Root fracture detection on digital images: effect of the zoom function

Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study

Using super-resolution (SR) algorithms, an image with a low resolution can be converted into a high-quality image. Our objective was to compare deep learning-based SR models to a conventional approach for improving the resolution of dental panoramic radiographs. A total of 888 dental panoramic radiographs were obtained. Our study involved five state-of-the-art deep learning-based SR approaches, including SR convolutional neural networks (SRCNN), SR generative adversarial network (SRGAN), U-Net, Swin for image restoration (SwinIr), and local texture estimator (LTE). Their results were compared with one another and with conventional bicubic interpolation. The performance of each model was evaluated using the metrics of mean squared error (MSE), peak signal-to-noise ratio (PNSR), structural similarity index (SSIM), and mean opinion score by four experts (MOS). Among all the models evaluated, the LTE model presented the highest performance, with MSE, SSIM, PSNR, and MOS results of 7.42 ± 0.44, 39.74 ± 0.17, 0.919 ± 0.003, and 3.59 ± 0.54, respectively. Additionally, compared with low-resolution images, the output of all the used approaches showed significant improvements in MOS evaluation. A significant enhancement in the quality of panoramic radiographs can be achieved by SR. The LTE model outperformed the other models.

Comparison between periapical radiography and cone beam computed tomography for the diagnosis of anterior maxillary trauma in children and adolescents

BACKGROUND/AIMS

Under-estimating the damage caused by trauma to the dental structures may delay treatment. Timely and accurate diagnosis remains challenging in clinical practice. Radiography is an important modality for the diagnosis of traumatic injuries. The aim of this study was to compare the efficacy of periapical radiography and cone beam computed tomography for the diagnosis of trauma to the anterior maxillary dentoalveolar region in children and adolescents.

MATERIAL AND METHODS

Images of patients who underwent both periapical radiography and cone beam computed tomography simultaneously because of trauma to the anterior maxillary region between January 2016 and January 2020 were analyzed retrospectively. Pairwise comparison between the receiver operating characteristic curves was performed to statistically compare the two methods for the diagnosis of crown fractures, root fractures, alveolar bone fractures and luxations, tooth resorption, and periapical radiolucencies.

RESULTS

A total of 190 patients met the inclusion criteria. There were 120 (63.2%) males and 70 (36.8%) females, with a mean age of 11.1 years (range: 6-17 years). A crown fracture was observed in 144 teeth, while a root fracture was observed in 71 teeth. Alveolar fracture and luxation were observed in 44 incisors. During follow-up, tooth resorption and periapical radiolucencies were observed in 25 and 33 teeth, respectively. Pairwise receiver operating characteristic curve analysis revealed that cone beam computed tomography was significantly superior to periapical radiography for the diagnosis of root fractures, alveolar fractures and luxations, and tooth resorption (p < .05). However, no significant differences were found for the diagnosis of crown fractures and periapical radiolucencies (p > .05).

CONCLUSIONS

Cone beam computed tomography in the low-dose mode was better for diagnosing root and bone fractures and resorption, but no different to periapical radiographs for crown fractures and periapical radiolucencies in pediatric patients.

Using super-resolution generative adversarial network models and transfer learning to obtain high resolution digital periapical radiographs

Periapical Radiographs are commonly used to detect several anomalies, like caries, periodontal, and periapical diseases. Even considering that digital imaging systems used nowadays tend to provide high-quality images, external factors, or even system limitations can result in a vast amount of radiographic images with low quality and resolution. Commercial solutions offer tools based on interpolation methods to increase image resolution. However, previous literature shows that these methods may create undesirable effects in the images affecting the diagnosis accuracy. One alternative is using deep learning-based super-resolution methods to achieve better high-resolution images. Nevertheless, the amount of data for training such models is limited, demanding transfer learning approaches. In this work, we propose the use of super-resolution generative adversarial network (SRGAN) models and transfer learning to achieve periapical images with higher quality and resolution. Moreover, we evaluate the influence of using the transfer learning approach and the datasets selected for it in the final generated images. For that, we performed an experiment comparing the performance of the SRGAN models (with and without transfer learning) with other super-resolution methods. Considering Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Mean Opinion Score (MOS), the results of SRGAN models using transfer learning were better on average. This superiority was also verified statistically using the Wilcoxon paired test. In the visual analysis, the high quality achieved by the SRGAN models, in general, is visible, resulting in more defined edges details and fewer blur effects.

Cone-beam computed tomography imaging of dentoalveolar and mandibular fractures

Three-dimensional imaging methods have an important role in the diagnosis of dentomaxillofacial fractures that can not be seen on the plain films. Cone-beam computed tomography (CBCT) is one of the three-dimensional imaging methods and has facilitated dental professionals' access to cross-sectional imaging. CBCT units allow different technical parameters and the data acquired by CBCT, can be reformatted. Osseous structures are correctly examined with this technique but the technique is not useful for the examination of soft tissues. Therefore, the purpose of its use should be based on the expected diagnostic gain. The aim of this review is to present the use of CBCT with different multi-planar reformatted sections and three-dimensional reconstructions of dentoalveolar and mandibular fractures.

Cone-beam CT in paediatric dentistry: DIMITRA project position statement

DIMITRA (dentomaxillofacial paediatric imaging: an investigation towards low-dose radiation induced risks) is a European multicenter and multidisciplinary project focused on optimizing cone-beam CT exposures for children and adolescents. With increasing use of cone-beam CT for dentomaxillofacial diagnostics, concern arises regarding radiation risks associated with this imaging modality, especially for children. Research evidence concerning cone-beam CT indications in children remains limited, while reports mention inconsistent recommendations for dose reduction. Furthermore, there is no paper using the combined and integrated information on the required indication-oriented image quality and the related patient dose levels. In this paper, therefore, the authors initiate an integrated approach based on current evidence regarding image quality and dose, together with the expertise of DIMITRA's members searching for a state of the art. The aim of this DIMITRA position statement is to provide indication-oriented and patient-specific recommendations regarding the main cone-beam CT applications in the pediatric field. The authors will review this position statement document when results regarding multidisciplinary approaches evolve, in a period of 5 years or earlier.

The Evaluation of Root Fracture with Cone Beam Computed Tomography (CBCT): An Epidemiological Study

Background

The aim of this study was evaluation of the cone-beam computed tomography (CBCT) image of 50 patients at the ages of 8-15 suspecting root fracture and root fracture occurred, exposed to dental traumatic. In additionally, this study was showed effect of crown fracture on root fracture healing.

Material and Methods

All of the individuals included in the study were obtained images with the cone-beam computed tomography range of 0,3 voxel and 8.9 seconds.(i-CAT®, Model 17-19, Imaging SciencesInternational, Hatfield, Pa USA).The information obtained from the history and CBCT images of patients were evaluated using chi-square test statistical method the mean and the distribution of the independent variables.

Results

50 children, have been exposed to trauma, was detected root fracture injury in 97 teeth. Horizontal root fracture 63.9% of the 97 tooth, the oblique in 31.9%, both the horizontal and oblique in 1.03%, partial fracture in 2.06% ,and both horizontally and vertical in 1.03% was observed.The most affected teeth, respectively of, are the maxillary central incisor (41.23% left, right, 37.11%), maxillary left lateral incisor (9.27%), maxillary right lateral incisor (11.34%), and mandibular central incisor (1.03%).

Conclusions

Crown fractures have negative effects on spontaneous healing of root fractures. CBCT are used selected as an alternative to with conventional radiography for diagnosis of root fractures. In particular, ıt's cross-sectional image is quite useful and has been provided more conveniences seeing the results of diagnosis and treatment for clinician. Key words:Root fracture, CBCT, Epidemiolog.

Evaluation of Root Fracture in endodontically treated Teeth using Cone Beam Computed Tomography

AIM

Our objective was to perform an in vitro evaluation of root fracture in endodontically treated teeth using two cone beam computed tomography (CBCT) machines.

MATERIALS AND METHODS

The sample comprised 86 single-rooted human premolars that had been fractured by a universal testing machine. The tomographic images were acquired using an Orthopantomograph OP300^® and an Orthophos XG 3D^® and evaluated by three examiners, by means of specific software. The teeth were classified into presence or absence of root fracture, then the root third where the fracture occurred, was determined. With regard to the detection of the fracture, the Kappa statistic was used for intra and interexaminer repro-ducibility at two distinct points in time. Chi-squared test was employed to analyze the sensitivity and specificity of the two tomographs (p < 0.05).

RESULTS

The results showed a good or excellent Kappa index between examiners. As for the absolute frequency, the sensitivity (0.6) of the Orthophos XG 3D^® equipment was superior, while specificity (0.91) was higher with the Orthopantomograph OP300^®. On the receiver operating characteristics curve, moderate performance was found with an accuracy of 0.73 (OrthopantomographOP300^®) and 0.74 (Orthophos XG 3D^®) respectively. As far as the location of the root fracture is concerned, moderate agreement was verified using the Kappa statistic (k = 0.56).

CONCLUSION

Although the regular CBCTs represent the imaging examination of choice for assisting root fracture diagnosis in endodontically treated teeth, their performance in this study demonstrated an imprecise diagnosis of fractures in a good many cases, irrespective of the tomography machine used.

CLINICAL SIGNIFICANCE

An early and precise detection of root fractures is of the utmost clinical importance, but the radiopaque and/or metallic filling materials in the CBCT viewing field may generate artifacts, known as the beam-hardening effect, which could compromise root fracture detection.

Assessment of vertical root fractures using three imaging modalities: cone beam CT, intraoral digital radiography and film

OBJECTIVES

The aim of this study was to assess the accuracy of cone beam CT (CBCT) in detecting vertical root fractures and to compare the accuracy with images from an intraoral sensor and from conventional intraoral film.

METHODS

60 extracted, single-rooted human teeth were divided equally into two groups: a control group of 30 teeth and an induced fracture group of 30 teeth. All teeth were randomly placed into sockets in six dry mandibles. Each tooth was imaged by three modalities: CBCT, intraoral digital radiography and intraoral F-speed film. Three beam angulations (an orthogonal projection and additional projections with ± 20° horizontal shifts of the central ray) were used when radiographs were made using film and a digital sensor. Three oral and maxillofacial radiologists evaluated the presence of root fractures twice in each image modality using a five-point confidence rating scale. Areas under receiver operating characteristic curves (A(z)) were computed for each observer and modality and were tested for statistical differences using the Kruskal-Wallis test.

RESULTS

There was no statistical difference in the performance of the three modalities (mean of A(z) values: CBCT = 0.811, film = 0.797 and sensor = 0.775; p = 0.771).

CONCLUSIONS

There was no significant difference between intraoral film, a high-resolution complementary metal oxide semiconductor digital imaging system and CBCT in detecting vertical root fractures in mandibular single-rooted teeth.

Detection of vertical root fractures using digitally enhanced images: reverse-contrast and colorization

Root fracture diagnosis is a clinical difficulty that in most cases can only be detected through radiography. The objective of this study was to compare the diagnostic accuracy of two types of digitally enhanced images (reverse-contrast and colorization) with original digital radiographies in detecting experimental root fractures. Two hundred extracted single-rooted human teeth were endodontically instrumented and then divided in two groups, one control group and one test group, including fractured teeth. Vertical root fractures were experimentally made in the fractured group. The digital image of each tooth was taken, using the paralleling technique. There were three groups of images: (i) original, (ii) reverse contrast, and (iii) colorized. Three experienced dental specialists examined the images with no prior knowledge of the distribution of the root fractures. Two-way analysis of variance was used to assess the differences in accuracy, sensitivity, and specificity of each technique in detecting root fractures. Cohen's kappa coefficients were calculated to investigate the degree of interobserver agreement. The accuracy, sensitivity, and specificity of original images were 67.4%, 66.7%, and 68%, respectively; these amounts were 61.5%, 61%, and 65.5% in reverse contrast images and 66.4%, 70.7%, and 62% in colorized digital radiography. The original images had the best inter observer kappa coefficients (between 0.45 and 0.55). The results showed that the accuracy of original images is better than reverse contrast and colorized images. Use of reverse-contrast and colorization digital images in root fracture detection should be regarded as an adjunct to other diagnostic methods not as a highly critical diagnostic aid.

Detection of experimentally induced root fractures on digital and conventional radiographs: an in vitro study

This study compared the diagnostic accuracy of digital radiographic images with conventional radiographs for the detection of experimentally induced root fractures. Horizontal fractures were induced by a mechanical force to the root of 15 single rooted teeth. Vertical fractures were induced in 15 single rooted teeth and 15 molars, respectively, by disk cutting. The teeth were mounted in dried mandibles and were radiographed with the parallel technique using a CCD-based Planmeca imaging system and F-speed films. Seven observers recorded their findings and then 2 pairs of them examined the same images together. Az values expressed the diagnostic accuracy of the imaging systems and the degree of agreement was estimated using the Cohen's kappa statistic. The areas under the ROC curves (Az) in single rooted teeth were 0.61 for conventional radiography and 0.64 for digital radiography. Digital imaging system did not perform significantly better than conventional one (p > 0.01). Digital radiographs (Az: 0.72) provided higher detection accuracy in molars than conventional images (Az: 0.51) (p = 0.0102). The digital images scored higher kappa values with narrower range than conventional. Observers in pairs did not perform significantly better than individually. The results were not affected by the observers but were affected by the cases (p < 0.001). Digital images were equivalent to F-speed films for the detection of root fractures in single rooted teeth. The digital system performed significantly better than the conventional in detecting root fractures in molars.

The effects of digital image enhancement on the detection of vertical root fracture

AIM

To determine the effects of digital image enhancement on observer ability to detect experimentally induced vertical root fractures (VRF).

MATERIAL AND METHODS

A total of 64 extracted human mandibular premolar teeth were used in this study. In 32 teeth, VRFs were created in the bucco-lingual planes by gently tapping with screw-type root-canal pins. The remaining 32 intact teeth served as a control group. Digital images were obtained using a charge coupled device sensor. Three observers separately examined the original and four types of digitally enhanced images (enhanced using sharpness, zoom-in, reverse-contrast, and pseudo-3D functions) at 1-week intervals. All teeth were evaluated using a 5-point scale for the presence/absence of VRF. Evaluations of each image set were repeated 1 month after the initial viewings. Kappa coefficients were calculated to investigate the degree of intra- and inter-observer agreement. The areas under the receiver operating characteristic (ROC) curves (Az values) were calculated using the MedCalc statistical software. ROC values for each image type, observer and viewing were compared using t-tests. A level of alpha = 0.05 was considered significant.

RESULTS

Kappa coefficients for intra-observer agreement ranged from 0.304 to 0.679. Inter-observer agreement kappa values ranged from 0.109 to 0.399 for the first reading and from 0.106 to 0.380 for the second reading. Statistical comparisons between Az values for each observer showed no significant differences (P > 0.05) among image types.

CONCLUSION

There were no differences in diagnostic outcomes among differently enhanced images in the in vitro detection of VRF.

Effectiveness of limited cone-beam computed tomography in the detection of horizontal root fracture

To compare the diagnostic accuracy of conventional film radiography, charge coupled device (CCD) and photostimulable phosphor plate (PSP) digital images and limited cone-beam computed tomography in detecting simulated horizontal root fracture. Root fractures were created in the horizontal plane in 18 teeth by a mechanical force and fragments were relocated. Another 18 intact teeth with no horizontal root fracture served as a control group. Thirty-six teeth were placed in the respective empty maxillary anterior sockets of a human dry skull in groups three by three. Intraoral radiographs were obtained in three different vertical views by utilizing Eastman Kodak E-speed film, CCD sensor, RVG 5.0 Trophy and a PSP sensor Digora, Optime. Cone beam CT images were taken with a unit (3D Accuitomo; J Morita MFG. Corp, Kyoto, Japan). Three dental radiologists separately examined the intraoral film, PSP, CCD and cone beam CT images for the presence of horizontal root fracture. Specificity and sensitivity for each radiographic technique were calculated. Kappa statistics was used for assessing the agreement between observers. Chi-square statistics was used to determine whether there were differences between the systems. Results were considered significant at P < 0.05. Cone beam CT images revealed significantly higher sensitivities (P < 0.05) than the intraoral systems between which no significant differences were found. Specificities did not show any statistically significant differences between any of the four systems. The kappa values for inter-observer agreement between observers (four pairs) ranged between 0.82-0.90 for the 3DX evaluations and between 0.63-0.71 for the different types of intraoral images. Limited cone beam CT, outperformed the two-dimensional intraoral, conventional as well as digital, radiographic methods in detecting simulated horizontal root fracture.

Accuracy of zoomed digital image in the detection of periodontal bone defect: in vitro study

OBJECTIVES

(1) To evaluate the intraobserver agreement related to image interpretation and (2) to compare the accuracy of 100%, 200% and 400% zoomed digital images in the detection of simulated periodontal bone defects.

METHODS

Periodontal bone defects were created in 60 pig hemi-mandibles with slow-speed burs 0.5 mm, 1.0 mm, 1.5 mm, 2.0 mm and 3.0 mm in diameter. 180 standardized digital radiographs were made using Schick sensor and evaluated at 100%, 200% and 400% zooming. The intraobserver agreement was estimated by Kappa statistic (kappa). For the evaluation of diagnostic accuracy receiver operating characteristic (ROC) analysis was performed followed by chi-square test to compare the areas under ROC curves according to each level of zooming.

RESULTS

For 100%, 200% and 400% zooming the intraobserver agreement was moderate (kappa=0.48, kappa=0.54 and kappa=0.43, respectively) and there were similar performances in the discrimination capacity, with ROC areas of 0.8611 (95% CI: 0.7660-0.9562), 0.8600 (95% CI: 0.7659-0.9540), and 0.8368 (95% CI: 0.7346-0.9390), respectively, with no statistical significant differences (chi2-test; P=0.8440).

CONCLUSIONS

A moderate intraobserver agreement was observed in the classification of periodontal bone defects and the 100%, 200% and 400% zoomed digital images presented similar performances in the detection of periodontal bone defects.

Imaging of maxillofacial trauma: Evolutions and emerging revolutions

The aim of diagnostic imaging for maxillofacial trauma is to provide additional information that can positively influence medical or surgical patient management. Current advances in diagnostic imaging have come from the confluence of 3 driving forces: (1) the demand from clinicians to enhance and expand their diagnostic abilities; (2) the development of new theoretical concepts by basic scientists; and (3) the application of concepts by engineers and manufacturers to provide increasingly sophisticated imaging capabilities. The role of imaging within the health care environment is, however, also buffeted by the complex, sometimes competing, interactions of external social, political, economic, and technological pressures at the national, regional, and local levels. The purposes of this review are to provide a perspective on current imaging modalities used for maxillofacial trauma and to provide an insight into the influences, both technologic and external, on future developments and applications.