Learning a Discriminative Feature Attention Network for pancreas CT segmentation

• 作者: HUANG Mei-xiang WANG Yuan-jin HUANG Chong-fei YUAN Jing KONG De-xing
• 来源期刊: 高校应用数学学报B辑（英文版）
• 年，卷（期）: 2022,（1）
• 所属期刊栏目: Pages
• 页码范围: 73-90
• 页数: 18页
• 语种: 英文
• DOI: 10.3969/j.issn.1005-1031.2022.01.005

摘要

Accurate pancreas segmentation is critical for the diagnosis and management of diseases of the pancreas.It is challenging to precisely delineate pancreas due to the highly vari-ations in volume,shape and location.In recent years,coarse-to-fine methods have been widely used to alleviate class imbalance issue and improve pancreas segmentation accuracy.However,cascaded methods could be computationally intensive and the refined results are significantly dependent on the performance of its coarse segmentation results.To balance the segmentation accuracy and computational efficiency,we propose a Discriminative Feature Attention Network for pancreas segmentation,to effectively highlight pancreas features and improve segmentation accuracy without explicit pancreas location.The final segmentation is obtained by applying a simple yet effective post-processing step.Two experiments on both public NIH pancreas CT dataset and abdominal BTCV multi-organ dataset are individually conducted to show the ef-fectiveness of our method for 2D pancreas segmentation.We obtained average Dice Similarity Coefficient (DSC) of 82.82±6.09％,average Jaccard Index (JI) of 71.13± 8.30％ and average Symmetric Average Surface Distance (ASD) of 1.694± 0.83 mm on the NIH dataset.Compared to the existing deep learning-based pancreas segmentation methods,our experimental results achieve the best average DSC and JI value.