Dataset Information

Deep Learning for the Radiographic Detection of Periodontal Bone Loss.

ABSTRACT: We applied deep convolutional neural networks (CNNs) to detect periodontal bone loss (PBL) on panoramic dental radiographs. We synthesized a set of 2001 image segments from panoramic radiographs. Our reference test was the measured % of PBL. A deep feed-forward CNN was trained and validated via 10-times repeated group shuffling. Model architectures and hyperparameters were tuned using grid search. The final model was a seven-layer deep neural network, parameterized by a total number of 4,299,651 weights. For comparison, six dentists assessed the image segments for PBL. Averaged over 10 validation folds the mean (SD) classification accuracy of the CNN was 0.81 (0.02). Mean (SD) sensitivity and specificity were 0.81 (0.04), 0.81 (0.05), respectively. The mean (SD) accuracy of the dentists was 0.76 (0.06), but the CNN was not statistically significant superior compared to the examiners (p = 0.067/t-test). Mean sensitivity and specificity of the dentists was 0.92 (0.02) and 0.63 (0.14), respectively. A CNN trained on a limited amount of radiographic image segments showed at least similar discrimination ability as dentists for assessing PBL on panoramic radiographs. Dentists' diagnostic efforts when using radiographs may be reduced by applying machine-learning based technologies.

SUBMITTER: Krois J

PROVIDER: S-EPMC6560098 | biostudies-literature | 2019 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning for the Radiographic Detection of Periodontal Bone Loss.

Krois Joachim J Ekert Thomas T Meinhold Leonie L Golla Tatiana T Kharbot Basel B Wittemeier Agnes A Dörfer Christof C Schwendicke Falk F

Scientific reports 20190611 1

We applied deep convolutional neural networks (CNNs) to detect periodontal bone loss (PBL) on panoramic dental radiographs. We synthesized a set of 2001 image segments from panoramic radiographs. Our reference test was the measured % of PBL. A deep feed-forward CNN was trained and validated via 10-times repeated group shuffling. Model architectures and hyperparameters were tuned using grid search. The final model was a seven-layer deep neural network, parameterized by a total number of 4,299,651 ...[more]

PMID: 31186466

Similar Datasets

Project description:The highly rapid spread of the current pandemic has quickly overwhelmed hospitals all over the world and motivated extensive research to address a wide range of emerging problems. The unforeseen influx of COVID-19 patients to hospitals has made it inevitable to deploy a rapid and accurate triage system, monitor progression, and predict patients at higher risk of deterioration in order to make informed decisions regarding hospital resource management. Disease detection in radiographic scans, severity estimation, and progression and prognosis prediction have been extensively studied with the help of end-to-end methods based on deep learning. The majority of recent works have utilized a single scan to determine severity or predict progression of the disease. In this paper, we present a method based on deep sequence learning to predict improvement or deterioration in successive chest X-ray scans and build a mathematical model to determine individual patient disease progression profile using successive scans. A deep convolutional neural network pretrained on a diverse lung disease dataset was used as a feature extractor to generate the sequences. We devised three strategies for sequence modeling in order to obtain both fine-grained and coarse-grained features and construct sequences of different lengths. We also devised a strategy to quantify positive or negative change in successive scans, which was then combined with age-related risk factors to construct disease progression profile for COVID-19 patients. The age-related risk factors allowed us to model rapid deterioration and slower recovery in older patients. Experiments conducted on two large datasets showed that the proposed method could accurately predict disease progression. With the best feature extractor, the proposed method was able to achieve AUC of 0.98 with the features obtained from radiographs. Furthermore, the proposed patient profiling method accurately estimated the health profile of patients.

Project description:RATIONALE:Osteoporosis is common in individuals with chronic obstructive pulmonary disease. Lung-specific factors, including radiographic emphysema, independently associate with low bone mineral density in cross-sectional smoking cohorts. However, factors associated with progressive bone loss in smokers are understudied and largely unknown. OBJECTIVES:To determine the relationship between radiographic emphysema, circulating bone metabolism markers, and pulmonary function and accelerated bone mineral density loss in smokers. METHODS:Two hundred and forty male and female current and former smokers, 40 years of age or older, underwent baseline and 2-year assessments of pulmonary function, computed tomography-assessed emphysema, dual X-ray absorptiometry-measured bone mineral density, and circulating bone metabolism biomarker levels (type I collagen C-telopeptide [CTX], amino-terminal propeptide of type I procollagen [P1NP]). The association of radiographic emphysema, bone metabolism biomarker levels, and pulmonary function with accelerated hip bone mineral density loss, defined by the 75th percentile of annual hip bone mineral density decline, was determined by logistic regression modeling with adjustment for age, sex, inhaled and intermittent steroid use, active smoking, body mass index, and the presence of baseline low hip bone mineral density. RESULTS:Of those participants with accelerated hip bone mineral density loss, 22% had moderate or severe visually assessed emphysema compared with 7.2% of smokers without accelerated bone mineral density decline. Moderate to severe visually assessed emphysema (odds ratio, 2.84; 95% confidence interval, 1.01-7.98 compared with trace/mild or no visually assessed emphysema) and the 75th percentile of CTX levels (odds ratio, 2.38; 95% confidence interval, 1.20-4.72 compared with CTX levels below the 75th percentile), a marker of bone resorption, were associated with accelerated hip bone mineral density decline after adjustment for covariates and the presence of baseline low hip bone mineral density. FEV1% predicted was not associated with accelerated bone mineral density decline after adjustment for covariates. Multivariate modeling showed moderate to severe visually assessed emphysema, and the 75th percentiles of CTX were independently associated with accelerated hip bone mineral density decline after adjustment for covariates. CONCLUSIONS:Emphysema and elevated markers of bone resorption are independently associated with progressive bone mineral density loss in smokers. These clinical markers may guide targeted bone mineral density screening and monitoring in smokers at highest risk.

Dataset Information

Deep Learning for the Radiographic Detection of Periodontal Bone Loss.

Publications

Deep Learning for the Radiographic Detection of Periodontal Bone Loss.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets