Abstract:

The pancreas has always been one of the most challenging tasks in medical image segmentation due to its complex anatomical structure and complex surrounding environment. Aiming at the above problems, a deep learning segmentation model combining Dual Decoding and Global Attention Upsampling module (DGANet) is proposed. The model consists of an encoder and two decoders, where thelater realize the full utilization of different depth feature information. The model uses the Global Attention Upsampling module to guide the low-level selection of more accurate feature information by using high-level rich semantic information. The data set provided by Changhai Hospital was used for experiments. The results showed that the Dice similarity coefficient was 86.28 %, Intersection-over-Union (IoU) was 0.77, and Hausdorff Distance (HD) was 7.7 mm. The data confirmed that the model had certain clinical significance and value in the segmentation of pancreatic cystic tumors.

Key words: Medical Image Segmentation, DGANet, Deep Learning, Pancreas