Abstract
Computer-aided diagnosis systems have been developed to assist doctors in diagnosing thyroid nodules to reduce errors made by traditional diagnosis methods, which are mainly based on the experiences of doctors. Therefore, the performance of such systems plays an important role in enhancing the quality of a diagnosing task. Although there have been the state-of-the art studies regarding this problem, which are based on handcrafted features, deep features, or the combination of the two, their performances are still limited. To overcome these problems, we propose an ultrasound image-based diagnosis of the malignant thyroid nodule method using artificial intelligence based on the analysis in both spatial and frequency domains. Additionally, we propose the use of weighted binary cross-entropy loss function for the training of deep convolutional neural networks to reduce the effects of unbalanced training samples of the target classes in the training data. Through our experiments with a popular open dataset, namely the thyroid digital image database (TDID), we confirm the superiority of our method compared to the state-of-the-art methods.
Highlights
Traditional disease diagnosis/treatment methods are mostly based on doctors’ expert knowledge on any given condition
We propose the use of multiple Convolutional Neural Network (CNN)-based models to analyze input ultrasound thyroid images deeply for the classification problem
The deep learning-based method implies the use of a deep neural network for a regression or classification problem
Summary
Traditional disease diagnosis/treatment methods are mostly based on doctors’ expert knowledge on any given condition. The deep learning-based method implies the use of a deep (many layers) neural network for a regression or classification problem This is not a new technique, this method has recently attracted lots of attention from researchers because of the development of GPUs that are used to speed-up the processing of the network, and lots of superior (state-of-the-art) performances of digital signal processing systems have been reported [39,40,41,42,43,44,45,46,47,48,49,50]. The use of convolution operation with a weight-sharing scheme allows us to construct a deeper network than the conventional neural network
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
