An improved YOLOv5 network for lung nodule detection

Lung cancer has ranked first in incidence and mortality among all malignant tumors. Lung nodules are one of the early features of lung cancer. The early detection of lung nodules can help reduce the mortality rate of lung cancer. However, the detection performance of lung nodules is low due to their diverse shapes and small size. In this paper, an improved YOLOv5 method is proposed for lung nodule detection. By adding an attention mechanism to the feature extraction network, the feature expression capability is effectively improved. The method of feature fusion has also changed to make feature fusion more adequate. The experiments are conducted using the publicly available dataset provided by the Lung Image Database Consortium (LIDC). The experimental results show that the improved network has stronger feature expression and more adequate feature fusion capability compared with the original YOLOv5 network. The index of AP is improved by 1.4%.