RESUMEN
AIM: To develop a new approach for locating the minor apical foramen (AF) using feature-extracting procedures from radiographs and then processing data using an artificial neural network (ANN) as a decision-making system. METHODOLOGY: Fifty straight single-rooted teeth were selected and placed in a socket within the alveolar bone of a dried skull. Access cavities were prepared and a file was place in the canals to determine the working length. A radiograph was taken to evaluate the location of the file in relation to the minor foramen and further checked after retrieving the tooth from the alveolar socket. The location of the file tip was categorized into: beyond the AF (long), within the root canal (short) and just at the minor AF (exact). Each radiograph was used to extract relevant features using K-means, Otsu method and Wavelet protocol. Thirty-six extracted features were used for training and the rest were used for evaluating the multi-layer Perceptron ANN model. RESULTS: Analysis of the images from radiographs (test samples) by ANN showed that in 93% of the samples, the location of the AF had been determined correctly by false rejection and acceptation error methods. CONCLUSION: Artificial neural networks can act as a second opinion to locate the AF on radiographs to enhance the accuracy of working length determination by radiography. In addition, ANN can function as a decision-making system in various similar clinical situations.