The detection and classification of cystic lesions of the jaw is of high clinical relevance and represents a topic of interest in medical artificial intelligence research. The human clinical diagnostic reasoning process uses contextual information, including the spatial relation of the detected lesion to other anatomical structures, to establish a preliminary classification. Here, we aimed to emulate clinical diagnostic reasoning step by step by using a combined object detection and image segmentation approach on panoramic radiographs (OPGs). We used a multicenter training dataset of 855 OPGs (all positives) and an evaluation set of 384 OPGs (240 negatives). We further compared our models to an international human control group of ten dental professionals from seven countries. The object detection model achieved an average precision of 0.42 (intersection over union (IoU): 0.50, maximal detections: 100) and an average recall of 0.394 (IoU: 0.50–0.95, maximal detections: 100). The classification model achieved a sensitivity of 0.84 for odontogenic cysts and 0.56 for non-odontogenic cysts as well as a specificity of 0.59 for odontogenic cysts and 0.84 for non-odontogenic cysts (IoU: 0.30). The human control group achieved a sensitivity of 0.70 for odontogenic cysts, 0.44 for non-odontogenic cysts, and 0.56 for OPGs without cysts as well as a specificity of 0.62 for odontogenic cysts, 0.95 for non-odontogenic cysts, and 0.76 for OPGs without cysts. Taken together, our results show that a combined object detection and image segmentation approach is feasible in emulating the human clinical diagnostic reasoning process in classifying cystic lesions of the jaw.

Although the association between risk factors and non-surgical root canal treatment (NSRCT) failure has been extensively studied, methods to predict the outcomes of NSRCT are in an early stage, and dentists currently make the treatment prognosis based mainly on their clinical experience. Since this involves different sources of error, we investigated the use of machine learning (ML) models as a second opinion to support the clinical decision on whether to perform NSRCT. We undertook a retrospective study of 119 confirmed and not previously treated Apical Periodontitis cases that received the same treatment by the same specialist. For each patient, we recorded the variables from a newly proposed data collection template and defined a binary outcome: Success if the lesion clears and failure otherwise. We conducted tests for detecting the association between the variables and the outcome and selected a set of variables as the initial inputs into four ML algorithms: Logistic Regression (LR), Random Forest (RF), Naive-Bayes (NB), and K Nearest Neighbors (KNN). According to our results, RF and KNN significantly improve (p-values < 0.05) the sensitivity and accuracy of the dentist’s treatment prognosis. Taking our results as a proof of concept, we conclude that future randomized clinical trials are worth designing to test the clinical utility of ML models as a second opinion for NSRCT prognosis.

Background/Objectives In a previous study, we utilized categorical variables and Machine Learning (ML) algo-rithms to predict the success of non-surgical root canal treatments (NSRCTs) in apical periodontitis (AP), classifying the outcome as either success (healed) or failure (not healed). Given the importance of radiographic imaging in diagnosis, the present study evaluates the efficacy of Deep Learning (DL) in predicting NSRCT outcomes using two-dimensional (2D) periapical radiographs, comparing its performance with ML models. Methods The DL model was trained and validated using Leave-One-Out Cross-Validation (LOOCV). Its output was incorporated into the set of categorical variables, and the ML study was reproduced using Backward Stepwise Selection (BSS). The chi-square test was applied to assess the association between this new variable and NSRCT outcomes. Finally, after identifying the best-performing method from the ML study reproduction, statistical comparisons were conducted between this method, clinical professionals, and the im-age-based model using Fisher’s Exact Test. Results The association study yielded a p-value of 0.000000127, highlighting the predictive ca-pability of 2D radiographs. After incorporating the DL-based predictive variable, the ML algorithm that demonstrated the best performance was Logistic Regression (LR), differing from the previous study, where Random Forest (RF) was the top performer. When comparing the Deep Learning – Logistic Regression (DL-LR) model with the clinician’s prognosis (DP), DL-LR showed superior performance with a statistically significant dif-ference (p-value < 0.05) in sensitivity, NPV, and accuracy. The same trend was observed in the DL vs. DP comparison. However, no statistically significant differences were found in the comparisons of RF vs. DL-LR, RF vs. DL, and DL vs. DL-LR. Conclusions The findings of this study suggest that image-based artificial intelligence models exhibit superior predictive capability compared to those relying exclusively on categorical data. Moreover, they outperform clinician prognosis.