3 AUTOMATED CLASSIFICATION APPARATUS FOR SHOULDER DISEASE VIA THREE DIMENSIONAL DEEP LEARNING METHOD METHOD OF PROVIDING INFORMATION FOR CLASSIFICATION OF SHOULDER DISEASE AND ELECTRONIC RECORDING MEDIUM FOR COMPUTER PROGRAM OPERATING THE METHODOF PROVIDING INFORMATION FOR CLASSIFICATION OF SHOULDER DISEASE

摘要

The shoulder disease diagnosis apparatus includes a three-dimensional Inception-ResNet block structure, a global average pooling structure, and a fully connected layer. The 3D Inception Resnet block structure is a 3D Inception-ResNet structure that receives a 3D medical image obtained by photographing a patient's shoulder and derives features from the 3D medical image; and a three-dimensional inception downsampling structure that abbreviates information of a feature map formed by the features. The global average pooling structure average pools the output of the 3D Inception Resnet block structure. The fully connected layer is disposed at a rear end of the global average pooling block. The shoulder disease diagnosis apparatus automatically classifies the diagnosis result of the 3D medical image into a plurality of categories.