Limitations of panoramic radiography in the detection of bone defects in the posterior wall of the maxillary sinus: an experimental study

Automatic Segmentation of Teeth, Crown-Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls

BACKGROUND

The aim of our study is to provide successful automatic segmentation of various objects on orthopantomographs (OPGs).

METHODS

8138 OPGs obtained from the archives of the Department of Dentomaxillofacial Radiology were included. OPGs were converted into PNGs and transferred to the segmentation tool's database. All teeth, crown-bridge restorations, dental implants, composite-amalgam fillings, dental caries, residual roots, and root canal fillings were manually segmented by two experts with the manual drawing semantic segmentation technique.

RESULTS

The intra-class correlation coefficient (ICC) for both inter- and intra-observers for manual segmentation was excellent (ICC > 0.75). The intra-observer ICC was found to be 0.994, while the inter-observer reliability was 0.989. No significant difference was detected amongst observers (p = 0.947). The calculated DSC and accuracy values across all OPGs were 0.85 and 0.95 for the tooth segmentation, 0.88 and 0.99 for dental caries, 0.87 and 0.99 for dental restorations, 0.93 and 0.99 for crown-bridge restorations, 0.94 and 0.99 for dental implants, 0.78 and 0.99 for root canal fillings, and 0.78 and 0.99 for residual roots, respectively.

CONCLUSIONS

Thanks to faster and automated diagnoses on 2D as well as 3D dental images, dentists will have higher diagnosis rates in a shorter time even without excluding cases.

Aux-MVNet: Auxiliary Classifier-Based Multi-View Convolutional Neural Network for Maxillary Sinusitis Diagnosis on Paranasal Sinuses View

Computed tomography (CT) is undoubtedly the most reliable and the only method for accurate diagnosis of sinusitis, while X-ray has long been used as the first imaging technique for early detection of sinusitis symptoms. More importantly, radiography plays a key role in determining whether or not a CT examination should be performed for further evaluation. In order to simplify the diagnostic process of paranasal sinus view and moreover to avoid the use of CT scans which have disadvantages such as high radiation dose, high cost, and high time consumption, this paper proposed a multi-view CNN able to faithfully estimate the severity of sinusitis. In this study, a multi-view convolutional neural network (CNN) is proposed which is able to accurately estimate the severity of sinusitis by analyzing only radiographs consisting of Waters’ view and Caldwell’s view without the aid of CT scans. The proposed network is designed as a cascaded architecture, and can simultaneously provide decisions for maxillary sinus localization and sinusitis classification. We obtained an average area under the curve (AUC) of 0.722 for maxillary sinusitis classification, and an AUC of 0.750 and 0.700 for the left and right maxillary sinusitis, respectively, using the proposed network.

A deep transfer learning approach for the detection and diagnosis of maxillary sinusitis on panoramic radiographs

To investigate the use of transfer learning when applying a deep learning source model from one institution (institution A) to another institution (institution B) for creating effective models (target models) for the detection of maxillary sinuses and diagnosis of maxillary sinusitis on panoramic radiographs. In addition, to determine appropriate numbers of training data for the transfer learning. Source model was created using 350 panoramic radiographs from institution A as training data. Transfer learning was performed by adding 25, 50, 100, 150, or 225 panoramic radiographs as training data from institution B to the source model; this yielded the target models T25, T50, T100, T150 and T225. Each model was then evaluated using test data that comprised 40 images from institution A, 30 images from institution B. The performance indices (recall, precision and F1 score) for detecting the maxillary sinuses by the source model exceeded 0.98 when using test data A from institution A, but they deteriorated when using test data B from institution B. In the evaluation of target models using test data B, model T25 showed improved detection performance (recall of 0.967). The diagnostic performance of model T50 for maxillary sinusitis exceeded 0.9 in sensitivity. Transfer learning, which involves applying a small amount of data to the source model, yielded high performances in detecting the maxillary sinuses and diagnosing the maxillary sinusitis on panoramic radiographs. This study serves as a reference when adapting source models to other institutions.

Deep-learning classification using convolutional neural network for evaluation of maxillary sinusitis on panoramic radiography

OBJECTIVES

To apply a deep-learning system for diagnosis of maxillary sinusitis on panoramic radiography, and to clarify its diagnostic performance.

METHODS

Training data for 400 healthy and 400 inflamed maxillary sinuses were enhanced to 6000 samples in each category by data augmentation. Image patches were input into a deep-learning system, the learning process was repeated for 200 epochs, and a learning model was created. Newly-prepared testing image patches from 60 healthy and 60 inflamed sinuses were input into the learning model, and the diagnostic performance was calculated. Receiver-operating characteristic (ROC) curves were drawn, and the area under the curve (AUC) values were obtained. The results were compared with those of two experienced radiologists and two dental residents.

RESULTS

The diagnostic performance of the deep-learning system for maxillary sinusitis on panoramic radiographs was high, with accuracy of 87.5%, sensitivity of 86.7%, specificity of 88.3%, and AUC of 0.875. These values showed no significant differences compared with those of the radiologists and were higher than those of the dental residents.

CONCLUSIONS

The diagnostic performance of the deep-learning system for maxillary sinusitis on panoramic radiographs was sufficiently high. Results from the deep-learning system are expected to provide diagnostic support for inexperienced dentists.

Utilization of computer-aided detection system in diagnosing unilateral maxillary sinusitis on panoramic radiographs

OBJECTIVES

It is unclear whether computer-aided detection (CAD) systems for panoramic radiography can help inexperienced dentists to diagnose maxillary sinusitis. The aim of this study was to clarify whether a CAD system for panoramic radiography can contribute to improved diagnostic performance for maxillary sinusitis by inexperienced dentists.

METHODS

The panoramic radiographs of 49 patients with maxillary sinusitis and 49 patients with healthy sinuses were evaluated in this study. The diagnostic performance of the CAD system was determined. 12 inexperienced dentists and 4 expert oral and maxillofacial radiologists observed the total of 98 panoramic radiographs and judged the presence or absence of maxillary sinusitis, under conditions with and without the support of the CAD system. The receiver operating characteristic curves of the two groups were compared.

RESULTS

The CAD system provided sensitivity of 77.6%, specificity of 69.4% and accuracy of 73.5%. The diagnostic performance of the inexperienced dentists increased with the support of the CAD system. When the inexperienced dentists diagnosed maxillary sinusitis with CAD support, the area under the curve (AUC) was significantly higher than that without CAD support. When the focus was only on panoramic radiographs in which CAD support led to a correct diagnosis, the AUC of the inexperienced dentists increased to an equivalent level to that of the experienced radiologists.

CONCLUSIONS

The CAD system supported the inexperienced dentists in diagnosing maxillary sinusitis on the panoramic radiographs. If the accuracy of the CAD system can be increased, the benefits of CAD support will be further enhanced.

The significance of cone beam computed tomography for the visualization of anatomical variations and lesions in the maxillary sinus for patients hoping to have dental implant-supported maxillary restorations in a private dental office in Japan

Objectives

The purpose of the present study was to elucidate the significance of cone bean computed tomography (CBCT) for patients hoping to undergo implant-supported restorations of the maxilla. Therefore, two studies were planned. One was to compare the prevalence of anatomic variations and lesions in the maxillary sinus on CBCT of patients hoping to undergo implant-supported restorations of the maxilla with that in patients with other chief complaints in a private dental office in Japan. The other study was to elucidate the limitations of panoramic radiographs in the detection of anatomic variations and lesions in the maxillary sinus.

Study design

Sixty-one pairs of panoramic radiographs and CBCT were retrospectively analyzed in two groups of patients, those who hoped to undergo implant-supported restorations in the maxilla (Implant group) and those who did not (Non-implant group). The presence of anatomic variations and lesions in the maxillary sinus were analyzed.

Results

The detection rate of mucosal thickening was significantly higher in the Implant group than in the Non-implant group. The detection rates for the features analyzed were significantly lower on panoramic radiographs. In particular, the detection rates of internal and anterior locations of some features were noticeably lower on panoramic radiographs. A significant relationship was found between the change in the detection rate on panoramic radiographs and the widths of mucosal thickening or the lengths of the major axis of SOLs in the maxillary sinus. If the width of mucosal thickening or the length of the major axis of SOLs was <3 mm or <4 mm, respectively, the detection rate on panoramic radiographs was significantly decreased.

Conclusion

CBCT is important for patients hoping to undergo implant-supported restorations of the maxilla because of the mucosal thickening in the maxillary sinus in such patients and their lower detection rates on panoramic radiographs.

Quantitative analyses of maxillary sinus using computed tomography

The aim of this study was to evaluate the precision and accuracy of linear measurements of maxillary sinus made in tomographic films, by comparing with 3D reconstructed images. Linear measurements of both maxillary sinus in computed tomography CT of 17 patients, with or without lesion by two calibrated examiners independently, on two occasions, with a single manual caliper. A third examiner has done the same measurements electronically in 3D-CT reconstruction. The statistical analysis was performed using ANOVA (analyses of variance). Intra-observer percentage error was little in both cases, with and without lesion; it ranged from 1.14% to 1.82%. The inter-observer error was a little higher reaching a 2.08% value. The accuracy presented a higher value. The perceptual accuracy error was higher in samples, which had lesion compared to that which had not. CT had provided adequate precision and accuracy for maxillary sinus analyses. The precision in cases with lesion was considered inferior when compared to that without lesion, but it can't affect the method efficacy.

Three-dimensional images contribute to the diagnosis of mucous retention cyst in maxillary sinus

OBJECTIVE

To evaluate the detection of mucous retention cyst of maxillary sinus (MRCMS) using panoramic radiography and cone beam computed tomography (CBCT).

STUDY DESIGN

A digital database with 6,000 panoramic radiographs was reviewed for MRCMS. Suggestive images of MRCMS were detected on 185 radiographs, and patients were located and invited to return for follow-up. Thirty patients returned, and control panoramic radiographs were obtained 6 to 46 months after the initial radiograph. When MRCMS was found on control radiographs, CBCT scans were obtained. Cysts were measured and compared on radiographs and scans. The Wilcoxon, Spearman and Kolmorogov-Smirnov tests were used for statistical analysis. The level of significance was set at 5%.

RESULTS

There were statistically significant differences between the two methods (p<0.05): 23 MRCMS detected on panoramic radiographs were confirmed by CBCT, but 5 MRCMS detected on CBCT images had not been identified by panoramic radiography. Eight MRCMS detected on control radiographs were not confirmed by CBCT. MRCMS size differences from initial to control panoramic radiographs and CBCT scans were not statistically significant (p= 0.617 and p= 0.626). The correlation between time and MRCMS size differences was not significant (r = -0.16, p = 0.381).

CONCLUSION

CBCT scanning detect MRCMS more accurately than panoramic radiography.