Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and texture descriptors

Abstract

Fully automated and volumetric segmentation of critical tumors may play a crucial role in diagnosis and surgical planning. One of the most challenging tumor segmentation tasks is localization of Pancreatic Ductal Adenocarcinoma (PDAC). Exclusive application of conventional methods does not appear promising. Deep learning approaches has achieved great success in the computer aided diagnosis, especially in biomedical image segmentation. This paper introduces a framework based on convolutional neural network (CNN) for segmentation of PDAC mass and surrounding vessels in CT images by incorporating powerful classic features, as well. First, a 3D-CNN architecture is used to localize the pancreas region from the whole CT volume using 3D Local Binary Pattern (LBP) map of the original image. Segmentation of PDAC mass is subsequently performed using 2D attention U-Net and Texture Attention U-Net (TAU-Net). TAU-Net is introduced by fusion of dense Scale-Invariant Feature Transform (SIFT) and LBP descriptors into the attention U-Net. An ensemble model is then used to cumulate the advantages of both networks using a 3D-CNN. In addition, to reduce the effects of imbalanced data, a new loss function is proposed as a weighted combination of three classic losses including Generalized Dice Loss (GDL), Weighted Pixel-Wise Cross Entropy loss (WPCE) and boundary loss. Due to insufficient sample size for vessel segmentation, we used the above-mentioned pre-trained networks and fin-tuned them. Experimental results show that the proposed method improves the Dice score for PDAC mass segmentation in portal-venous phase by 7.52% compared to state-of-the-art methods (from 53.08% to 60.6%) in term of DSC. Besides, three dimensional visualization of the tumor and surrounding vessels can facilitate the evaluation of PDAC treatment response.

Automatic Segmentation of Pancreas and Pancreatic Tumor: A Review of a Decade of Research

“…Table 3 focuses on various deep learning based segmentation methods for pancreatic tumor and cyst. Few methods have performed both pancreas and pancreatic tumor/cyst segmentation [57], [58], [63], [65], [66], [72].…”

“…In a recent study by Du et al [56], they achieved a noteworthy DSC of 68.03% for pancreatic tumor segmentation on a private dataset focusing on small size tumor. Mahmoudi et al [63] achieved a DSC of about 60. 6% on the MSD challenge dataset.…”

“…Mahmoudi et al [63] developed a framework for pancreas and tumor segmentation by combining the CNN architecture with textured U-Net architecture. Initially, the pancreas was localized by CNN and then segmentation of tumor was performed using textured U-Net architecture.…”