DENSEN: a convolutional neural network for estimating chronological ages from panoramic radiographs

Abstract

Background Age estimation from panoramic radiographs is a fundamental task in forensic sciences. Previous age assessment studies mainly focused on juvenile rather than elderly populations (> 25 years old). Most proposed studies were statistical or scoring-based, requiring wet-lab experiments and professional skills, and suffering from low reliability. Result Based on Soft Stagewise Regression Network (SSR-Net), we developed DENSEN to estimate the chronological age for both juvenile and older adults, based on their orthopantomograms (OPTs, also known as orthopantomographs, pantomograms, or panoramic radiographs). We collected 1903 clinical panoramic radiographs of individuals between 3 and 85 years old to train and validate the model. We evaluated the model by the mean absolute error (MAE) between the estimated age and ground truth. For different age groups, 3–11 (children), 12–18 (teens), 19–25 (young adults), and 25+ (adults), DENSEN produced MAEs as 0.6885, 0.7615, 1.3502, and 2.8770, respectively. Our results imply that the model works in situations where genders are unknown. Moreover, DENSEN has lower errors for the adult group (> 25 years) than other methods. The proposed model is memory compact, consuming about 1.0 MB of memory overhead. Conclusions We introduced a novel deep learning approach DENSEN to estimate a subject’s age from a panoramic radiograph for the first time. Our approach required less laboratory work compared with existing methods. The package we developed is an open-source tool and applies to all different age groups.

Panoramic imaging errors in machine learning model development: a systematic review

“… 8 , 9 , 11 , 13 , 17 , 26–28 , 36 , 39 , 40 , 42 , 43 , 48 In contrast, 27 studies used a single model to carry out distinct tasks. 7 , 10 , 12 , 14–16 , 19–25 , 29–35 , 37 , 38 , 41 , 44–47 …”

A population-based study to assess two convolutional neural networks for dental age estimation

“…Moreover, to further improve the accuracy, Sharifonnasabi F et al proposed a method of image classifiers and a hybrid model based on CNNs and K-nearest neighbors (KNN); their innovative model (HCNN-KNN) managed to obtain high accuracies with satisfaction [ 28 ]. Wang et al developed DENSEN based on a Soft Stagewise Regression Network for both juveniles and older adults [ 29 ]. In their studies of the 3–11 (children), 12–18 (teens), 19–25 (young adults), and 25 + (adults) groups, DENSEN produced MAEs of 0.6885, 0.7615, 1.3502, and 2.8770, respectively.…”

A deep-learning artificial intelligence system for estimating chronological age using panoramic radiography in the Korean population

“…Numerous techniques are available for estimating age using various body components. Several studies have focused on the connection between epiphyseal closure and age 3,4 . Many factors are related to epiphyseal fusion, including sex, genetics, and geography 3,5 .…”

“…Several studies have focused on the connection between epiphyseal closure and age 3,4 . Many factors are related to epiphyseal fusion, including sex, genetics, and geography 3,5 . However, the bone age assessment method is usually used to evaluate immature individuals because of incomplete skeletal development 6 .…”

“…Evaluation of dental age using radiographic tooth development and tooth eruption sequences is more accurate than other methods 7,8 . As tooth and dental tissue is largely genetically formed and is less susceptible to environmental and dietary in uences, there is less deformation caused by external chemical and physical damage 2,3,7 .…”