Accuracy of advanced deep learning with tensorflow and keras for classifying teeth developmental stages in digital panoramic imaging

• Published in: BMC medical imaging Vol. 22; no. 1; pp. 66 - 13
• Main Authors: Mohammad, Norhasmira, Muad, Anuar Mikdad, Ahmad, Rohana, Yusof, Mohd Yusmiaidil Putera Mohd
• Format: Journal Article
• Language: English
• Published: London BioMed Central 08.04.2022; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Age; Algorithms; Artificial intelligence; Artificial neural networks; Automation; Background noise; Bicuspid - growth & development; Clustering; Deep Learning; Developmental stages; Digital dental panoramic radiographs; Digital imaging; Dynamic programming; Equipment and supplies; Forensic science; Humans; Image classification; Image enhancement; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Imaging; Machine learning; Mandible; Medical imaging equipment; Medicine; Medicine & Public Health; Methods; Model accuracy; Morphology; Neural networks; Neural Networks, Computer; Odontology; Premolar; Premolars; Radiology; Teeth; Tooth segmentation; Watersheds; Deep learning; Premolar; Tooth segmentation; Digital dental panoramic radiographs
• ISSN: 1471-2342; 1471-2342
• DOI: 10.1186/s12880-022-00794-6

Background This study aims to propose the combinations of image processing and machine learning model to segment the maturity development of the mandibular premolars using a Keras-based deep learning convolutional neural networks (DCNN) model. Methods A dataset consisting of 240 images (20 images per stage per sex) of retrospect digital dental panoramic imaging of patients between 5 and 14 years of age was retrieved. In image preprocessing, abounding box with a dimension of 250 × 250 pixels was assigned to the left mandibular first (P1) and second (P2) permanent premolars. The implementation of dynamic programming of active contour (DP-AC) and convolutions neural network on images that require the procedure of image filtration using Python TensorFlow and Keras libraries were performed in image segmentation and classification, respectively. Results Image segmentation using the DP-AC algorithm enhanced the visibility of the image features in the region of interest while suppressing the image's background noise. The proposed model has an accuracy of 97.74%, 96.63% and 78.13% on the training, validation, and testing set, respectively. In addition, moderate agreement (Kappa value = 0.58) between human observer and computer were identified. Nonetheless, a robust DCNN model was achieved as there is no sign of the model's over-or under-fitting upon the learning process. Conclusions The application of digital imaging and deep learning techniques used by the DP-AC and convolutions neural network algorithms to segment and identify premolars provides promising results for semi-automated forensic dental staging in the future.