Abstract
Thyroid cancer is a malignant tumor that occurs in the thyroid gland and is the most common malignant tumor in the endocrine system. Ultrasound examination is the most important method to diagnose thyroid cancer. The accuracy of ultrasound examination for thyroid cancer is closely related to doctors' cognition and understanding of ultrasound images, and there are subjective judgment and misjudgment. The ultrasound images of thyroid papillary carcinoma are mostly represented by two-dimensional gray scale, and with lower resolution, complicated internal tissue structure, and not obvious features of the cancer, it is difficult to distinguish and diagnose the thyroid papillary carcinoma. In this paper, we introduce the theory of convolution neural network (CNN) in view of the difficulty in recognizing the ultrasound image of thyroid papillary carcinoma, and propose a method which can automatically recognize the ultrasound image of thyroid papillary carcinoma. In terms of the need of ultrasonic image recognition of thyroid papillary carcinoma, the Fast Region-based Convolutional Network method (Faster RCNN) network is improved and normalized by connecting the fourth layer and the fifth layer of the shared convolution layer in the Faster RCNN network. Then, a multi-scale ultrasound image is used at the time of input. Finally, according to the main features of the ultrasound images of thyroid papillary carcinoma, they are classified so as to output detailed ultrasound image diagnosis reports. The experimental results show that compared with the original Faster RCNN network, the proposed method has higher recognition accuracy, shorter training time and higher efficiency in ultrasonic image recognition of thyroid papillary carcinoma.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.