Abstract
Thyroid disease has now become the second largest disease in the endocrine field; SPECT imaging is particularly important for the clinical diagnosis of thyroid diseases. However, there is little research on the application of SPECT images in the computer-aided diagnosis of thyroid diseases based on machine learning methods. A convolutional neural network with optimization-based computer-aided diagnosis of thyroid diseases using SPECT images is developed. Three categories of diseases are considered, and they are Graves' disease, Hashimoto disease, and subacute thyroiditis. A modified DenseNet architecture of convolutional neural network is employed, and the training method is improved. The architecture is modified by adding the trainable weight parameters to each skip connection in DenseNet. And the training method is improved by optimizing the learning rate with flower pollination algorithm for network training. Experimental results demonstrate that the proposed method of convolutional neural network is efficient for the diagnosis of thyroid diseases with SPECT images, and it has superior performance than other CNN methods.
Highlights
Imaging technology is very important for the diagnosis of thyroid diseases, so there have been a lot of research studies on Computer-aided diagnosis (CAD) for imaging technology
Ultrasound imaging has the advantages of good real time, convenient operation, and low cost, so it is widely used in the clinical diagnosis of thyroid diseases. e CAD of thyroid disease based on ultrasonography was developed earlier, and the typical example was a benign or malignant diagnosis of thyroid nodules based on ultrasound [8,9,10]
From the perspective of machine learning methods, the use of SPECT images for thyroid disease diagnosis is to link the characteristics of SPECT images with the diagnosis of thyroid diseases, and the classification problem of SPECT is to classify thyroid SPECT images into specific diseases according to characteristics. erefore, for machine learning methods, the use of SPECT images for disease diagnosis is to solve the classification problem of SPECT images. e DenseNet network is an important deep learning network architecture that has emerged in recent years, and it has performed well in many practical applications. is paper uses DenseNet network to establish the diagnosis model of thyroid disease based on SPECT image
Summary
Imaging technology is very important for the diagnosis of thyroid diseases, so there have been a lot of research studies on CAD for imaging technology. The machine learning method of deep learning is adopted to diagnose thyroid diseases using SPECT images. Erefore, for machine learning methods, the use of SPECT images for disease diagnosis is to solve the classification problem of SPECT images. Is paper uses DenseNet network to establish the diagnosis model of thyroid disease based on SPECT image. On the basis of the traditional DenseNet network architecture, both the architecture and the training method are improved in this paper, which greatly improves the diagnosis effect of thyroid disease. E main contributions of the paper include the following: first, the paper introduces the deep learning method into the diagnosis of thyroid disease based on SPECT images.
Sign-in/Register to view highlights & summary 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.
