Pediatric age estimation from radiographs of the knee using deep learning

Medico-legal indicators and cut-offs in different age classes through quantitative analysis of epiphyseal fusion segments on knee CT scans

Scientists are interested in determining age in subadults for several forensic purposes. High- resolution instrumental techniques are being increasingly used for age estimation, driven by the need to minimize errors; in this context, several studies have focused on the knee joint, recognized as a potential site for age examination in late adolescence. We analyzed 200 CT scans performed on Russian subjects (106 males and 94 females) between 13 and 20 years, without growth diseases, endocrine disorders, or osteodystrophy. Each subject underwent two scans, one for each leg. Two indicators were measured for each bone (femur, tibia and fibula): the entire length of the epiphyseal scar and the length of the part/s that is/are fused with metaphysis. Intra class Correlation Coefficient (ICC) was performed to evaluate the intra-operator reproducibility. The ratio between the two lengths was calculated for each bone (FemurR, TibiaR and FibulaR). The first aim was to evaluate a correlation between the ratios of the three bones and the three bones treated as a single parameter (given by the sum of the ratios) versus age. The results showed good correlations in both cases (τ a = 0.74, 0.64, 0.57 and 0.67). The second aim was to estimate the cut-offs derived from the sum of the three ratios respect to four age classes (14-15 years: cut-off ≤ 0.63, 15-16 years: cut-off ≤ 1.19, 16-17 years: cut-off ≥ 0.68 and 17-18 years: cut-off ≥ 1.49. The results from this research encourage further studies of the knee joint as an indicator of legal adult age.

Automated Skeletal Bone Age Assessment with Two-Stage Convolutional Transformer Network Based on X-ray Images

Human skeletal development is continuous and staged, and different stages have various morphological characteristics. Therefore, bone age assessment (BAA) can accurately reflect the individual's growth and development level and maturity. Clinical BAA is time consuming, highly subjective, and lacks consistency. Deep learning has made considerable progress in BAA in recent years by effectively extracting deep features. Most studies use neural networks to extract global information from input images. However, clinical radiologists are highly concerned about the ossification degree in some specific regions of the hand bones. This paper proposes a two-stage convolutional transformer network to improve the accuracy of BAA. Combined with object detection and transformer, the first stage mimics the bone age reading process of the pediatrician, extracts the hand bone region of interest (ROI) in real time using YOLOv5, and proposes hand bone posture alignment. In addition, the previous information encoding of biological sex is integrated into the feature map to replace the position token in the transformer. The second stage extracts features within the ROI by window attention, interacts between different ROIs by shifting the window attention to extract hidden feature information, and penalizes the evaluation results using a hybrid loss function to ensure its stability and accuracy. The proposed method is evaluated on the data from the Pediatric Bone Age Challenge organized by the Radiological Society of North America (RSNA). The experimental results show that the proposed method achieves a mean absolute error (MAE) of 6.22 and 4.585 months on the validation and testing sets, respectively, and the cumulative accuracy within 6 and 12 months reach 71% and 96%, respectively, which is comparable to the state of the art, markedly reducing the clinical workload and realizing rapid, automatic, and high-precision assessment.

Fully automated method for dental age estimation using the ACF detector and deep learning

Background

Dental age estimation plays an important role in identifying an unknown person. In forensic science, estimating age with high accuracy depends on the experience of the practitioner. Previous studies proposed classification of tooth development of the mandibular third molar by following Demirjian’s method, which is useful for dental age estimation. Although stage of tooth growth is very helpful in assessing age estimation, it must be performed manually. The drawback of this procedure is its need for skilled observers to carry out the tasks precisely and reproducibly because it is quite detailed. Therefore, this research aimed to apply computer-aid methods for reducing time and subjectivity in dental age estimation by using dental panoramic images based on Demirjian’s method. Dental panoramic images were collected from persons aged 15 to 23 years old. In accordance with Demirjian’s method, this study focused only on stages D to H of tooth development, which were discovered in the 15- to 23-year age range. The aggregate channel features detector was applied automatically to localize and crop only the lower left mandibular third molar in panoramic images. Then, the convolutional neural network model was applied to classify cropped images into D to H stages. Finally, the classified stages were used to estimate dental age.

Results

Experimental results showed that the proposed method in this study can localize the lower left mandibular third molar automatically with 99.5% accuracy, and training in the convolutional neural network model can achieve 83.25% classification accuracy using the transfer learning strategy with the Resnet50 network.

Conclusion

In this work, the aggregate channel features detector and convolutional neural network model were applied to localize a specific tooth in a panoramic image and identify the developmental stages automatically in order to estimate the age of the subjects. The proposed method can be applied in clinical practice as a tool that helps clinicians to reduce the time and subjectivity for dental age estimation.