Gland Segmentation in H&E Histopathological Images using U-Net with Attention Module

Gland segmentation refers to the process of identifying and delineating glandular regions within histopathology images. However, gland segmentation in histopathology images is a challenging task due to several factors such as shape variations and overlapping structures. Despite numerous research efforts dedicated to addressing this challenge, it remains an unresolved problem. To address this issue, we introduce a deep gland segmentation method by designing an enhanced U-Net variant combined with an Attention module. By incorporating the Attention module into the U-Net architecture, the model becomes more adept at capturing contextual information and fine details within the histopathology images. To verify the effectiveness of the introduced method, we compare it with well-known semantic segmentation architectures on the GLAS and GRAG datasets. According to the results, our approach demonstrates a high success rate in gland segmentation, effectively competing with existing state-of-the-art methods.