ABSTRACT
PURPOSE: Periodontitis is the sixth most prevalent disease worldwide and periodontal bone loss (PBL) detection is crucial for its early recognition and establishment of the correct diagnosis and prognosis. Current radiographic assessment by clinicians exhibits substantial interobserver variation. Computer-assisted radiographic assessment can calculate bone loss objectively and aid in early bone loss detection. Understanding the rate of disease progression can guide the choice of treatment and lead to early initiation of periodontal therapy. METHODOLOGY: We propose an end-to-end system that includes a deep neural network with hourglass architecture to predict dental landmarks in single, double and triple rooted teeth using periapical radiographs. We then estimate the PBL and disease severity stage using the predicted landmarks. We also introduce a novel adaptation of MixUp data augmentation that improves the landmark localisation. RESULTS: We evaluate the proposed system using cross-validation on 340 radiographs from 63 patient cases containing 463, 115 and 56 single, double and triple rooted teeth. The landmark localisation achieved Percentage Correct Keypoints (PCK) of 88.9%, 73.9% and 74.4%, respectively, and a combined PCK of 83.3% across all root morphologies, outperforming the next best architecture by 1.7%. When compared to clinicians' visual evaluations of full radiographs, the average PBL error was 10.69%, with a severity stage accuracy of 58%. This simulates current interobserver variation, implying that diverse data could improve accuracy. CONCLUSIONS: The system showed a promising capability to localise landmarks and estimate periodontal bone loss on periapical radiographs. An agreement was found with other literature that non-CEJ (Cemento-Enamel Junction) landmarks are the hardest to localise. Honing the system's clinical pipeline will allow for its use in intervention applications.
Subject(s)
Alveolar Bone Loss/diagnosis , Neural Networks, Computer , Periodontitis/diagnosis , Radiography/methods , Humans , Observer VariationABSTRACT
Background: Many smokers have undiagnosed chronic obstructive pulmonary disease(COPD), and yet screening for COPD is not recommended. Smokers who know that they haveairflow limitation are more likely to quit smoking. This study aims to identify the prevalence andpredictors of airflow limitation among smokers in primary care.Methods: Current smokers ≥ 40 years old who were asymptomatic clinic attendees in aprimary care setting were recruited consecutively for two months. We used a two-step strategy.Step 1: participants filled in a questionnaire. Step 2: Assessment of airflow limitation using apocket spirometer. Multiple logistic regression was utilised to determine the best risk predictorsfor airflow limitation.Results: Three hundred participants were recruited. Mean age was 58.35 (SD 10.30) yearsold and mean smoking history was 34.56 pack-years (SD 25.23). One in two smokers were found tohave airflow limitation; the predictors were Indian ethnicity, prolonged smoking pack-year historyand Lung Function Questionnaire score ≤ 18. Readiness to quit smoking and the awareness ofCOPD were low.Conclusions: The high prevalence of airflow limitation and low readiness to quit smokingimply urgency with helping smokers to quit smoking. Identifying airflow limitation as an additionalmotivator for smoking cessation intervention may be considered. A two-step case-finding methodis potentially feasible.
