当前位置: X-MOL 学术IEEE J. Biomed. Health Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
GCSBA-Net: Gabor-Based and Cascade Squeeze Bi-Attention Network for Gland Segmentation
IEEE Journal of Biomedical and Health Informatics ( IF 7.7 ) Pub Date : 2020-08-11 , DOI: 10.1109/jbhi.2020.3015844
Zhijie Wen 1 , Ru Feng 1 , Jingxin Liu 2 , Ying Li 3 , Shihui Ying 1
Affiliation  

Colorectal cancer is the second and the third most common cancer in women and men, respectively. Pathological diagnosis is the “gold standard” for tumor diagnosis. Accurate segmentation of glands from tissue images is a crucial step in assisting pathologists in their diagnosis. The typical methods for gland segmentation form a dense image representation, ignoring its texture and multi-scale attention information. Therefore, we utilize a Gabor-based module to extract texture information at different scales and directions in histopathology images. This paper also designs a Cascade Squeeze Bi-Attention (CSBA) module. Specifically, we add Atrous Cascade Spatial Pyramid (ACSP), Squeeze Position Attention (SPA) module and Squeeze Channel Attention module (SCA) to model semantic correlation and maintain the multi-level aggregation on the spatial pyramid with different dilations. Besides, to solve the imbalance of data distribution and boundary blur, we propose a hybrid loss function to response the object boudary better. The experimental results show that the proposed method achieves state-of-the-art performance on the GlaS challenge dataset and CRAG colorectal adenocarcinoma dataset, respectively.

中文翻译:

GCSBA-Net:用于腺体分割的基于 Gabor 和 Cascade Squeeze Bi-Attention 网络

结直肠癌分别是女性和男性中第二和第三位最常见的癌症。病理诊断是肿瘤诊断的“金标准”。从组织图像中准确分割腺体是协助病理学家进行诊断的关键步骤。腺体分割的典型方法形成密集图像表示,忽略其纹理和多尺度注意信息。因此,我们利用基于 Gabor 的模块来提取组织病理学图像中不同尺度和方向的纹理信息。本文还设计了一个 Cascade Squeeze Bi-Attention (CSBA) 模块。具体来说,我们添加了 Atrous Cascade Spatial Pyramid (ACSP),Squeeze Position Attention (SPA) 模块和 Squeeze Channel Attention 模块 (SCA) 对语义相关性进行建模,并在不同膨胀的空间金字塔上保持多级聚合。此外,为了解决数据分布不平衡和边界模糊的问题,我们提出了一种混合损失函数来更好地响应对象边界。实验结果表明,所提出的方法分别在 GlaS 挑战数据集和 CRAG 结直肠腺癌数据集上达到了最先进的性能。
更新日期:2020-08-11
down
wechat
bug