Clinical application of an automatic facial recognition system based on deep learning for diagnosis of Turner syndrome.

PURPOSE: Automated facial recognition technology based on deep learning has achieved high accuracy in diagnosing various endocrine diseases and genetic syndromes. This study attempts to establish a facial diagnostic system for Turner syndrome (TS) based on deep convolutional neural networks. METHODS: Photographs of 207 TS patients and 1074 female controls were collected from July 2016 to April 2019. Finally, 170 patients diagnosed with TS and 1053 female controls were included. Deep convolutional neural networks were used to develop the facial diagnostic system. A prospective study, which included two TS patients and 35 controls, was conducted to test the efficacy in the real clinical setting. RESULTS: The average areas under the curve (AUCs) in three different scenarios were 0.9540 ± 0.0223, 0.9662 ± 0.0108 and 0.9557 ± 0.0119, separately. The average sensitivity and specificity of the prospective study were 96.7% and 97.0%, respectively. CONCLUSIONS: The facial diagnostic system achieved high accuracy. Prospective study results demonstrated the application value of this system, which is promising in the screening of Turner syndrome.

The manufacturing procedure of 3D printed models for endoscopic endonasal transsphenoidal pituitary surgery.

BACKGROUND: Endoscopic endonasal transsphenoidal pituitary surgery is usually difficult and risky. With limited sources of cadaveric skulls, traditional methods of using virtual images to study the surgery are difficult for neurosurgeons and students because the surgery requires spatial imagination and good understanding of the patient's conditions as well as practical experience. The three-dimensional (3D) printing technique has played an important role in clinical medicine due to its advantages of low cost, high-efficiency and customization. OBJECTIVE: CT images are used as the source data of 3D printing. The data obtained directly from the CT machine has limited accuracy, which cannot be printed without processing. Some commercial platforms can help build an accurate model but the cost and customization are not satisfactory. In this situation, a tactile, precise and low-cost 3D model is highly desirable. METHODS: Five kinds of computer software are used in the manufacturing of medical 3D models and the processing procedure is easy to understand and operate. RESULTS: This study proposes a practical and cost-effective method to obtain the corrected digital model and produce the 3D printed skull with complete structures of nasal cavity, sellar region and different levels of pituitary tumors. The model is used for the endoscopic endonasal transsphenoidal pituitary surgery preparation. CONCLUSION: The 3D printed medical model can directly help neurosurgeons and medical students to practice their surgery skills on both general and special cases with customized structures and different levels of tumors.

The Prediction of the Epidemic Trend of COVID-19 Using Neural Networks.

In this paper, a BP neural network and an LSTM network are applied respectively to the prediction of Coronavirus Disease 2019 (COVID-19) in Wuhan, China and South Korea. The methods do not require specific theories of modelling and the predicted values can be obtained as long as the conventional parameters are set. The mean absolute percentage error (MAPE) of all the experiments are below 5% and the values of the determinable coefficient R2 are all larger than 0.9. The experiments show that the models can fit the actual values well and make relatively accurate predictions. As of March 29, 2020, the cumulative number of confirmed cases in Wuhan is expected to reach 50,068 using BP neural networks and 49,972 using LSTM network, respectively. As of April 13, 2020, the cumulative number of confirmed cases in South Korea is expected to reach 8,862 using BP neural networks and 8,716 using LSTM network, respectively. The models of neural networks are effective in predicting the trend of the COVID-19 epidemic, which is meaningful to prevent and control the epidemic.

The process of 3D printed skull models for anatomy education.

In general, the 3 D printed medical models are made based on virtual digital models obtained from machines such as the computed tomography scanner. However, due to the limited accuracy of CT scanning technology, which is usually 1 millimeter, there are differences between scanned results and the real structure. Besides, the collected data can hardly be printed directly because of some errors in the model. In this paper, we present a general and efficient procedure to process the digital skull data to make the printed structures meet the requirements of anatomy education, which combines the use of five 3 D manipulation tools and the procedure can be finished within 6 hours. Then the model is printed and compared with the cadaveric skull from frontal, left, right and anterior views respectively. The printed model can describe the correct structure and details of the skull clearly, which can be considered as a good alternative to the cadaveric skull. The manipulation procedure presented in this study is an easily available and cost-effective way to obtain a printed skull model from the original CT data, which has a considerable economic and social benefit for the medical education. The steps of the data processing can be performed easily. The cost for the 3 D printed model is also low. Outcomes of this study can be applied widely in processing skull data.

A Learning-Based Framework for Error Compensation in 3D Printing.

As a typical cyber-physical system, 3D printing has developed very fast in recent years. There is a strong demand for mass customization, such as printing dental crowns. However, the accuracy of the 3D printed objects is low compared with traditional methods. The main reason is that the model to be printed is arbitrary and usually the quantity is small. The deformation is affected by the shape of the object and there is a lack of a universal method for the error compensation. It is neither easy nor economical to perform the compensation manually. In this paper, we present a framework for the automatic error compensation. We obtain the shape by technologies such as 3D scanning. And we use the "3D deep learning" method to train a deep neural network. For a specific task, such as dental crown printing, the network can learn the function of deformation when a large amount of data is used for training. To the best of our knowledge, this is the first application of the deep neural network to the error compensation in 3D printing. And we propose the "inverse function network" to compensate for the error. We use four types of deformations of the dental crowns to verify the performance of the neural network: 1) translation; 2) scaling up; 3) scaling down; and 4) rotation. The convolutional AutoEncoder structure is employed for the end-to-end learning. The experiments show that the network can predict and compensate for the error well. By introducing the new method, we can improve the accuracy with little need for increasing the hardware cost.