Evaluation of Efficacy of Artificial Intelligence in Orthopantomogram in Detecting and Classifying Radiolucent Lesions

Abstract Aim and Objective: The objective of our study was to build a convolutional neural network (CNN) model and detection and classification of benign and malignant radiolucent lesions in orthopantomogram (OPG) by implementing CNN. Method: Two basic CNN models were implemented on Anaconda with Python 3 on 64-bit, CNN-I for detection of radiolucency and CNN-II for classification of radiolucency into benign and malignant lesions. One hundred fifty eight OPG with radiolucency and 115 OPG without radiolucency was used for training and validation of CNN models. Data augmentation was performed for the training and validation dataset. The evaluation of the performance of both CNN by new data consisting (60 OPG images) 30 benign and 30 malignant lesions. Statistical Analysis: Performed using SPSS (Statistical package for social science) 20.0 version. The descriptive statistics was performed. The Cohen kappa correlation coefficient was used for assessment of reliability of the diagnostic methods. P < .05 was considered statistically significant. Determination of sensitivity, specificity, positive and negative predictive value was also performed. Result: CNN-I showing sensitivity for detection of the benign lesion is 76.6% and sensitivity for the malignant lesion is 63.3% with overall sensitivity is 70%. CNN-II showing sensitivity for classification of the benign lesion is 70% and for classification of the malignant lesion is 63.3% with overall classification sensitivity is 66.6%. The kappa correlation coefficient value for diagnosis made by CNN-II is 0.333 and P < .05. Conclusion: Both CNN showed statistically significant and satisfactory results in detecting and classifying radiolucency in OPG.