18 June 2020>: Clinical Research
Ensemble Deep Learning Model for Multicenter Classification of Thyroid Nodules on Ultrasound Images
Xi Wei 1ACDEG* , Ming Gao 2BEF , Ruiguo Yu 3BCD , Zhiqiang Liu 3BCE , Qing Gu 4BC , Xun Liu 5BC , Zhiming Zheng 6BC , Xiangqian Zheng 2BC , Jialin Zhu 1ABCDEF* , Sheng Zhang 1BDDOI: 10.12659/MSM.926096
Med Sci Monit 2020; 26:e926096
Figure 2 The multistep cascade experiment pathway of EDLC-TN. (A) The process of extracting ROI and mask. First, the boundary was cut off (a). Second, the nodule area was segregated (b). Then, the mask image of the thyroid nodule was depicted (c). Finally, ROI was segmented (d). (B) The process of classifying images by ensemble learning model. After obtaining the ROI and its corresponding mask, three classification models were trained and combined to obtain an advanced classification model. ROI was put into models and got the final classification result through the voting method.