Accuracy of mean grey density values obtained with small field of view cone beam computed tomography in differentiation between periapical cystic and solid lesions

A deep learning approach for radiological detection and classification of radicular cysts and periapical granulomas

OBJECTIVES

Dentists and oral surgeons often face difficulties distinguishing between radicular cysts and periapical granulomas on panoramic imaging. Radicular cysts require surgical removal while root canal treatment is the first-line treatment for periapical granulomas. Therefore, an automated tool to aid clinical decision making is needed.

METHODS

A deep learning framework was developed using panoramic images of 80 radicular cysts and 72 periapical granulomas located in the mandible. Additionally, 197 normal images and 58 images with other radiolucent lesions were selected to improve model robustness. The images were cropped into global (affected half of the mandible) and local images (only the lesion) and then the dataset was split into 90% training and 10% testing sets. Data augmentation was performed on the training dataset. A two-route convolutional neural network using the global and local images was constructed for lesion classification. These outputs were concatenated into the object detection network for lesion localization.

RESULTS

The classification network achieved a sensitivity of 1.00 (95% C.I. 0.63 - 1.00), specificity of 0.95 (0.86 - 0.99), and AUC (area under the receiver-operating characteristic curve) of 0.97 for radicular cysts and a sensitivity of 0.77 (0.46 - 0.95), specificity of 1.00 (0.93 - 1.00), and AUC of 0.88 for periapical granulomas. Average precision for the localization network was 0.83 for radicular cysts and 0.74 for periapical granulomas.

CONCLUSIONS

The proposed model demonstrated reliable diagnostic performance for the detection and differentiation of radicular cysts and periapical granulomas. Using deep learning, diagnostic efficacy can be enhanced leading to a more efficient referral strategy and subsequent treatment efficacy.

CLINICAL SIGNIFICANCE

A two-route deep learning approach using global and local images can reliably differentiate between radicular cysts and periapical granulomas on panoramic imaging. Concatenating its output to a localizing network creates a clinically usable workflow for classifying and localizing these lesions, enhancing treatment and referral practices.

Diagnostic Accuracy of Cystic Lesions Using a Pre-Programmed Low-Dose and Standard-Dose Dental Cone-Beam Computed Tomography Protocol: An Ex Vivo Comparison Study

Background: This study aimed to analyze the diagnostic reliability of radiographic assessment of cystic lesions using a pre-set, manufacturer-specific, low-dose mode compared to a standard-dose dental cone-beam computed tomography (CBCT) imaging protocol. Methods: Forty pig mandible models were prepared with cystic lesions and underwent both CBCT protocols on an Orthophos SL Unit (Dentsply-Sirona, Bensheim, Germany). Qualitative and quantitative analysis of CBCT data was performed by twelve investigators independently in SIDEXIS 4 (Dentsply-Sirona) using a trial-specific digital examination software tool. Thereby, the effect of the two dose types on overall detectability rate, the visibility on a scale of 1 (very low) to 10 (very high) and the difference between measured radiographic and actual lesion size was assessed. Results: Low-dose CBCT imaging showed no significant differences considering detectability (78.8% vs. 81.6%) and visibility (9.16 vs. 9.19) of cystic lesions compared to the standard protocol. Both imaging protocols performed very similarly in lesion size assessment, with an apparent underestimation of the actual size. Conclusion: Low-dose protocols providing confidential diagnostic evaluation with an improved benefit–risk ratio according to the ALADA principle could become a promising alternative as a primary diagnostic tool as well as for radiological follow-up in the treatment of cystic lesions.