Automatic Pancreas Segmentation in CT Images With Distance-Based Saliency-Aware DenseASPP Network

Pancreas identification and segmentation is an essential task in the diagnosis and prognosis of pancreas disease. Although deep neural networks have been widely applied in abdominal organ segmentation, it is still challenging for small organs (e.g. pancreas) that present low contrast, highly flexible anatomical structure and relatively small region. In recent years, coarse-to-fine methods have improved pancreas segmentation accuracy by using coarse predictions in the fine stage, but only object location is utilized and rich image context is neglected. In this paper, we propose a novel distance-based saliency-aware model, namely DSD-ASPP-Net, to fully use coarse segmentation to highlight the pancreas feature and boost accuracy in the fine segmentation stage. Specifically, a DenseASPP (Dense Atrous Spatial Pyramid Pooling) model is trained to learn the pancreas location and probability map, which is then transformed into saliency map through geodesic distance-based saliency transformation. In the fine stage, saliency-aware modules that combine saliency map and image context are introduced into DenseASPP to develop the DSD-ASPP-Net. The architecture of DenseASPP brings multi-scale feature representation and achieves larger receptive field in a denser way, which overcome the difficulties brought by variable object sizes and locations. Our method was evaluated on both public NIH pancreas dataset and local hospital dataset, and achieved an average Dice-Sorensen Coefficient (DSC) value of 85.49 +/- 4.77% on the NIH dataset, outperforming former coarse-to-fine methods.

Automated summary

In this study, a novel distance-based saliency-aware model, DSD-ASPP-Net, was proposed to improve pancreas feature highlighting and accuracy in the fine segmentation stage. By introducing saliency-aware modules that combine saliency map and image context, the method achieved significant results on both the public NIH pancreas dataset and a local hospital dataset.