Thyroid Nodule Segmentation in Ultrasound Images Based on Cascaded Convolutional Neural Network

Based on U-shaped Fully Convolutional Neural Network (UNET), Convolutional Neural Network (CNN) classifier and Deep Fully Convolutional Neural Network (FCN), this paper proposes a thyroid nodule segmentation model in form of cascaded convolutional neural network. In this paper, we study the segmentation of thyroid nodules from two aspects, segmentation process and model structure. On the one hand, the research of the segmentation process includes the gradual reduction of the segmentation region and the selection of different model structures. On the other hand, the research of model structures includes the design of network structure, the adjustment of model parameters and so on. And the experiment shows that our thyroid nodule segmentation in ultrasound images has a good performance, which is superior to the current algorithms and can be used as a reference for the diagnosis of the doctor.