Bone Loss Estimation in Periodontitis Using Machine Learning on Periapicals

Objectives: To develop an automatic analysis of periapical radiographs from periodontitis patients and non-periodontitis subjects for the % alveolar bone loss (ABL) on the approximal surfaces of teeth using a machine learning technique based on artificial intelligence, i.e. convolutional neural networks (CNN).
Methods: A total of 1546 approximal sites from 54 subjects on mandibular periapical radiographs were manually annotated (MA) for a training set (n=1308), a validation set (n=98) and a test set (n=140). The training and validation sets were used for the development of a CNN algorithm. The algorithm recognized the cemento-enamel junction, the most apical extent of the alveolar crest, the apex and the surrounding alveolar bone.
Results: For 140 unseen images in the test set, the CNN scored a mean of 23.1 ± 11.8 %ABL, while the corresponding value for MA was 27.8 ± 13.8 %ABL. The intraclass correlation (ICC) was 0.0601 (p<0.001). Further sub-analyses for various tooth types and various bone loss patterns showed that ICC’s remained significant although the algorithm performed better on incisors than molars.
Conclusions: A CNN trained algorithm on radiographic images, showed a diagnostic performance with moderate to good reliability to detect and quantify %ABL in unseen periapical radiographs.