Zhanlan Chen1, Xiuying Wang2, Ke Yan3, Jiangbin Zheng4. 1. School of Software, Northwestern Polytechnical University, Xi'an, China. 2. School of Computer Science, University of Sydney, Sydney, Australia. xiu.wang@sydney.edu.au. 3. School of Computer Science, University of Sydney, Sydney, Australia. 4. School of Software, Northwestern Polytechnical University, Xi'an, China. zhengjb@nwpu.edu.cn.
Abstract
PURPOSE: Pancreas segmentation from computed tomography (CT) images is an important step in surgical procedures such as cancer detection and radiation treatment. While manual segmentation is time-consuming and operator-dependent, current computer-assisted segmentation methods are facing challenges posed by varying shapes and sizes. To address these challenges, this paper presents a multi-scale feature fusion (MsFF) model for accurate pancreas segmentation from CT images. METHODS: The proposed MsFF is built upon the well-recognized encoder-decoder framework. Firstly, in the encoder stage, the squeeze-and-excitation module is incorporated to enhance the learning of features by exploiting channel-wise independence. Secondly, a hierarchical fusion module is introduced to better utilize both low-level and high-level features to retain boundary information and make final predictions. RESULTS: The proposed MsFF is evaluated on the NIH pancreas dataset and outperforms the current state-of-the-art methods, by achieving a mean of 87.26% and 22.67% under the Dice Sorensen Coefficient and Volumetric Overlap Error, respectively. CONCLUSION: The experimental results confirm that the incorporation of squeeze-and-excitation and hierarchical fusion modules contributes to a net gain in the performance of our proposed MsFF.
PURPOSE: Pancreas segmentation from computed tomography (CT) images is an important step in surgical procedures such as cancer detection and radiation treatment. While manual segmentation is time-consuming and operator-dependent, current computer-assisted segmentation methods are facing challenges posed by varying shapes and sizes. To address these challenges, this paper presents a multi-scale feature fusion (MsFF) model for accurate pancreas segmentation from CT images. METHODS: The proposed MsFF is built upon the well-recognized encoder-decoder framework. Firstly, in the encoder stage, the squeeze-and-excitation module is incorporated to enhance the learning of features by exploiting channel-wise independence. Secondly, a hierarchical fusion module is introduced to better utilize both low-level and high-level features to retain boundary information and make final predictions. RESULTS: The proposed MsFF is evaluated on the NIH pancreas dataset and outperforms the current state-of-the-art methods, by achieving a mean of 87.26% and 22.67% under the Dice Sorensen Coefficient and Volumetric Overlap Error, respectively. CONCLUSION: The experimental results confirm that the incorporation of squeeze-and-excitation and hierarchical fusion modules contributes to a net gain in the performance of our proposed MsFF.
Authors: Holger R Roth; Le Lu; Nathan Lay; Adam P Harrison; Amal Farag; Andrew Sohn; Ronald M Summers Journal: Med Image Anal Date: 2018-02-01 Impact factor: 8.545