 This paper proposes a deep convolutional neural network, DCNN, classification system for assessing breast positioning criteria in mammography. The system uses image processing to identify the region of interest, then uses four different DCNN models to evaluate the accuracy of the positioning. The results show that the DCNN model achieves the highest accuracy of 0.7836 in the inframammary fold and 0.7278 in the nipple profile. Additionally, the system can provide a quantitative evaluation of the positioning accuracy through the use of a softmax function. This article was authored by Haruyuki Watanabe, Saiko Hayoshi, Yohan Kondo, and others.