Pancreatic CT image segmentation based on transfer learning

Abstract

Pancreatic Ductal Adenocarcinoma (PDAC) is one of the most common types of pancreatic cancer and one of the malignant cancers, with an overall five-year survival rate of 5%. CT is the most important imaging examination method for pancreatic diseases with high resolutions. Due to the subtle texture changes of PDAC, single-phase pancreatic imaging is not sufficient to assist doctors in diagnosis. Therefore, dual- phase pancreatPancreatic Ductal Adenocarcinoma (PDAC) is one of the most common types of pancreatic cancer and one of the malignant cancers, with an overall five-year survival rate of 5%. CT is the most important imaging examination method for pancreatic diseases with high resolutions. Due to the subtle texture changes of PDAC, single-phase pancreatic imaging is not sufficient to assist doctors in diagnosis. Therefore, dual- phase pancreatic imaging is recommended for better diagnosis of pancreatic disease. However, since manual labeling requires a lot of time and efforts for experienced physicians, and dual-phase images are often not aligned and largely different in texture, it is difficult to combine cross-phase images. Therefore, in this study, we aim to enhance PDAC automatic segmentation by integrating multi-phase images (i.e. arterial and venous phase) through transfer learning. Therefore, we first transform the image in source domain into the image in target domain through CycleGAN. Secondly, we propose an uncertainty loss to auxiliary training of pseudo target domain images by using pseudo images of different qualities generated during CycleGAN training. Finally, a feature fusion block is designed to compensate for the loss of details caused by downsampling. Experimental results show that the proposed method can obtain more accurate segmentation results than the existing methods.c imaging is recommended for better diagnosis of pancreatic disease. However, since manual labeling requires a lot of time and efforts for experienced physicians, and dual-phase images are often not aligned and largely different in texture, it is difficult to combine cross-phase images. Therefore, in this study, we aim to enhance PDAC automatic segmentation by integrating multi-phase images (i.e. arterial and venous phase) through transfer learning.