patients who presented for a checkup in our department fulfilled the study criteria and were analyzed. Clinical examinations and panoramic radiographs were performed to investigate dental dysplasia of permanent teeth. A total of 34 developmental abnormalities (18 missing teeth, 16 cases of microdontia) occurred in 5 patients. The patients' medical records were also analyzed to assess the relationships of specific types of dysplasia with the treatment duration and cumulative drug dose administered. All five pediatric cancer survivors had dental dysplasia; all five had tooth agenesis, and four had microdontia. All five patients were < 4 years of age and had undergone high-dose chemotherapy. In this study, childhood cancer survivors who received high-dose chemotherapy before age 4 years experienced the dental dysplasia, including tooth agenesis, microdontia. These findings highlight the need for careful dental monitoring and early intervention in pediatric patients undergoing high-dose chemotherapy. This research was conducted in accordance with the Declaration of Helsinki and approved by the Medical Ethics Committee of the Medical University of Kobe (protocol code No. B230066, 1 September 2023).

Evaluation of Dental Panoramic Radiographs by Artificial Intelligence Compared to Human Reference: A Diagnostic Accuracy Study.

Background/Objectives: The role of artificial intelligence (AI) in dentistry is becoming increasingly significant, particularly in diagnosis and treatment planning. This study aimed to assess the sensitivity, specificity, accuracy, and precision of AI-driven software in analyzing dental panoramic radiographs (DPRs) in patients with permanent dentition. Methods: Out of 638 DPRs, 600 fulfilled the inclusion criteria. The radiographs were analyzed by AI software and two researchers. The following variables were assessed: (1) missing tooth, (2) root canal filling, (3) endodontic lesion, (4) implant, (5) abutment, (6) pontic, (7) crown, (8) and sound tooth. Results: The study revealed very high performance metrics for the AI algorithm in detecting missing teeth, root canal fillings, and implant abutment crowns, all greater than 90%. However, it demonstrated moderate sensitivity and precision in identifying endodontic lesions and the lowest precision (65.30%) in detecting crowns. Conclusions: AI software can be a valuable tool in clinical practice for diagnosis and treatment planning but may require additional verification by clinicians, especially for identifying endodontic lesions and crowns. Due to some limitations of the study, further research is recommended.

How does the direction of region of interest selection affect the fractal dimension?

Introduction Fractal analysis (FA) is a computational method used to quantify the complex trabecular structure of bone. While FA has been widely applied in dentistry, there are challenges in standardizing the technique due to factors such as image resolution, region of interest (ROI) selection, and image processing. This study aimed to investigate the impact of the direction of ROI selection (DROIS) on fractal dimension (FD) calculations. Panoramic radiographs of 226 individuals aged 20-35 years were analyzed. ROIs were selected on the mandibular condyle, angular region, and mental region, and oriented at 0°, 22.5°, 45°, and 67.5° angles. FD was calculated using the box-counting method in ImageJ. The Friedman test and Wilcoxon signed-rank test were used for statistical analysis. The FD values differed significantly between the angled ROI groups in all three regions (Friedman test, p < 0.0001).Pairwise comparisons showed significant differences in FD between most ROI orientations, except between 22.5° and 67.5° in the angular region. DROIS is an important factor that should be considered in FA studies to ensure reliable and reproducible FD values. Appropriate methodological choices can help account for the influence of DROIS on FD calculations..

Impact of Different Orthodontic Appliances on Mandibular Condyle, Anterior Region of Mandibular, and Maxillary Sinus Using Panoramic Radiography.

BACKGROUND This retrospective study of 44 patients requiring removable functional dental appliances aimed to compare the use of a maxillary expansion device, twinblock/monoblock, face mask, and chincup on maxillary sinus dimensions, mandibular anterior region bone density (MABD), and mandibular condyle head bone formation (MCBF) using panoramic radiography. MATERIAL AND METHODS The patients were divided into 4 groups based on the treatment modalities used: group A, maxillary expansion device (n=11); group B, twinblock/monoblock (n=11); group C, face mask (n=11); and group D, chincup (n=11). MABD and MCBF were assessed using the fractal analysis method, while maxillary sinus dimensions were compared using the ImageJ program. Different groups of patients were tested by the Mann-Whitney U test, with Bonferroni correction. RESULTS Group A showed an increase in MABD, MCBF, and average maxillary sinus indentation base length (MSIL) and a decrease in average planar base length (MSPL) and maxillary sinus area (MSA) (P<0.05). Group B showed an increase in MABD, MSIL, MSPL, MSA, and MCBF (P<0.05). Group C showed an increase in MABD, MSIL, MSPL, and MCBF, with a decrease in MSA (P>0.05). Group D showed an increase in MCBF, MABD, MSIL, and MSA, with a decrease in MSPL at the end of treatment, compared with pretreatment (P<0.05). CONCLUSIONS Orthodontic treatment with different removable functional dental appliances has varying effects on the mandible and maxilla. Possible changes in the maxilla and mandible should be considered before treatments with removable functional dental appliances.

Prevalence, Occurrence, and Characteristics of Supernumerary Teeth Among the Saudi Arabian Population Using Panoramic Radiographs.

Supernumerary teeth numerical anomalies and the early diagnosis of supernumerary teeth is very important to avoid potential complications. The study aim was to determine the prevalence, occurrence, and characteristics of supernumerary teeth among the Arabian population. A retrospective radiographic study was performed using panoramic radiographs of patients attending a teaching hospital from January 2018 to December 2020. Only healthy patients with clear radiographs were included in the study, and patients with syndromes, cleft lip, and palate, and unclear radiographs were excluded from the study. The details include the patient's age and gender, supernumerary tooth number, location, orientation, and position. Only a single examiner was involved in the data collection and analysis. Overall, 38 (2%) patients were observed with 47 supernumerary teeth. Among them, 76% were males and 24% were females, with a mean age of 16.1 ± 9.7 years. Mesiodens (87%) are the common type of supernumerary tooth, and the majority of the supernumerary teeth were impacted (66%). The majority of the patients presented with a single supernumerary tooth, while 24% of the patients presented with two supernumerary teeth. Sixty percent of the supernumerary teeth were conical in morphology, followed by a tuberculate morphology. In the study population, most of the supernumerary teeth were normal in orientation. The prevalence of supernumerary teeth was 2%. Among them, the majority were observed at the anterior region of the maxillary arch with a conical shape of normal orientation. The gender-based comparison of location, orientation, morphology, eruption, and number of supernumerary teeth showed male predilection.

Knowledge and Attitudes toward Dental X-Rays among Patients at Muhimbili School of Dentistry in Tanzania

Background Dental X-rays are vital diagnostic tools in dentistry, providing critical information for treatment planning. However, patient awareness and understanding of the risks and benefits associated with dental radiography can significantly influence their attitudes toward these procedures. Method This cross-sectional study was conducted in 2008 at the Radiology Department of Muhimbili Dental School. A total of seventy patients attending the dental clinic who underwent periapical and orthopantomogram (OPG) radiography were surveyed. Data were collected using structured questionnaires designed to assess knowledge and attitudes regarding dental X-rays. Results The results revealed that 70% of participants understood the radiation risks associated with X-rays, while 75% were aware of the indications for their use. However, only 60% were familiar with the benefits of OPG. In terms of attitudes, 80% of patients agreed that X-rays are essential for diagnosis, and 85% believed their dentist should explain the necessity of X-rays. Conclusion The findings indicate that while patients at Muhimbili Dental School exhibit a moderate level of knowledge and positive attitudes toward dental X-rays, there is a need for enhanced patient education regarding the risks and benefits. Implementing educational initiatives could improve understanding and alleviate concerns related to dental radiography.

Fractal dimension, lacunarity, and bone area fraction analysis of peri-implant trabecular bone after prosthodontic loading.

To assess the structural alterations in peri-implant bone occurring 5years after prosthodontic loading in panoramic radiography (PR). PR images of 44 mandibular and 33 maxillary implants along with 42 healthy control teeth taken before and 5years after prosthodontic loading were included. Two regions-of-interest (ROI) were selected from mesial and distal surrounding bone of each implant and tooth. Then, the selected ROIs were divided to obtain three sub-ROIs (coronal, middle, and apical) on each side. A total of eight ROIs and sub-ROIs from each implant and control tooth were used for the calculations of fractal dimension (FD), lacunarity, and bone area fraction (BA/TA). The paired-sample t test was used to compare measurements before and 5years after loading (p = 0.05). Overall evaluation of 77 implants showed that FD decreased at the middle and apical peri-implant bone levels 5years after loading (p < 0.05). In mandibular implants, BA/TA decreased after loading (p < 0.05). While FD decreased at the coronal level (p = 0.022), lacunarity increased at the middle level of mandibular implants (p < 0.05). In maxillary implants, FD decreased at the middle and BA/TA decreased at the coronal level (p < 0.05). On the other hand, BA/TA increased at the apical level of maxillary implants (p = 0.016) after loading. None of the parameters revealed any difference in the control group (p > 0.05). FD and BA/TA can be used to analyze structural changes in peri-implant bone after prosthodontic loading. Additionally, FD, lacunarity and BA/TA may provide useful information about changes occurring at different levels of peri-implant bone.

Unveiling the power of artificial intelligence for image-based diagnosis and treatment in endodontics: An ally or adversary?

Artificial intelligence (AI), a field within computer science, uses algorithms to replicate human intelligence tasks such as pattern recognition, decision-making and problem-solving through complex datasets. In endodontics, AI is transforming diagnosis and treatment by applying deep learning algorithms, notably convolutional neural networks, which mimic human brain function to analyse two-dimensional (2D) and three-dimensional (3D) data. This article provides an overview of AI applications in endodontics, evaluating its use in 2D and 3D imaging and examining its role as a beneficial tool or potential challenge. Through a narrative review, the article explores AI's use in 2D and 3D imaging modalities, discusses their limitations and examines future directions in the field. AI significantly enhances endodontic practice by improving diagnostic accuracy, workflow efficiency, and treatment planning. In 2D imaging, AI excels at detecting periapical lesions on both periapical and panoramic radiographs, surpassing expert radiologists in accuracy, sensitivity and specificity. AI also accurately detects and classifies radiolucent lesions, such as radicular cysts and periapical granulomas, matching the precision of histopathology analysis. In 3D imaging, AI automates the segmentation of fine structures such as pulp chambers and root canals on cone-beam computed tomography scans, thereby supporting personalized treatment planning. However, a significant limitation highlighted in some studies is the reliance on in vitro or ex vivo datasets for training AI models. These datasets do not replicate the complexities of clinical environments, potentially compromising the reliability of AI applications in endodontics. Despite advancements, challenges remain in dataset variability, algorithm generalization, and ethical considerations such as data security and privacy. Addressing these is essential for integrating AI effectively into clinical practice and unlocking its transformative potential in endodontic care. Integrating radiomics with AI shows promise for enhancing diagnostic accuracy and predictive analytics, potentially enabling automated decision support systems to enhance treatment outcomes and patient care. Although AI enhances endodontic capabilities through advanced imaging analyses, addressing current limitations and fostering collaboration between AI developers and dental professionals are essential. These efforts will unlock AI's potential to achieve more predictable and personalized treatment outcomes in endodontics, ultimately benefiting both clinicians and patients alike.