Butte Sujata, Wang Haotian, Xian Min, Vakanski Aleksandar
Department of Computer Science, University of Idaho, Idaho, USA.
Proc IEEE Int Symp Biomed Imaging. 2022 Mar;2022. doi: 10.1109/isbi52829.2022.9761534. Epub 2022 Apr 26.
Existing deep learning-based approaches for histopathology image analysis require large annotated training sets to achieve good performance; but annotating histopathology images is slow and resource-intensive. Conditional generative adversarial networks have been applied to generate synthetic histopathology images to alleviate this issue, but current approaches fail to generate clear contours for overlapped and touching nuclei. In this study, We propose a sharpness loss regularized generative adversarial network to synthesize realistic histopathology images. The proposed network uses normalized nucleus distance map rather than the binary mask to encode nuclei contour information. The proposed sharpness loss enhances the contrast of nuclei contour pixels. The proposed method is evaluated using four image quality metrics and segmentation results on two public datasets. Both quantitative and qualitative results demonstrate that the proposed approach can generate realistic histopathology images with clear nuclei contours.
现有的基于深度学习的组织病理学图像分析方法需要大量带注释的训练集才能取得良好的性能；但注释组织病理学图像既缓慢又耗费资源。条件生成对抗网络已被用于生成合成组织病理学图像以缓解这一问题，但目前的方法无法为重叠和相互接触的细胞核生成清晰的轮廓。在本研究中，我们提出了一种锐度损失正则化生成对抗网络来合成逼真的组织病理学图像。所提出的网络使用归一化的细胞核距离图而不是二值掩码来编码细胞核轮廓信息。所提出的锐度损失增强了细胞核轮廓像素的对比度。使用四个图像质量指标和在两个公共数据集上的分割结果对所提出的方法进行了评估。定量和定性结果均表明，所提出的方法可以生成具有清晰细胞核轮廓的逼真组织病理学图像。
