18 June 2020 : Clinical Research
Ensemble Deep Learning Model for Multicenter Classification of Thyroid Nodules on Ultrasound Images
Xi Wei1ACDEG*, Ming Gao2BEF, Ruiguo Yu3BCD, Zhiqiang Liu3BCE, Qing Gu4BC, Xun Liu5BC, Zhiming Zheng6BC, Xiangqian Zheng2BC, Jialin Zhu1ABCDEF, Sheng Zhang1BDDOI: 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.