Search

In this work, a novel semisupervised framework is proposed to tackle the small-sample problem of dental-based human identification (DHI), achieving enhanced performance via a "classifying while generating" paradigm. A generative adversarial network (GAN), called the DHI-GAN, is presented to implement this idea, in which an extra classifier is also dedicatedly proposed to achieve an efficient training procedure. Considering the complex specificities of this problem, except for the noise input of the generator, an identity embedding-guided architecture is proposed to retain informative features for each individual. A parallel spatial and channel fusion attention block is innovatively designed to encourage the model to learn discriminative and informative features by focusing on different regional details and abstract concepts. The attention block is also widely applied to the overall classifier to learn identity-dependent information. A loss combination of the ArcFace and focal loss is utilized to address the small-sample problem. Two parameters are proposed to control the generated samples that are fed into the classifier during the optimization procedure. The proposed DHI-GAN framework is finally validated on a real-world dataset, and the experimental results demonstrate that it outperforms other baselines, achieving a 92.5% top-one accuracy rate. Most importantly, the proposed GAN-based semisupervised training strategy is able to reduce the required number of training samples (individuals) and can also be incorporated into other classification models. Our code will be available at https://github.com/sculyi/MedicalImages/.

Forensic odontology is regarded as an important branch of forensics dealing with human identification based on dental identification. This paper proposes a novel method that uses deep convolution neural networks to assist in human identification by automatically and accurately matching 2-D panoramic dental X-ray images. Designed as a top-down architecture, the network incorporates an improved channel attention module and a learnable connected module to better extract features for matching. By integrating associated features among all channel maps, the channel attention module can selectively emphasize interdependent channel information, which contributes to more precise recognition results. The learnable connected module not only connects different layers in a feed-forward fashion but also searches the optimal connections for each connected layer, resulting in automatically and adaptively learning the connections among layers. Extensive experiments demonstrate that our method can achieve new state-of-the-art performance in human identification using dental images. Specifically, the method is tested on a dataset including 1,168 dental panoramic images of 503 different subjects, and its dental image recognition accuracy for human identification reaches 87.21% rank-1 accuracy and 95.34% rank-5 accuracy. Code has been released on Github. (https://github.com/cclaiyc/TIdentify).

Forensic identification of human remains is crucial for legal, humanitarian, and civil reasons. Wide heterogeneity in sphenoid sinus morphology can be used for personal identification. This study aimed to propose a new protocol for personal identification based on three-dimensional (3D) reconstruction of sphenoid sinus CT images using Iterative Closest Point (ICP) algorithm. Seven hundred thirty-two patients which consisted of 348 females and 384 males were retrospectively included. The study sample includes 732 previous images as a source point set and 743 later ones as a scene target set. The sphenoid sinus computed tomography (CT) images were processed on a workstation (Dolphin imaging) to obtain 3D images and stored as a file format of Stereo lithography (.STL). Then, a Python library vtkplotter was used to transform the STL format to PLY format, which was adapted to Point Cloud Library (PCL). The ICP algorithm was used for point clouds matching. The metric Rank-N recognition rate was used for evaluation. The scene target set of 743 individuals was compared with the source point set of 732 individual models and achieved Rank-1 accuracy of 96.24%, Rank-2 accuracy of 99.73%, and Rank-3 accuracy of 100%. Our results indicated that the 3D point cloud registration of sphenoid sinuses was useful for assessing personal identification in forensic contexts. [ABSTRACT FROM AUTHOR]

Objectives: This study aimed to explore whether computed tomography (CT) images of cranial sutures can contribute to adult age estimation in Chinese Han individuals. Materials and methods: This study was based on cranial CT scans of 230 Chinese Han males aged 23.33–76.93 years. A total of 160 images from 16 suture segments were scored after volume reformation and multiplanar reconstruction in each individual. Decision tree regression, linear support vector regression, Bayesian ridge regression, and gradient boosting regression were developed for adult age estimation by a training set using leave‐one‐out cross‐validation and further evaluated by the test set. The inaccuracy and bias were calculated to evaluate the four models and the previously used models from the literature. Results: The degree of suture closure was associated with adult age. The minimum inaccuracy of the test set was 7.73 years obtained by linear support vector regression, while the inaccuracy of previous simple linear regression models was 13.09 and 10.97 years. The accuracy was higher in the age group from 40.00 to 59.99 years compared to the other age groups. Discussion: The accuracy of our models for adult age estimation was superior to those in previous studies based on cranial sutures. Hence, the application of novel statistical data mining tools helps to improve aging issues. Nevertheless, age estimation of adults should be combined with other methods, since the accuracy level is still not satisfactory. [ABSTRACT FROM AUTHOR]

• The proximal femur has considerable value in estimating sex. • Deep learning can be used to create an automated sex estimation model based on femur radiographic features. • The model proposed in this paper achieves competitive performance compared with existing models. To develop a fully automated deep learning pipeline using digital radiographs to detect the proximal femur region for accurate automated sex estimation. Radiograph predictive features from 2122 Chinese Han clinical pelvic with ages ranging from 18 to 26 years were collected retrospectively to train and test the sex prediction model using deep machine learning's convolutional neural networks (CNN). Model performance was assessed using a Chinese Han population with 361 samples and a white population with 50 samples. The average accuracy of the sex estimation of the two test datasets was determined. For the Chinese Han population test dataset, the sex estimation accuracy was 94.6% (males: 93.9% and females: 94.7%). For the white population samples, the accuracy of sex estimation was 82.9% (males: 80.9% and females: 88.6%). The accuracy of CNN tested in the Chinese population was significantly higher than that tested in the White population (p < 0.001) The model based on convolutional neural networks has an accuracy similar to that of current state-of-the-art mathematical functions using manually extracted features for the Chinese Han population samples, proving to be a reliable choice for the human sex estimation. [ABSTRACT FROM AUTHOR]

The developmental patterns of the pelvic epiphyses are one of the anatomical markers used in the assessment of skeletal age and the legally relevant age threshold. In this study, four regression models and five classification models were developed for forensic age estimation and the determination of the 18-year threshold, respectively. A total of 2137 conventional pelvic radiographs (1215 males and 922 females) aged 10.00-25.99 years were analyzed, and the ossification and fusion of the iliac crest and ischial tuberosity epiphyses were scored separately. The epiphyses on both sides were used as inputs for all models. The accuracy of the regression models was compared using the mean absolute error (MAE) and root mean square error. The percentages of correct classifications were evaluated for the determination of the 18-year threshold. Support vector regression (SVR) and gradient boosting regression (GBR) showed higher accuracy for age estimation in both sexes. The lowest MAE was 1.38 years in males when using SVR and 1.16 years in females when using GBR. In the demarcation of minors and adults, the percentage of correct classification was over 92%, and the area under the receiver operating characteristic curves was over 0.91 in all models, except the Bernoulli naive Bayes classifier. This study demonstrated that the present models may be helpful for age estimation and the determination of the 18-year threshold. However, owing to the high effective dose of ionizing radiation used during conventional radiography of the pelvis, it is expected that these models will be tested with pelvic MRI for age estimation. [ABSTRACT FROM AUTHOR]