Multi-task generative adversarial learning for nuclei segmentation with dual attention and recurrent convolution
Multi-task generative adversarial learning for nuclei segmentation with dual attention and recurrent convolution
复制标题
具有双重注意和循环卷积的细胞核分割的多任务生成对抗学习
DOI：
10.1016/j.bspc.2022.103558
复制
发表时间：
2022
影响因子：
5.1
通讯作者：
Xiaonan Luo
中科院分区：
文献类型：
--
作者：
Huadeng Wang;Guang Xu;Xipeng Pan;Zhenbing Liu;Rushi Lan;Xiaonan Luo
·构建了一种新的基于多任务深度学习的核分割模型。·提出了一种将改进的U网与生成性对抗性学习相结合的方法。·双重注意和递归卷积获得了良好的分割性能。·对于多器官分割应用具有良好的泛化能力。病理图像是诊断和评价癌症的金标准。细胞核分割是对病理图像进行定量分析的基础。尽管目前基于深度学习的核分割方法总体上要好于传统的核分割方法，但它们仍然存在过度分割和欠分割的问题，特别是当核子相互粘连和重叠时。因此，如何有效地区分不同的原子核一直是一个具有挑战性的任务。本文结合改进的U网和产生式对抗性学习，提出了一种新的核分割方法。通过引入空间和通道映射表(SC-MT)注意机制，缓解了核过度分割和欠分割的问题，并且循环卷积单元将有助于核轮廓拓扑的连续性。在多核分割数据集上的大量实验结果表明，该方法能够有效地区分粘连核和重叠核，并具有较好的性能。代码将在https://github.com/antifen/Nuclei-Segmentation上获得。
• Constructing A novel multi-task deep learning-based model for nuclei segmentation. • Proposing a method integrating improved U-Net and generative adversarial learning. • Dual attention and recurrent convolution achieve good segmentation performance. • Good generalization ability for multi-organ segmentation applications. Pathological image is the gold standard for diagnosis and evaluation of cancer. Nuclei segmentation is the basis for quantitative analysis of the pathological image. Although the current deep learning-based nuclei segmentation methods generally perform better than the traditional ones, They are still plagued by over-segmentation and under-segmentation, especially when the nuclei are adherent and overlapping with each other. Therefore, how to effectively distinguish different nuclei has always been a challenging task. In this paper, we proposed a novel segmentation method for nuclei via integrating improved U-Net and generative adversarial learning. By introducing spatial and channel mapping table (SC-MT) attention mechanism, the issues about nuclei over-segmentation and under-segmentation have been alleviated and recurrent convolution units will contribute to the continuity of nuclei contours topology. Extensive experimental results on multiple nuclei segmentation datasets show that the proposed method can effectively distinguish the adherent and overlapping nuclei with robust performance. The code will be available at: https://github.com/antifen/Nuclei-Segmentation .