15 August 2020>: Clinical Research
Visual Interpretability in Computer-Assisted Diagnosis of Thyroid Nodules Using Ultrasound Images
Xi Wei 1ADEFG , Jialin Zhu 1ACDEF* , Haozhi Zhang 2CDF , Hongyan Gao 3BCF , Ruiguo Yu 4BCD , Zhiqiang Liu 4BCD , Xiangqian Zheng 2BF , Ming Gao 2AF , Sheng Zhang 1ABDEF*DOI: 10.12659/MSM.927007
Med Sci Monit 2020; 26:e927007
Figure 2 The boundary visualization model was used to localize nodule boundaries during the prediction of neural networks, with sketches of the global average pooling (A) and fully connected layer (B). The visualized reverse calculation result from global average pooling was rough. On the contrary, through the fully connection layer, we made full use of all the data from the feature map to reduce the loss of information, and obtained finer visualization results.