Liver Detection Algorithm Based on an Improved Deep Network Combined with Edge Perception

Abstract

Due to the large number of organs and the similar grayscale in abdominal medical images, accurately locating and identifying the liver in an abdominal image is a challenging problem. To improve the accuracies of liver detection and localization, this paper proposes an improved deep network that is combined with edge perception. The network improves the contour-detection accuracy of the liver via an edge-perception fusion module and captures the high-level semantic features of the abdominal image using a multiscale pyramid pooling layer. The complementary characteristics of the edge-related features can effectively preserve the clear boundaries of the liver, while rich global context information can be extracted from the combination of the auxiliary channel output and the pyramid pooling layer output. Many qualitative and quantitative experimental results demonstrate that the proposed model can effectively improve the performance of detection and localization networks, which can narrow the range of regions of interest, and can enhance the accuracy of subsequent segmentation and recognition.