RESUMEN
OBJECTIVE: To evaluate the diagnostic capability of artificial intelligence (AI) for detecting and classifying odontogenic cysts and tumors, with special emphasis on odontogenic keratocyst (OKC) and ameloblastoma. STUDY DESIGN: Nine electronic databases and the gray literature were examined. Human-based studies using AI algorithms to detect or classify odontogenic cysts and tumors by using panoramic radiographs or CBCT were included. Diagnostic tests were evaluated, and a meta-analysis was performed for classifying OKCs and ameloblastomas. Heterogeneity, risk of bias, and certainty of evidence were evaluated. RESULTS: Twelve studies concluded that AI is a promising tool for the detection and/or classification of lesions, producing high diagnostic test values. Three articles assessed the sensitivity of convolutional neural networks in classifying similar lesions using panoramic radiographs, specifically OKC and ameloblastoma. The accuracy was 0.893 (95% CI 0.832-0.954). AI applied to cone beam computed tomography produced superior accuracy based on only 4 studies. The results revealed heterogeneity in the models used, variations in imaging examinations, and discrepancies in the presentation of metrics. CONCLUSION: AI tools exhibited a relatively high level of accuracy in detecting and classifying OKC and ameloblastoma. Panoramic radiography appears to be an accurate method for AI-based classification of these lesions, albeit with a low level of certainty. The accuracy of CBCT model data appears to be high and promising, although with limited available data.
RESUMEN
BACKGROUND AND PURPOSE: In comparison to conventional medical imaging diagnostic modalities, the aim of this overview article is to analyze the accuracy of the application of Artificial Intelligence (AI) techniques in the identification and diagnosis of malignant tumors in adult patients. DATA SOURCES: The acronym PIRDs was used and a comprehensive literature search was conducted on PubMed, Cochrane, Scopus, Web of Science, LILACS, Embase, Scielo, EBSCOhost, and grey literature through Proquest, Google Scholar, and JSTOR for systematic reviews of AI as a diagnostic model and/or detection tool for any cancer type in adult patients, compared to the traditional diagnostic radiographic imaging model. There were no limits on publishing status, publication time, or language. For study selection and risk of bias evaluation, pairs of reviewers worked separately. RESULTS: In total, 382 records were retrieved in the databases, 364 after removing duplicates, 32 satisfied the full-text reading criterion, and 09 papers were considered for qualitative synthesis. Although there was heterogeneity in terms of methodological aspects, patient differences, and techniques used, the studies found that several AI approaches are promising in terms of specificity, sensitivity, and diagnostic accuracy in the detection and diagnosis of malignant tumors. When compared to other machine learning algorithms, the Super Vector Machine method performed better in cancer detection and diagnosis. Computer-assisted detection (CAD) has shown promising in terms of aiding cancer detection, when compared to the traditional method of diagnosis. CONCLUSIONS: The detection and diagnosis of malignant tumors with the help of AI seems to be feasible and accurate with the use of different technologies, such as CAD systems, deep and machine learning algorithms and radiomic analysis when compared with the traditional model, although these technologies are not capable of to replace the professional radiologist in the analysis of medical images. Although there are limitations regarding the generalization for all types of cancer, these AI tools might aid professionals, serving as an auxiliary and teaching tool, especially for less trained professionals. Therefore, further longitudinal studies with a longer follow-up duration are required for a better understanding of the clinical application of these artificial intelligence systems. TRIAL REGISTRATION: Systematic review registration. Prospero registration number: CRD42022307403.
Asunto(s)
Inteligencia Artificial , Neoplasias , Adulto , Humanos , Algoritmos , Hidrolasas , Aprendizaje Automático , Neoplasias/diagnóstico por imagen , Revisiones Sistemáticas como AsuntoRESUMEN
The aim of this study was to evaluate CBCT exposure protocols and CBCT devices in terms of image quality for the detection of cracks and fine endodontic structures using 3 conditions of metallic artifacts. An anthropomorphic phantom containing teeth with cracks, isthmus, narrow canal, and apical delta was scanned using ten CBCT devices. A reference industrial CT image was used to detect and measure all structures. Three conditions were created: (1) metal-free, (2) 'endo' and (3) 'implant' with metallic objects placed next to the teeth of interest. For each condition, three protocols were selected: medium field of view (FOV) standard resolution, small FOV standard and high resolution. The results showed that only small FOV high-resolution metal-free images from two devices (A and H) were appropriate to visualize cracks. For fine structure identification, the best result was observed for small FOV high resolution. However, the visualization significantly worsened in the presence of metallic artefacts. The ability of CBCT images for visualizing cracks is restricted to certain CBCT devices. Once metallic artefacts are present, crack detection becomes unlikely. Overall, small FOV high-resolution protocols may allow detection of fine endodontic structures as long as there are no high-dense objects in the region of interest.
Asunto(s)
Tomografía Computarizada de Haz Cónico , Tomografía Computarizada de Haz Cónico Espiral , Tomografía Computarizada de Haz Cónico/métodos , Artefactos , Cintigrafía , Fantasmas de Imagen , MetalesRESUMEN
The aim of this study was to evaluate the foraminal enlargement and its influence on microcrack formation and apical transportation in root canals with apical curvature. Eighteen maxillary lateral incisors with apical curvature were selected by using micro-CT images. Root canals were randomly divided in two groups (n = 9) according to root canal preparation using two working lengths: 1 mm short of the apical foramen (control group) and 1 mm beyond the apical foramen (foraminal enlargement). For both groups Reciproc Blue R40 was used for root canal instrumentation. Specimens were scanned by nano-CT (UniTOM HR) before and after root canal preparation. Percentage, length, and width of microcracks, and apical transportation were assessed. Kappa, chi-square and McNemar tests were used for qualitative analyses while paired and unpaired t-test were used for quantitative analyses (α = 0.05). For both groups, rather similar and low percentages of microcracks were observed before root canal preparation (P > 0.05). The foraminal enlargement promoted new microcracks, not observed in the control group. An increase in microcrack length was observed when the foraminal enlargement was performed (P < 0.05). Higher apical transportation was observed when foraminal enlargement was performed (P < 0.05). Foraminal enlargement using a heat-treated reciprocating file size 40 promoted microcracks and higher apical transportation than root canal preparation up to 1 mm short of apical foramen.
Asunto(s)
Preparación del Conducto Radicular , Ápice del Diente , Calor , Ápice del Diente/diagnóstico por imagen , Microtomografía por Rayos X , HumanosRESUMEN
PURPOSE: To assess radiographic presentation of anatomical structures, bony changes and soft tissue calcifications on panoramic radiographs of oncologic patients under high dose antiresorptive drug therapy (ART) before exposure to dental extraction. METHODS: Panoramic radiographs of 57 patients under ART, taken previously to tooth extraction, and 57 control patients were evaluated by two oral radiologists regarding bone pattern, anatomical structures visibility, estimation of cortical width, mandibular cortical index (MCI), and presence of soft tissue calcifications. Parameters were compared between ART and age- and gender-matched healthy control groups. Bone patterns were further assessed by regions with or without tooth extractions and according to uneventful healing or MRONJ development. All comparisons were made using chi-square test with significance level set at 5%. RESULTS: Mandible and posterior maxilla presented more sclerotic bone patterns in patients under ART, regardless of tooth extraction and MRONJ development status (p < 0.05). Heterogeneous bone pattern was identified in two regions that both were subsequently affected by MRONJ. Anatomical structure visibility and presence of soft tissue calcifications was not different among groups (p > 0.05). ART patients showed significantly more C0 (thickening) and C1 MCI (p < 0.05). CONCLUSION: Sclerotic bone pattern and thicker mandibular cortices may represent a consequence of ART rather than MRONJ specific findings. Prospective studies on larger patient samples radiographically followed-up during the ART treatment are advised, with specific attention to heterogenous trabecular bone pattern as a possible MRONJ predictor.
Asunto(s)
Osteonecrosis de los Maxilares Asociada a Difosfonatos , Conservadores de la Densidad Ósea , Humanos , Osteonecrosis de los Maxilares Asociada a Difosfonatos/diagnóstico por imagen , Osteonecrosis de los Maxilares Asociada a Difosfonatos/etiología , Osteonecrosis de los Maxilares Asociada a Difosfonatos/tratamiento farmacológico , Estudios Prospectivos , Percepción , Conservadores de la Densidad Ósea/uso terapéuticoRESUMEN
OBJECTIVE: To define which are and how the radiomics features of jawbone pathologies are extracted for diagnosis, predicting prognosis and therapeutic response. METHODS: A comprehensive literature search was conducted using eight databases and gray literature. Two independent observers rated these articles according to exclusion and inclusion criteria. 23 papers were included to assess the radiomics features related to jawbone pathologies. Included studies were evaluated by using JBI Critical Appraisal Checklist for Analytical Cross-Sectional Studies. RESULTS: Agnostic features were mined from periapical, dental panoramic radiographs, cone beam CT, CT and MRI images of six different jawbone alterations. The most frequent features mined were texture-, shape- and intensity-based features. Only 13 studies described the machine learning step, and the best results were obtained with Support Vector Machine and random forest classifier. For osteoporosis diagnosis and classification, filtering, shape-based and Tamura texture features showed the best performance. For temporomandibular joint pathology, gray-level co-occurrence matrix (GLCM), gray level run length matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), first-order statistics analysis and shape-based analysis showed the best results. Considering odontogenic and non-odontogenic cysts and tumors, contourlet and SPHARM features, first-order statistical features, GLRLM, GLCM had better indexes. For odontogenic cysts and granulomas, first-order statistical analysis showed better classification results. CONCLUSIONS: GLCM was the most frequent feature, followed by first-order statistics, and GLRLM features. No study reported predicting response, prognosis or therapeutic response, but instead diseases diagnosis or classification. Although the lack of standardization in the radiomics workflow of the included studies, texture analysis showed potential to contribute to radiologists' reports, decreasing the subjectivity and leading to personalized healthcare.
Asunto(s)
Quistes , Imagen por Resonancia Magnética , Humanos , Estudios Transversales , Tomografía Computarizada de Haz Cónico , Maxilares/diagnóstico por imagenRESUMEN
Purpose: The aim of this study was to compare the fractal dimension (FD) measured at 2 bone sites (second cervical vertebra and mandible) on cone-beam computed tomography (CBCT). The research question was whether FD could serve as an accessory tool to refer postmenopausal women for densitometric analysis. Therefore, the reliability and accuracy of FD were evaluated. Materials and Methods: In total, 103 postmenopausal women were evaluated, of whom 52 had normal bone mineral density and 51 had osteoporosis, according to dual X-ray absorptiometry of the lumbar spine and hip. On the CBCT scans, 2 regions of interest were selected for FD analysis: 1 at the second cervical vertebra and 1 located at the mandible. The correlations between both measurements, intra- and inter-observer agreement, and the accuracy of the measurements were calculated. A P value less than 0.05 was considered to indicate statistical significance for all tests. Results: The mean FD values were significantly lower at the mandibular region of interest in osteoporotic patients than in individuals with normal bone mineral density. The areas under the curve were 0.644 (P=0.008) and 0.531 (P=0.720) for the mandibular and vertebral sites, respectively. Conclusion: FD at the vertebral site could not be used as an adjuvant tool to refer women for osteoporosis investigation. Although FD differed between women with normal BMD and osteoporosis at the mandibular site, it demonstrated low accuracy and reliability.
RESUMEN
OBJECTIVE: To assess the accuracy of a novel Artificial Intelligence (AI)-driven tool for automated detection of teeth and small edentulous regions on Cone-Beam Computed Tomography (CBCT) images. MATERIALS AND METHODS: After AI training and testing with 175 CBCT scans (130 for training and 40 for testing), validation was performed on a total of 46 CBCT scans selected for this purpose. Scans were split into fully dentate and partially dentate patients (small edentulous regions). The AI Driven tool (Virtual Patient Creator, Relu BV, Leuven, Belgium) automatically detected, segmented and labelled teeth and edentulous regions. Human performance served as clinical reference. Accuracy and speed of the AI-driven tool to detect and label teeth and edentulous regions in partially edentulous jaws were assessed. Automatic tooth segmentation was compared to manually refined segmentation and accuracy by means of Intersetion over Union (IoU) and 95% Hausdorff Distance served as a secondary outcome. RESULTS: The AI-driven tool achieved a general accuracy of 99.7% and 99% for detection and labelling of teeth and missing teeth for both fully dentate and partially dentate patients, respectively. Automated detections took a median time of 1.5s, while the human operator median time was 98s (P<0.0001). Segmentation accuracy measured by Intersection over Union was 0.96 and 0.97 for fully dentate and partially edentulous jaws respectively. CONCLUSIONS: The AI-driven tool was accurate and fast for CBCT-based detection, segmentation and labelling of teeth and missing teeth in partial edentulism. CLINICAL SIGNIFICANCE: The use of AI may represent a promising time-saving tool serving radiological reporting, with a major step forward towards automated dental charting, as well as surgical and treatment planning.
Asunto(s)
Arcada Edéntula , Boca Edéntula , Inteligencia Artificial , Tomografía Computarizada de Haz Cónico/métodos , Humanos , Procesamiento de Imagen Asistido por Computador , Arcada Edéntula/diagnóstico por imagen , Boca Edéntula/diagnóstico por imagen , Redes Neurales de la ComputaciónRESUMEN
OBJECTIVES: The overall objective of this study was to assess how metal artefacts impact image quality of 13 CBCT devices. As a secondary objective, the influence of scanning protocols and field of view on CBCT image quality with and without metal artefacts was also assessed. MATERIALS AND METHODS: CBCT images were acquired of a dry human skull phantom considering three clinical simulated conditions: one without metal and two with metallic materials (metallic pin and implant). An industrial micro-CT was used as a reference to register the CBCT images. Afterwards, four observers evaluated 306 representative image slices from 13 devices, ranking them from best to worst. Furthermore, within each device, medium FOV and small FOV standard images were compared. General linear mixed models were used to assess subjective perception of examiners on overall image quality in the absence and presence of metal-related artefacts (p < 0.05). RESULTS: Image quality perception significantly differed amongst CBCT devices (p < 0.05). Some devices performed significantly better, independently of scanning protocol and clinical condition. In the presence of metal artefacts, medium FOV standard scanning protocols scored significantly better, while in the absence of metal, small FOV standard yielded the highest performance. CONCLUSIONS: Subjective image quality differs significantly amongst CBCT devices and scanning protocols. Metal-related artefacts may highly impact image quality, with a significant device-dependent variability and only few scanners being more robust against metal artefacts. Often, metal artefact expression may be somewhat reduced by proper protocol selection. CLINICAL RELEVANCE: Metallic objects may severely impact image quality in several CBCT devices.
Asunto(s)
Artefactos , Tomografía Computarizada de Haz Cónico Espiral , Tomografía Computarizada de Haz Cónico/métodos , Humanos , Metales , Percepción , Fantasmas de ImagenRESUMEN
Patients with Osteogenesis Imperfecta (OI) present extra-skeletal manifestations, including important orodental and craniofacial features as dentinogenesis imperfecta, dental agenesis, failure of maxilla growth and hypotonia of masticatory muscles. These features may compromise vital functions speech and mastication. Studies have demonstrated that cyclic pamidronate infusion, the standard therapy for patients with moderate to severe OI, influences the histomorphometric pattern of different body bones. The present study aimed to investigate the condyle trabecular bone pattern in OI patients. We used fractal dimension (FD) analysis on dental panoramic radiographic images to characterize the mandibular condyle trabecular bone in adolescents diagnosed with OI and treated with pamidronate. Imaging exam of 33 adolescents of both sexes, aged between 12 and 17 years, were analyzed and compared with 99 age- and sex-matched healthy adolescents. FD in patients was significantly lower (1.23 ± 0.15) than in healthy controls (1.29 ± 0.11; p < 0.01). Type of OI, age at treatment onset, and the duration of therapy were variables that showed a statistically significant effect on the FD results. This study demonstrated that the bone architecture of mandibular condyles may be altered in pediatric patients with moderate and severe forms of OI. Also, pamidronate treatment seems to have a positive effect on condyle trabecular bone in these patients. This is supported by our finding that FD values were positively influenced by the length of cyclic pamidronate treatment at the time of imaging, as well as by the age of the individual at treatment onset.
Asunto(s)
Osteogénesis Imperfecta , Adolescente , Densidad Ósea , Hueso Esponjoso , Niño , Difosfonatos/uso terapéutico , Femenino , Humanos , Masculino , Cóndilo Mandibular , Osteogénesis Imperfecta/tratamiento farmacológico , PamidronatoRESUMEN
OBJECTIVES: The present study aimed to assess whether anatomical variations of the mandibular canal are associated with neurosensory disturbances of the inferior alveolar nerve (IAN) following mandibular third molar removal. METHODS: Two observers compared the detection of third molar root-nerve relations and bifurcations of the mandibular canal on panoramic radiographs and CBCT images of 201 patients undergoing removal of 357 mandibular third molars. Potential neurosensory disturbances of the IAN were surveyed ten days after surgery. Fisher's Exact was performed to correlate presence of canal variations to postoperative neurosensory disturbances. Positive and negative predictive values (PPV, NPV) and likelihood ratios (LR + , LR-) were calculated. RESULTS: Thirteen patients reported postoperative altered sensation of the lower lip, with 2 of them having mandibular canal bifurcations on the ipsilateral side of the injury. Fisher's Exact showed that the studied mandibular canal variations were not related to postoperative neurosensory disturbances. CBCT was superior in visualization of anatomical variations of the mandibular canal. Prevalence of bifurcations was 14% on CBCT and 7% on panoramic radiographs. In both imaging modalities and for all parameters, PPVs were low (0.04 - 0.06) and NPVs were high (0.92 - 0.98), with LR ranging around 1. CONCLUSION: In the present study, the assessed mandibular canal variations had limited predictive value for IAN neurosensory disturbances following third molar removal. CLINICAL RELEVANCE: While a close relation between the third molar and the mandibular canal remains a high risk factor, mandibular canal variations did not pose an increased risk of postoperative IAN injury after third molar removal.
Asunto(s)
Diente Impactado , Traumatismos del Nervio Trigémino , Humanos , Mandíbula/diagnóstico por imagen , Mandíbula/cirugía , Canal Mandibular , Nervio Mandibular/diagnóstico por imagen , Tercer Molar/diagnóstico por imagen , Tercer Molar/cirugía , Radiografía Panorámica , Extracción Dental/efectos adversos , Traumatismos del Nervio Trigémino/etiologíaRESUMEN
OBJECTIVES: This integrative review aimed to assess the benefits of the use of teledentistry for patients undergoing treatment of oral and head and neck cancer during the COVID-19 pandemic. MATERIALS AND METHODS: We searched in PubMed, Cochrane, Scopus, Web of Science, Lilacs, Embase, Open Grey, Google Scholar, and Jstor databases for studies referring to the management, control, and assistance, through teledentistry, to patients with oral and head and neck cancer during the COVID-19 pandemic. RESULTS: We found 356 references in the databases, 209 after duplicates removal, 23 met criteria for full-text reading, and 11 studies were included for qualitative synthesis, in four categories: virtual visits, use of remote technology, patient's satisfaction, multidisciplinary approach in teledentistry. We found that 78% of patients currently preferred teledentistry; 92% of patients would recommend the use of video consultation to other patients. The continuity of dental care, the reduction of patient visits to the hospital, the reduction of the risk of infection with the coronavirus, and limitation of face-to-face consultations to protect health professionals are benefits that reinforce the use of teledentistry by health institutions. Two studies showed patients' satisfaction with the use of teledentistry in monitoring cancer patients and showed an improvement in quality of life. CONCLUSIONS: The teledentistry, as a remote technology for monitoring patients with oral and head and neck cancer, is well accepted by patients in preliminary studies. Although these studies pointed out some benefits of using remote technologies for the care of cancer patients, further robust scientific evidence is still needed in this regard.
Asunto(s)
COVID-19 , Neoplasias de la Boca , Telemedicina , Humanos , Neoplasias de la Boca/epidemiología , Neoplasias de la Boca/terapia , Pandemias , Calidad de Vida , SARS-CoV-2RESUMEN
BACKGROUND: The purpose of this study was to objectively assess dimensional alteration (blooming artefact) on dental implant using 13 cone-beam computed tomography (CBCT) devices adjusted to device-specific scanning protocols and to assess whether subjective adjustment of brightness and contrast (B&C) could alter its visualization. METHODS: An anthropomorphic phantom containing a dental implant was scanned in 13 CBCT devices adjusted to three scanning protocols: medium-FOV standard resolution, small-FOV standard resolution, and small-FOV high resolution. The diameter of the implant was measured at five levels, averaged, and compared with those from a reference standard industrial CT image. B&C adjustments were performed and measurements were repeated. The intraclass correlation coefficient assessed the reliability of the measurements and general linear mixed models were applied for multiples comparisons at a 95% confidence interval. RESULTS: Implant diameter obtained from small-FOV high-resolution protocols in most CBCT devices was not significantly different when compared to that from the reference (p > 0.05). For standard protocols, significant dimensional alteration of the implant ranging from 23 to 34% (0.67 to 1.02 mm) was observed in 9 CBCT devices for small-FOV scanning (p < 0.05), and in 8 CBCT devices for medium-FOV scanning, implant dimensional alteration ranged significantly from 21 to 35% (0.62 to 1.04 mm). After B&C adjustments, dimensional alteration was reduced for several of the CBCT devices tested (p < 0.05). CONCLUSIONS: The visualization of the implant dimensional alteration differed between CBCT devices and scanning protocols with an increase in diameter ranging from 0.27 to 1.04 mm. For most CBCT devices, B&C adjustments allowed to reduce visualization of implant blooming.
Asunto(s)
Artefactos , Implantes Dentales , Tomografía Computarizada de Haz Cónico , Fantasmas de Imagen , Reproducibilidad de los ResultadosRESUMEN
INTRODUCTION: The purpose of this study was to classify 10 cone-beam computed tomographic (CBCT) devices using a ranking model according to the detection of fine endodontic structures. METHODS: A dedicated dentate anthropomorphic phantom was scanned 2 times using 10 CBCT devices without any metal (metal-free condition) and with an endodontically treated tooth containing a metallic post (metal condition). A reference image acquired on an industrial micro-CT scanner was used to register all CBCT images, yielding corresponding anatomic slices. Afterward, 3 experienced observers assessed all acquired CBCT images for their ability to assess a narrow canal, isthmus, and apical delta ramification using a categoric rank from 1 (best) to 10 (worst). Fleiss kappa statistics were used to calculate intra- and interobserver agreements for each CBCT device separately. Based on the observers' scores, general linear mixed models were applied to compare image quality among different CBCT devices for performing endodontic diagnostic tasks (α = .05). RESULTS: The 10 CBCT devices performed differently for the evaluated endodontic tasks (P < .05), with 3 devices performing better for endodontic feature detection. Yet, in the presence of metal, only 2 devices were able to keep a high level of endodontic feature detection. CONCLUSIONS: The evaluated endodontic tasks were CBCT device dependent, and their detection was influenced by the presence of metal.
Asunto(s)
Tomografía Computarizada de Haz Cónico , Diente no Vital , Humanos , Fantasmas de Imagen , Microtomografía por Rayos XRESUMEN
OBJECTIVE: This article aims to appraise how scientific evidence related to CBCT has changed over the years, based on levels of evidence and diagnostic efficacy. METHODS: A general search strategy was used in different databases (Pubmed, Embase, and Web of Science) to identify systematic reviews (SRs) on CBCT until November of 2020. The SRs included were divided according to different specialties of dentistry. A critical review of the articles was made, describing the level of evidence and efficacy. RESULTS: In total, 75 articles were selected. There was an increase in the number of SRs on CBCT from 2014 onwards, as 83% of the SRs on this topic were published after 2013, and 72% between 2016 and to date. Twenty SRs (27%) performed meta-analysis. Only 28% of the SRs provided a detailed description of CBCT protocols. According to SR evidence, almost all specialties of dentistry have advanced concomitantly with the introduction of CBCT. The majority of SRs were related to clinical applications (level 2 of efficacy), followed by technical parameters (level 1 of efficacy). Only some CBCT models were mentioned in the SRs selected. CONCLUSION: Over the course of 20 years, SRs related to CBCT applications for a broad range of dental specialties have been published, with the vast majority of studies at levels 1 and 2 of diagnostic efficacy. Not all CBCT models available on the market have been scientifically validated. At all times, one should remain cautious as such not to simply extrapolate in vitro results to the clinical setting. Also, considering the wide variety of CBCT devices and protocols, reported results should not be overstated or generalized, as outcomes often refer to specific CBCT devices and protocols.
Asunto(s)
Tomografía Computarizada de Haz Cónico Espiral , Tomografía Computarizada de Haz Cónico , HumanosRESUMEN
OBJECTIVE: Bisphosphonates and denosumab are both antiresorptive medications, each with their own mechanism of action; yet both may result in the same adverse effect: medication-related osteonecrosis of the jaw (ONJ). The present systematic review aims to answer the following question: "Are bisphosphonate-related ONJ and denosumab-related ONJ any different, regarding clinical and imaging aspects?" METHODS: This review followed the Joanna Briggs Review's Manual, and the searches were performed on PubMed, Cochrane, Scopus, Web of Science, and Lilacs databases and on the grey literature (ProQuest, Open Grey, and Google Scholar). RESULTS: The searches resulted in 7535 articles that were critically assessed. Based on the selection criteria, seven studies were included in the review: five cross-sectional studies and two randomized clinical trials. A total of 7755 patients composed the final population. An increase in bone sequestra, cortical bone lysis, and bone density was observed in bisphosphonate-related ONJ, while larger bone sequestra, more frequent periosteal reactions, and mandibular canal enhancement were noted in denosumab-related ONJ. CONCLUSION: This systematic review demonstrated that the imaging characteristics of bisphosphonate-related and denosumab-related ONJ are not similar. Although clinically similar conditions, they were found to be radiographically distinct. More studies are necessary to further elucidate these differences.
Asunto(s)
Osteonecrosis de los Maxilares Asociada a Difosfonatos/tratamiento farmacológico , Conservadores de la Densidad Ósea/uso terapéutico , Denosumab/efectos adversos , Difosfonatos/efectos adversos , Conservadores de la Densidad Ósea/farmacología , Estudios Transversales , HumanosRESUMEN
OBJECTIVE: To evaluate the performance of a new artificial intelligence (AI)-driven tool for tooth detection and segmentation on panoramic radiographs. MATERIALS AND METHODS: In total, 153 radiographs were collected. A dentomaxillofacial radiologist labeled and segmented each tooth, serving as the ground truth. Class-agnostic crops with one tooth resulted in 3576 training teeth. The AI-driven tool combined two deep convolutional neural networks with expert refinement. Accuracy of the system to detect and segment teeth was the primary outcome, time analysis secondary. The Kruskal-Wallis test was used to evaluate differences of performance metrics among teeth groups and different devices and chi-square test to verify associations among the amount of corrections, presence of false positive and false negative, and crown and root parts of teeth with potential AI misinterpretations. RESULTS: The system achieved a sensitivity of 98.9% and a precision of 99.6% for tooth detection. For segmenting teeth, lower canines presented best results with the following values for intersection over union, precision, recall, F1-score, and Hausdorff distances: 95.3%, 96.9%, 98.3%, 97.5%, and 7.9, respectively. Although still above 90%, segmentation results for both upper and lower molars were somewhat lower. The method showed a clinically significant reduction of 67% of the time consumed for the manual. CONCLUSIONS: The AI tool yielded a highly accurate and fast performance for detecting and segmenting teeth, faster than the ground truth alone. CLINICAL SIGNIFICANCE: An innovative clinical AI-driven tool showed a faster and more accurate performance to detect and segment teeth on panoramic radiographs compared with manual segmentation.
Asunto(s)
Inteligencia Artificial , Diente , Diente Molar , Redes Neurales de la Computación , Radiografía PanorámicaRESUMEN
This critical review discusses the clinical challenges for patient-specific and indication-oriented dentomaxillofacial cone beam computed tomography (CBCT). Large variations among units and protocols may lead to variable degrees of diagnostic and three-dimensional model accuracy, impacting both specific diagnostic tasks and treatment planning. Particular indications, whether diagnostic or therapeutic, may give rise to very specific challenges with regard to CBCT unit and parameter setup, considering the required image quality, segmentation accuracy, and artifact level. Considering that dental materials are in the field of view needed for diagnosis or treatment planning, artifact expression is a dominant factor in proper CBCT selection. The heterogeneity of dental CBCT units and performances may highly impact the scientific results. Thus research findings cannot be simply generalized as published evidence, and a demonstrated clinical applicability for a specific indication should not be simply extrapolated from one CBCT unit to another.
Asunto(s)
Tomografía Computarizada de Haz Cónico/métodos , Radiografía Dental/métodos , Enfermedades Estomatognáticas/diagnóstico por imagen , Artefactos , HumanosRESUMEN
OBJECTIVE: The aim of this longitudinal study was to characterize the dento-osseous phenotype of eleven familial adenomatous polyposis (FAP) patients and twenty-two family members from four Brazilian families who were followed over nine years and to investigate adenomatous polyposis coli (APC) gene variants using a targeted next-generation sequencing approach. MATERIALS AND METHODS: Medical and dental history, oral examination, and panoramic radiography were performed to diagnose and follow up the dento-osseous anomalies. The anomalies were evaluated following the validated diagnostic tool dental panoramic radiographic score (DPRS), a system developed for high-risk FAP patients. Patients diagnosed with dento-osseous anomalies underwent cone-beam computed tomography. For genetic analysis, DNA was isolated from patients' saliva. RESULTS: Dento-osseous anomalies were identified in ten of the eleven FAP patients by panoramic radiograph evaluation. DPRS ≥ 7 (significant changes) was found in 81.8% (9/11) of FAP patients. The follow-up showed an increase in osseous jaw lesions in two young patients during adolescence. Dento-osseous anomalies were not found in non-FAP patients. A novel heterozygous nonsense pathogenic variant in APC exon 5 (c.481C > T; p.Gln161*) was identified in family 2, and a heterozygous splice-site pathogenic variant was identified in family 1 (c.532-1G > A). CONCLUSION: Our study expands the mutation spectrum of the APC gene and provides evidence that dento-osseous screening by imaging is a putative tool for early diagnosis of FAP. Also, the detection of dento-osseous anomalies in young patients with increasing osseous lesions during adolescence highlights the need for dental follow-up of high-risk FAP children. CLINICAL RELEVANCE: Dental radiographs are important for the screening and the follow-up of dento-osseous anomalies associated with FAP. It can also contribute to the early diagnosis of the disease.