| 引用本文: | 周孟然,刘思怡,卞 凯,王 宁,高立鹏.基于混合域注意力 ResNeSt 的结肠息肉分割模型(J/M/D/N,J:杂志，M：书，D：论文，N：报纸).期刊名称,2025，42（1）：85-93 |
| CHEN X. Adap tive slidingmode contr ol for discrete2ti me multi2inputmulti2 out put systems[ J ]. Aut omatica, 2006, 42(6): 4272-435 |
|
| 摘要: |
| 目的 针对因息肉大小不一,边界不清,光线影响,在图片中所占比例较小导致的分割精度不高的问题,提出
了一种改进的 U 型结构网络 BMR-Net。 方法 该模型的框架为编码器-解码器形式,在编码器部分采用 ResNeSt 提
取特征,在计算成本增加很少的情况下改善了特征提取效果; 在编码器和解码器之间设计边界预测生成模块
( BPGM) 来聚合高层特征并加入改良空间金字塔池化模块,在其中引入注意力机制,提升多尺度信息融合效果,获
得更精确的全局特征图表示;针对不清晰的边缘部分采用反向注意力模块,删除已预测区域,校正边界信息。 结果
在 CVC-ClinicDB、Kvasir - SEG、CVC - ColonDB、 ETIS - Larib、 EndoScene 数据集上进行测试, mDice 值分别达到了
0. 930、0. 903、0. 743、0. 712、0. 874。 结论 该方法分割性能和泛化性能均优于其他的先进方法,并且可以更加精确
和完整地分割出小尺寸息肉,可以为结肠息肉患者提供早期预后信息。 |
| 关键词: 图像分割 结肠息肉 ResNeSt 编解码网络 注意力机制 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Colon Polyp Segmentation Model Based on Mixed-domain Attention ResNeSt |
|
ZHOU Mengran LIU Siyi BIAN Kai WANG Ning GAO Lipeng
|
|
School of Electrical and Information Engineering Anhui University of Science and Technology Anhui Huainan 232001
China
|
| Abstract: |
| Objective To address the challenges posed by polyps of varied sizes unclear boundaries lighting effects and
their relatively small proportions in images that result in lower segmentation accuracy an improved U-shaped network
structure BMR-Net was proposed. Methods The model adopted an encoder-decoder architecture. The encoder partially
utilized ResNeSt for feature extraction enhancing the feature extraction performance with only a slight increase in
computational cost. Between the encoder and the decoder a boundary prediction generation module BPGM was
designed to aggregate high-level features and incorporate a modified spatial pyramid pooling module in which an attention
mechanism was introduced. This promoted multi-scale information fusion obtaining a more accurate global feature map
representation. For unclear edge areas a reverse attention module was applied to remove previously predicted areas and
correct the boundary information. Results Tests were conducted on the CVC-ClinicDB Kvasir-SEG CVC-ColonDB
ETIS-Larib and EndoScene datasets with mDice values reaching 0. 930 0. 903 0. 743 0. 712 and 0. 874
respectively. Conclusion This method outperforms other advanced methods in terms of segmentation performance and generalization ability. Furthermore it can segment small-sized polyps more precisely and completely providing early
prognosis information for patients with colon polyps. |
| Key words: image segmentation colonic polyps ResNeSt encoder-decoder network attention mechanism |
