Abstract
The diagnosis of thyroid nodules at an early stage is a challenging task. Manual diagnosis of thyroid nodules is labor-intensive and time-consuming. Meanwhile, due to the difference of instruments and technical personnel, the original thyroid nodule ultrasound images collected are very different. In order to make better use of ultrasound image information of thyroid nodules, some image processing methods are indispensable. In this paper, we developed a method for automatic thyroid nodule classification based on image enhancement and deep neural networks. The selected image enhancement method is histogram equalization, and the neural networks have four-layer network nodes in our experiments. The dataset in this paper consists of thyroid nodule images of 508 patients. The data are divided into 80% training and 20% validation sets. A comparison result demonstrates that our method can achieve a better performance than other normal machine learning methods. The experimental results show that our method has achieved 0.901961 accuracy, 0.894737 precision, 1 recall, and 0.944444 F1-score. At the same time, we also considered the influence of network structure, activation function of network nodes, number of training iterations, and other factors on the classification results. The experimental results show that the optimal network structure is 2500-40-2-1, the optimal activation function is logistic function, and the best number of training iterations is 500.
Highlights
Academic Editor: Jianli Liu e diagnosis of thyroid nodules at an early stage is a challenging task
We developed a method for automatic thyroid nodule classification based on image enhancement and deep neural networks. e selected image enhancement method is histogram equalization, and the neural networks have four-layer network nodes in our experiments. e dataset in this paper consists of thyroid nodule images of 508 patients. e data are divided into 80% training and 20% validation sets
We considered the influence of network structure, activation function of network nodes, number of training iterations, and other factors on the classification results. e experimental results show that the optimal network structure is 2500-40-2-1, the optimal activation function is logistic function, and the best number of training iterations is 500
Summary
Academic Editor: Jianli Liu e diagnosis of thyroid nodules at an early stage is a challenging task. We developed a method for automatic thyroid nodule classification based on image enhancement and deep neural networks. In 2007, Savelonas et al focused on the directional patterns of the image they extracted using radon transformation and proposed a computer-aided diagnosis system based on support vector machine on the data of 66 patients, achieving maximal classification accuracy of 0.89 [8]. In 2011, Ding et al studied the classification of thyroid nodules using the support vector machine classifier and 125 thyroid nodules consisting of 56 malignant and 69 benign patients [9]. In 2020, Harshini et al used linear discriminant analysis and support vector machine to distinguish thyroid nodules and compared the results of two methods [11]. E sensitivity and specificity of ultrasound thyroid imaging reporting and data system classification results for benign and malignant tumors were calculated [14]. In 2020, Ataide et al aimed to reduce subjectivity in the current diagnostic process by using geometric and morphological (G-M) features that represent the visual characteristics of thyroid nodules to provide physicians with decision support [15]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
