ResDAC-Net: a novel pancreas segmentation model utilizing residual double asymmetric spatial kernels

Abstract

The pancreas not only is situated in a complex abdominal background but is also surrounded by other abdominal organs and adipose tissue, resulting in blurred organ boundaries. Accurate segmentation of pancreatic tissue is crucial for computer-aided diagnosis systems, as it can be used for surgical planning, navigation, and assessment of organs. In the light of this, the current paper proposes a novel Residual Double Asymmetric Convolution Network (ResDAC-Net) model. Firstly, newly designed ResDAC blocks are used to highlight pancreatic features. Secondly, the feature fusion between adjacent encoding layers fully utilizes the low-level and deep-level features extracted by the ResDAC blocks. Finally, parallel dilated convolutions are employed to increase the receptive field to capture multiscale spatial information. ResDAC-Net is highly compatible to the existing state-of-the-art models, according to three (out of four) evaluation metrics, including the two main ones used for segmentation performance evaluation (i.e., DSC and Jaccard index).

Keywords: Image segmentation; Medical image processing; Pancreatic segmentation; ResDAC-Net.

Fig. 1

The elaborated ResDAC block

Fig. 2

The elaborated ALF block

Fig. 3

The elaborated PDC block

Fig. 4

The proposed ResDAC-Net model

Fig. 5

The DSC validation curves of the compared models

Fig. 6

The DSC training curves of the compared models

Fig. 7

Sample visualizations of pancreas segmentation results of different models on NIH dataset