12 July 2023

---

Artificial intelligence in the diagnosis of gingivitis

Lara Figini

---

Periodontal disease is a chronic inflammatory disease that affects the periodontium and is classified into gingivitis and periodontitis with reversible and irreversible tissue damage. The prevalence of periodontal disease is estimated to be over 50% worldwide and nearly one third are severe cases, defined as clinical attachment loss greater than five mm and bone loss greater than 30%, according to the World Health Organization.

Periodontal disease is caused by the accumulation of plaque or biofilm along the gumline, resulting in localized gingival inflammation and ongoing host response. It is difficult to maintain satisfactory plaque control by patients without ongoing supervision by a professional hygienist or dentist. Artificial intelligence can be used to provide a visual check and automated continuous advice via intraoral photographs.

There are currently several network architectures used to detect gingivitis via intraoral photographs with accuracy ranging from 0.47 to 0.83, with 1.00 being the maximum accuracy value. The accuracy of any diagnostic system for clinical use should be as high as possible, and the precision should be at least 0.90 or better for clinical use.

The purpose of the following study was to accurately predict the gingival health status, in terms of sensitivity and specificity, through a new artificial intelligence system built with DeepLabv3+, after training with an adequate number of intraoral photographs.

Materials and methods

In a study published in the International Dental Journal in April 2023, the authors developed and validated a new artificial intelligence system that can be used to diagnose gingivitis via intraoral photographs without the intervention of the human eye. The authors collected front view intraoral photographs that met the inclusion criteria. In this study the artificial intelligence network architecture used was DeepLabv3+, based on Keras (v2.12, Google LLC) with TensorFlow 2 (v2.9, Google LLC). This neural network is highly transferable and offers multiple pre-trained control points to facilitate learning of the datasets.

Along the gingival margin, the gingival condition of individual sites was labeled as healthy, diseased, or questionable. Photographs were randomly assigned as a training or validation data set. Training datasets were fed into the new AI system and its accuracy in detecting gingivitis including sensitivity, specificity and intersection mean. Accuracy was reported according to the STARD-2015 statement.

Results 

A total of 567 intraoral photographs were collected and recorded, of which 80%. used for training and 20% for validation. Regarding the training datasets there were a total of 113,745,208 pixels with 9,270,413; 5,711,027; and 4,596,612 pixels labeled as healthy, ill and doubtful respectively. As for the validation datasets, they were 28,319,607 pixels with 1,732,031; 1,866,104; and 1,116,493 pixels labeled healthy, sick, and doubtful, respectively. The AI correctly predicted 1,114,623 healthy and 1,183,718 diseased pixels with a sensitivity of 0.92 and a specificity of 0.94. The average intersection on system join was found to be 0.60 and above the commonly accepted threshold of 0.50.

Conclusions

From the data of this study, which must be confirmed in other similar studies, it can be concluded that artificial intelligence could identify specific sites with and without gingival inflammation, with high sensitivity and high specificity on par with human visual examination.

For more information: "Accuracy of Artificial Intelligence-Based Photographic Detection of Gingivitis."