Abstract
This paper aimed to study the adoption of deep learning (DL) algorithm of oral lesions for segmentation of cone-beam computed tomography (CBCT) images. 90 patients with oral lesions were taken as research subjects, and they were grouped into blank, control, and experimental groups, whose images were treated by the manual segmentation method, threshold segmentation algorithm, and full convolutional neural network (FCNN) DL algorithm, respectively. Then, effects of different methods on oral lesion CBCT image recognition and segmentation were analyzed. The results showed that there was no substantial difference in the number of patients with different types of oral lesions among three groups (P > 0.05). The accuracy of lesion segmentation in the experimental group was as high as 98.3%, while those of the blank group and control group were 78.4% and 62.1%, respectively. The accuracy of segmentation of CBCT images in the blank group and control group was considerably inferior to the experimental group (P < 0.05). The segmentation effect on the lesion and the lesion model in the experimental group and control group was evidently superior to the blank group (P < 0.05). In short, the image segmentation accuracy of the FCNN DL method was better than the traditional manual segmentation and threshold segmentation algorithms. Applying the DL segmentation algorithm to CBCT images of oral lesions can accurately identify and segment the lesions.
Highlights
In recent years, with the development of computer technology and its popularity in various fields, medical institutions and other fields have been combined with computer technology, and computer-aided means are widely utilized
CT is a type of X-ray computed tomography, in which different tissues absorb different amounts of X-rays. is technology can be applied to display the internal structure of the human body in the form of three-dimensional imaging, providing convenience and basis for clinical diagnosis and treatment of diseases and related research [2]
Patients who voluntarily withdrew and transferred to the hospital were excluded. e included patients were randomly classified as three groups, blank group, control group, and experimental group (FCNN DL segmentation algorithm), with 30 cases in each group
Summary
With the development of computer technology and its popularity in various fields, medical institutions and other fields have been combined with computer technology, and computer-aided means are widely utilized. At present, computed tomography and magnetic resonance imaging (MRI) are widely adopted in the medical field [1]. Is technology can be applied to display the internal structure of the human body in the form of three-dimensional imaging, providing convenience and basis for clinical diagnosis and treatment of diseases and related research [2]. As a feedforward neural network, the CNN can effectively reduce the complexity of the feedback neural network, which can be utilized to identify some two-dimensional images with distorted and nondeformed forms such as displacement and scaling. E extensive application of DL in medical image classification, such as CNN, can provide convenience for researchers based on traditional research methods [3, 4]. The artificial neural network recognition technology has begun to attract attention and is widely applied in image segmentation. The artificial neural network recognition technology has begun to attract attention and is widely applied in image segmentation. e neural network has a large number of Journal of Healthcare Engineering connections and is easy to introduce spatial information, which can better solve the problems such as uneven distribution and noise in image recognition [9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
