RESUMEN

OBJECTIVE: To segment dental implants on PA radiographs using a Deep Learning (DL) algorithm. To compare the performance of the algorithm relative to ground truth determined by the human annotator. Methodology: Three hundred PA radiographs were retrieved from the radiographic database and consequently annotated to label implants as well as teeth on the LabelMe annotation software. The dataset was augmented to increase the number of images in the training data and a total of 1294 images were used to train, validate and test the DL algorithm. An untrained U-net was downloaded and trained on the annotated dataset to allow detection of implants using polygons on PA radiographs. RESULTS: A total of one hundred and thirty unseen images were run through the trained U-net to determine its ability to segment implants on PA radiographs. The performance metrics are as follows: accuracy of 93.8%, precision of 90%, recall of 83%, F-1 score of 86%, Intersection over Union of 86.4% and loss = 21%. CONCLUSIONS: The trained DL algorithm segmented implants on PA radiographs with high performance similar to that of the humans who labelled the images forming the ground truth.

Asunto(s)

RESUMEN

OBJECTIVE: Radiographs are an integral part of detecting proximal caries. The aim of this study was to evaluate the effect of contrast, brightness, noise, sharpness, and γ adjustment of digital intraoral radiographs on the diagnosis of proximal caries. MATERIALS AND METHODS: In this in vitro study, 40 extracted teeth including 20 premolars and 20 molars with enamel lesions (white spot or dentin discoloration seen through the enamel) were mounted together in groups of eight inside the skull. Bitewing radiographic images of each dental group were obtained by a photostimulable phosphor plate sensor with exposure conditions of 8 mA, 70 kV, and 0.2 s. The images were reconstructed by the built-in software and examined by two oral and maxillofacial radiologists in various settings of contrast, brightness, sharpness, noise, and γ. The teeth were then cut mesiodistally and the presence or absence of caries was confirmed by an oral and maxillofacial pathologist using a stereomicroscope. The data were then analyzed using the κ agreement coefficient, sensitivity, specificity, and accuracy (α = .05). RESULTS: Adjustment of brightness and contrast led to higher diagnostic performance with an accuracy of 82.5% and 83.8 (for observers 1 and 2, respectively) and 82.5% (for both observers), respectively. Noise adjustment was the least helpful approach for diagnosis of proximal dental caries among other adjustments, with an accuracy of 78.8% and 77.5% for observers 1 and 2, respectively. CONCLUSION: Brightness and contrast setting was more efficient in improving the diagnostic potential of bitewing radiographs compared to other adjustments.

Asunto(s)

RESUMEN

Introduction: The primary objective of this retrospective study was to document the normal variation of clinical mobility of the mandibular symphysis in cats and possible associations with bodyweight, age, sex, sexual status, breed and skull morphology. Secondarily, the radiographic appearance of the mandibular symphysis and possible associations with the analyzed data were evaluated. Materials and methods: Two hundred and sixteen cats of 15 different breeds that underwent maxillofacial, oral and dental procedures from April 2015 to December 2021 were included. Clinical mobility was evaluated under general anesthesia using a 0 to 3 scale in lateromedial (LM) and dorsoventral (DV) directions. The symphysis was radiographically classified on the occlusal radiographic view of the rostral mandibles as fused or open, and with parallel or divergent margins. Results: Bodyweight ranged from 2.2 to 12.5 kg (median 4.0 kg), age from 4 months to 17 years and 4 months (median 6 years and 4 months). At the first evaluation DV symphyseal mobility was 0 in 177 cases (82%), 1 in 32 cases (14.8%) and 2 in 7 cases (3.2%), LM mobility was 0 in 61 cases (28.3%), 1 in 110 cases (50.9%) and 2 in 45 cases (20.8%). 81.1% of the radiographs were included in the statistical analysis. Three symphyses (1.6%) were classified as fused and 190 (98.4%) as open, 129 (68.8%) having divergent margins and 61 (31.6%) parallel. One hundred and forty-eight cases (76.7%) did not show the presence of odontoclastic replacement resorption on the canine teeth (TR subgroup 1), 23 (11.9%) showed stage ≤3 lesions (TR subgroup 2) and 22 (11.4%) stage 4 lesions (TR subgroup 3). Logistic regression models exploring factors that affected DV and LM mobility were statistically significant (p < 0.0001; p < 0.0001) with an increase in LM mobility predicting an increase in DV mobility, and vice versa. An increase in DV mobility was associated with an increase in age and in having resorptive lesions. A decrease in LM symphyseal mobility was associated with being brachycephalic. Conclusion: The great majority of cases showed some degree of LM symphyseal mobility, and 18% showed DV mobility. Symphyseal bony fusion is rare but possible.

Asunto(s)

RESUMEN

Introduction: The primary objective of this retrospective study was to document the normal variation of clinical mobility of the mandibular symphysis in dogs, and evaluate possible associations with breed, bodyweight, age, sex, and skull morphology. Secondarily, the radiographic appearance of the mandibular symphysis and possible associations with the analyzed data were also evaluated. Methods: Medical records of dogs that underwent anesthetic procedures for maxillofacial, oral and dental evaluation from April 2015 to December 2021 were included. Results: 567 dogs of 95 different breeds were included, with a total of 695 evaluations. Body weight ranged from 0.8 kg to 79 kg (median 14.4 kg) and age from 3 months to 16 years and 4 months (median 6 years and 9 months). Clinical mobility was evaluated under general anesthesia using a 0 to 3 scale, in lateromedial (LM) and dorsoventral (DV) directions. The symphysis was radiographically classified as being fused or open. The open symphyses were further radiographically divided in having parallel or divergent margins. At the time of the first evaluation DV mobility was 0 in 551 cases (97.2%) and 1 in 16 cases (2.8%). LM mobility was 0 in 401 cases (70.7%), 1 in 148 cases (26.1%) and 2 in 18 cases (3.2%). There was not a significant change in mobility over time for cases examined more than once (P= 0.76). All cases had an intraoral radiographic examination. 83.8% of the radiographs were included in the statistical analysis. Two symphyses (0.4%) were classified as fused and 473 (99.6%) as open, 355 (74.7%) having divergent margins and 118 (24.8%) parallel margins. Logistic regression models exploring factors that affected DV and LM mobility were statistically significant (P < 0.0001; P < 0.0001), with an increase in LM mobility predicting an increase in DV mobility, and vice versa. An increase in age and in bodyweight was associated with a decrease in mobility. There was no statistical difference in clinical mobility across specific breeds or sexes. Increased probability of a divergent symphysis and increased DV mobility was found to be associated with a brachycephalic conformation. The increase in LM mobility was comparatively higher in small brachycephalic breeds compared with larger brachycephalic breed. Discussion: The majority of the cases showed little to no mobility of the mandibular symphysis and radiographically bony fusion can be rarely seen.

RESUMEN

PURPOSE: The dual imaging plate (DIP) method, which synthesizes intraoral radiographs from a front imaging plate (FIP) and a back imaging plate (BIP), produces adequate image quality and allows the radiation dose to be reduced. However, there are slight errors in superimposition and alignment between the FIP and BIP. The aim of this study was to establish positional correction in the DIP method and evaluate the effect. METHODS: Six sets of two imaging plates were used for imaging a mesh plate and a porcine mandible phantom. Subtraction images between FIP and BIP images were synthesized in four steps: correcting horizontal and vertical direction, rotation, enlargement ratio, and enlargement ratio into 12 blocks. Variance of the pixel value on the subtraction images at each step was compared to evaluate the alignment of FIP and BIP images. RESULTS: The variance of the pixel values in the subtraction images was gradually and significantly decreased by each step of image processing (P < 0.01), indicating that the degree of alignment of FIP and BIP images improved during the image processing. CONCLUSION: The present study revealed that it is possible to synthesize more precise DIP images using an additional four-step image processing technique.

RESUMEN

AIM: To develop a deep learning (DL) artificial intelligence (AI) model for instance segmentation and tooth numbering on orthopantomograms (OPGs). MATERIALS AND METHODS: Forty OPGs were manually annotated to lay down the ground truth for training two convolutional neural networks (CNNs): U-net and Faster RCNN. These algorithms were concurrently trained and validated on a dataset of 1280 teeth (40 OPGs) each. The U-net algorithm was trained on OPGs specifically annotated with polygons to label all 32 teeth via instance segmentation, allowing each tooth to be denoted as a separate entity from the surrounding structures. Simultaneously, teeth were also numbered according to the Fédération Dentaire Internationale (FDI) numbering system, using bounding boxes to train Faster RCNN. Consequently, both trained CNNs were combined to develop an AI model capable of segmenting and numbering all teeth on an OPG. RESULTS: The performance of the U-net algorithm was determined using various performance metrics including precision = 88.8%, accuracy = 88.2%, recall = 87.3%, F-1 score = 88%, dice index = 92.3%, and Intersection over Union (IoU) = 86.3%. The performance metrics of the Faster RCNN algorithm were determined using overlap accuracy = 30.2 bounding boxes (out of a possible of 32 boxes) and classifier accuracy of labels = 93.8%. CONCLUSIONS: The instance segmentation and tooth numbering results of our trained AI model were close to the ground truth, indicating a promising future for their incorporation into clinical dental practice. The ability of an AI model to automatically identify teeth on OPGs will aid dentists with diagnosis and treatment planning, thus increasing efficiency.

Asunto(s)

RESUMEN

OBJECTIVES: Artifacts including scratches and dirt artifacts on the digital intraoral radiographs finally contribute to making inaccurate diagnoses. The aim of this study was to reduce the incidence of artifacts using dual imaging plates (DIPs) in imaging processing. METHODS: Conventional X-rays were taken of a porcine mandible embedded in acrylic resin using a DIP which consists of a front IP (FIP) and a back IP (BIP) with some scratches and dirt. The two images of the FIP and BIP were then synthesized and averaged to obtain a conventional DIP image. The following image processing method was used to make a DIP with artifact reduction (DIP+AR) image. A subtraction image of the FIP and BIP was constructed and the standard deviation (SD) was calculated. If the pixel value was over 3SD on the subtraction images, the pixel value of the DIP was swapped with the value on the opposite side of the non-artifact pixel. The conventional and DIP+AR images were also subjectively evaluated. RESULTS: Image processing to create a DIP+AR image was able to reduce the number of artifacts. Medians of number of artifacts evaluated were 2.00 [interquartile range (IQR), 2.50] in DIP images and 0.67 (IQR, 1.29) in DIP+AR images, indicating a significant reduction of number of artifacts in DIP+AR images. CONCLUSIONS: DIP+AR image processing can reduce the incidence of artifacts caused by scratches and dirt, and could extend the lifespan of the IP and contribute accurate diagnosis in oral radiology.

Asunto(s)

RESUMEN

OBJECTIVE: This in vitro study aimed to compare the diagnostic outcomes of caries detection in premolar and molar teeth on digital periapical radiographs viewed as grayscale images and in the Java-based software (JBS) pseudocolor spectrum. METHOD AND MATERIALS: The study comprised 92 premolar or molar human teeth (n = 46 with caries and n = 46 without clinical caries). For each tooth, digital periapical radiographic images (DPRIs), JBS pseudocolor images, and stereomicroscope images were collected, and caries presence and depth were recorded. In JBS pseudocolor images, regions of interest (ROIs) were detected, and ROI values for caries area (ROI1), non-caries area (ROI2), mesial area (ROI3), and distal area (ROI4) were obtained. The degree of inter-observer agreement was determined using the kappa coefficient, and the sensitivity and specificity of the methods were assessed using ROC analysis. RESULTS: While neither method was consistent with stereomicroscopy in determining caries depth (P < .005), for both observers the kappa value of JBS pseudocolor images were slightly higher than those for DPRIs. ROI1 was found to be significantly lower than ROI2 (P < .001), whereas no difference was found between ROI3 and ROI4 (P = .877). For both observers, the sensitivity and specificity obtained from JBS pseudocolor were above 89%. CONCLUSION: JBS pseudocolor images can be used for caries detection and offer high sensitivity and specificity.

Asunto(s)

RESUMEN

OBJECTIVES: In digital intraoral radiography (DIR), images with defects caused by the digital process are sometimes produced. Hence, we analyzed DIR images with defects taken using the photostimulable phosphor (PSP) plate method and then classified these images based on the causes of the defect. The aim of this study was to classify defects in DIR using the PSP plate system, and to discuss the causes of each type of defect and the methods that can prevent their occurrence. METHODS: Images with defects due to the two PSP plate systems (Arcana and Arcana Mira) were selected and classified according to the defect. Image defects caused by geometrical techniques that occur in both the film and PSP plate methods were excluded from this study. Moreover, changes in the rate of occurrence of images with defects over time were analyzed in this study. RESULTS: The defects in images obtained by the PSP plate system were classified into six types, which were further divided into those caused by machine error or human error. Both types of error could influence the diagnostic performance. Machine error accidentally and rarely occurred; thus, the prevention of such errors is difficult. However, human error, especially errors caused by photo-induced discharge, could be prevented using appropriate measures. CONCLUSIONS: In DIR systems using the PSP plate method, human error should be prevented by education and training to improve operation.

Asunto(s)

RESUMEN

Aim: The aim of this article is to assess Tamil Nadu adult diagnostic reference levels (DRLs) by collecting radiation dose data from the four different dental modalities. Materials and Methods: The study was carried out using routine adult exposure settings in 131 intraoral, 75 panoramic, 35 cephalometric, and 10 dental cone beam computed tomography (CBCT) X-ray devices. DRLs were assessed for intraoral and extraoral (panoramic, cephalometric, and CBCT) examinations in terms of incident air kerma (Ka, i) and kerma area product (PKA), respectively. Air kerma measurements, for all dental units, were made using calibrated RTI black Piranha 557 dosimeter (RTI Electronics AB, Sweden). The dosimeter was kept at the exit cone of the X-ray tube and on the detector side of the X-ray unit for intraoral and extraoral air kerma measurements, respectively. The obtained air kerma in extraoral modalities is multiplied with the beam area to evaluate PKA. Results: The third quartile values calculated from the median for adult intraoral (mandibular molar), panoramic, cephalometric, and CBCT were 1.5 mGy, 116 mGycm2, 40 mGycm2, and 532 mGycm2, respectively. The proposed DRL in the present study was comparable to those reported in Germany, Greece, the UK, Japan, and Korea. Conclusion: This study revealed the need for dose management and radiation dose optimization, in various dental facilities in the state. It was also found that dental facilities employed with the digital type of detector are not always related to lower exposure.

RESUMEN

The developments in Artificial Intelligence have been on the rise since its advent. The advancements in this field have been the innovative research area across a wide range of industries, making its incorporation in dentistry inevitable. Artificial Intelligence techniques are making serious progress in the diagnostic and treatment planning aspects of dental clinical practice. This will ultimately help in the elimination of subjectivity and human error that are often part of radiographic interpretations, and will improve the overall efficiency of the process. The various types of Artificial Intelligence algorithms that exist today make the understanding of their application quite complex. The current narrative review was planned to make comprehension of Artificial Intelligence algorithms relatively straightforward. The focus was planned to be kept on the current developments and prospects of Artificial Intelligence in dentistry, especially Deep Learning and Convolutional Neural Networks in diagnostic imaging. The narrative review may facilitate the interpretation of seemingly perplexing research published widely in dental journals.

Asunto(s)

RESUMEN

This article describes the technical principles and indications for the most often encountered diagnostic imaging modalities in veterinary dentistry and oral surgery; with extensive coverage of intraoral (and extraoral) dental radiographic imaging and interpretation through detailed example figures of common dental and maxillofacial diseases in the dog and cat. Multidetector/multislice computed tomography (MDCT/MSCT) and emergent technologies such as cone-beam computed tomography (CBCT) are presented here in detail. Magnetic resonance imaging (MRI) and diagnostic ultrasound, which are used less frequently, are briefly discussed.

Asunto(s)

RESUMEN

PURPOSE: This study evaluated the contrast-to-noise ratio (CNR), spatial resolution, and subjective quality of dual imaging plates (DIP) intraoral radiography. METHODS: The DIP and conventional single IP (CSIP) methods both used YCR DT-1 imaging plates (Yoshida Co.). The DIP, comprising a front IP (FIP) and back IP (BIP), was constructed. DIP images were synthesized from the FIP and BIP images. An aluminum step phantom was used to measure the CNR. A line pair gauge was used to measure the spatial imaging resolution. A phantom comprising a porcine mandible embedded in acrylic resin was used for subjective evaluation. RESULTS: The CNR of the DIP image was 32% higher than that of the FIP image. The spatial resolution achieved using the FIP, DIP, and CSIP was highly comparable except above 4 line pairs/mm, where that of the CSIP was highest. In subjective evaluation, the noise in the DIP images was significantly lower than in those obtained using the FIP and CSIP. CONCLUSION: The CNR of the DIP was higher than that of the FIP. The decrease in spatial resolution of the DIP was limited. The subjective image quality of the DIP was higher than that of the FIP.

Asunto(s)

RESUMEN

The aim of this study was to evaluate whether textural analysis could differentiate between the two common types of lytic lesions imaged with use of radiography. Sixty-two patients were enrolled in the study with intraoral radiograph images and a histological reference study. Full textural analysis was performed using MaZda software. For over 10,000 features, logistic regression models were applied. Fragments containing lesion edges were characterized by significant correlation of structural information. Although the input images were stored using lossy compression and their scale was not preserved, the obtained results confirmed the possibility of distinguishing between cysts and granulomas with use of textural analysis of intraoral radiographs. It was shown that the important information distinguishing the aforementioned types of lesions is located at the edges and not within the lesion.

Asunto(s)

RESUMEN

The importance of intraoral periapical radiography is crucial as it represents a fundamental mean of evaluation and diagnosis for supporting bone and teeth hard tissues diseases and pathologies. Even though conventional film technology is still widespread, presently there are many digital radiography alternatives. Direct digital systems are devices with an intraoral sensor wired or paired wireless with a computer. These devices do generate an image immediately during exposure and acquisition. The semi direct digital systems instead are based on phosphor image plates. Digital radiography offers many chances to improve our patient's healthcare standards reducing exposition to X-rays and the related stochastic radiation risk. Aim of this study is to compare the quality of images for endodontic purposes comparing three systems: conventional films, direct digital radiography and semidirect digital radiography.

Asunto(s)

RESUMEN

BACKGROUND: The development of specialized panoramic radiograph machine software has spawned the introduction of an innovative and promising dental radiographic examination type: extraoral bite-wings. But does this unconventional type of imaging belong in the bite-wing family? Is there any relationship at all to the conventional bite-wing radiograph? OBJECTIVES: The purpose of this article is not to make a case for the diagnostic effectiveness of one system over the other; this is best left to further clinical evaluation. Instead, the authors intend to provide an outline of a few key and distinguishing elements of the intraoral bite-wing radiographic examination followed by those of the extraoral panoramic substitute and draw attention to the importance of reimagining the increasingly universal naming convention of this novel radiographic examination, the paradoxical "extraoral bite-wing radiograph", based on the fundamental principles of each of these imaging systems. PRACTICAL IMPLICATIONS: The accuracy of clinical and technical terminology in oral radiography is of paramount importance to both the profession and patients, especially when considering emerging technologies.

Asunto(s)

RESUMEN

The dosimetry of intraoral radiography procedures is of great interest since dental examinations are among the most numerous radiological procedures. Usually, the surveys are performed using measurements free in air. The entrance surface air kerma (Ke) can be estimated from measurements of incident air kerma and the use of backscatter factors (BSF). The purpose of this work is to calculate BSF values suitable for intraoral radiography. In addition to specific intraoral radiography, a comprehensive reassessment of internationally recommended BSF values was performed through Monte Carlo simulations. Moreover, theKewas estimated using the calculated BSF values for a sample of 44 intraoral radiography systems. The interpolation of intraoral radiography BSF values from reference data can lead to an overestimation of up to 10% and 6% in comparison with the values calculated in this work for monoenergetic photons and x-ray spectra, respectively. Such discrepancy may be relevant when defining diagnostic reference levels (DRLs) or performing quality control tests. The calculations for a sample of 44 intraoral radiography systems showed that the majority of the equipment operates with an entrance surface air kerma higher than 3.5 mGy. In the case of adopting a single value to estimateKe, the use of BSF equal to 1.2 results in less dispersion compared to calculated values in this work and the use of 1.1 can underestimateKevalues up to 12%.

Asunto(s)

RESUMEN

The objective of the present study was to evaluate the intensity and spatial distribution of the scattered radiation caused by the use of hand-held x-ray equipment in the zone occupied by the operator, using the Monte Carlo simulation for radiographic views of the upper and lower incisor teeth, and the consequent evaluation of the equivalent dose in the lens. In order to carry out this evaluation, the geometry of a typical dental facility with plaster walls containing the scattering object was used for the computational scenario implemented for the Monte Carlo method simulation. The PENELOPE code for Monte Carlo simulation of electron and photon transport was used with the radiation beam represented by a 60 kV spectrum, 1.5 mm Al and tungsten target. The simulations were carried out with typical parameters for workload and the number of radiographs/week. The results showed that the exposure levels varied significantly according to the angle of the x-ray beam and with the distance to the scattering object. It is concluded that the incorporation of hand-held equipment in dental radiology must be accompanied by the surveillance of occupational exposure levels and a review of the training structure of professionals in dental radiology regarding aspects of radiological protection and the particularities of using this type of equipment.

Asunto(s)

RESUMEN

OBJECTIVE: To create and validate two new Image Receptor-Holding devices (IRHDs) to reduce proximal surfaces overlapping in bitewing radiography in comparison to a regular well-established and commercially available IRHD. METHODS: Two IRHDs for bitewing radiographs with a wedge on the biting surface were designed and 3D-printed. These IRHDs, with a large wedge (Pr-Lw) and small wedge (Pr-Sw), were compared with a regular commercially available IRHD (Rinn XCP®) during image acquisition of bitewing radiographs of four posterior regions (one upper region and three lower regions) in two dry skulls and mandibles. A total of 156 interproximal regions on bitewing radiographs were radiographed by 13 oral radiology graduate students and independently assessed by two oral radiologists (10 years of experience). IRHDs were compared by Cochran's Q test regarding the number of overlapped proximal surfaces in the acquired radiographs with a significance level of 5%. RESULTS: The observers were in perfect agreement (κ = 1.0) to classify the proximal surfaces overlapping. The Pr-Lw IRHD presented the lowest number of surfaces overlapping (19.2%) followed by the Pr-Sw IRHD (48.1%) and the XCP®IRHD with the highest surfaces overlapping (71.2%). The Pr-Lw IRHD surfaces overlapping was statistically different from the XCP IRHD (p < 0.001), and the Pr-Sw IRHD (p = 0.014). CONCLUSIONS: The Pr-Lw IRHD demonstrated the most efficient performance in overlapping surfaces reduction, compared with the Pr-Sw IRHD and the XCP® IRHD in adult dry skulls and mandibles.

Asunto(s)