Thyroid nodule benign and malignant classification method based on TI-RADS multi-task neural network

The invention discloses a thyroid nodule benign and malignant classification method based on a TI-RADS multi-task neural network, and belongs to the technical field of deep learning of a computer technology. The technical problem to be solved is to provide the improvement of the thyroid nodule benign and malignant classification method based on the TI-RADS multi-task neural network. According to the technical scheme, the method comprises the steps of image preprocessing; the method comprises the following steps: constructing a convolutional neural network: using a DenseNets 121 as a backbone network, the DenseNets 121 comprising four Dense Blocks and three Transformation layers, and the Dense Blocks being composed of Dense Layers, and the Dense Layers being composed of Dense Layers, the Dense Layers being composed of Dense Layers, the Dense Layers being composed of Dense Layers, and the Dense Layers being composed of Dense Layers; an SGE module is inserted behind the batch normalization layer of the bottlenec