Thigh fracture detection using deep learning method based on new dilated convolutional feature pyramid network

In this paper, we design a new backbone network by using of dilated convolutions. By replacing the backbone network in the state-of-the-art FPN framework with the one we designed, we propose a new deep learning method called dilated convolutional feature pyramid network (DCFPN), and apply it to thigh fracture detection. To evaluate our method, we establish a dataset including 3842 thigh fracture X-ray radiographs collected from Linyi People's Hospital. The experiment results show that the Average Precision (AP) of DCFPN reaches 82.1% in the detection of 358 testing thigh fracture images, which is 3.9% higher than that of state-of-the-art FPN. As a consequence, the DCFPN has strong potential applicability in practical clinical environments. (C) 2019 Elsevier B.V. All rights reserved.