Abstract
Histopathology image synthesis aims to address the data shortage issue in training deep learning approaches for accurate cancer detection. However, existing methods struggle to produce realistic images that have accurate nuclei boundaries and less artifacts, which limits the application in downstream tasks. To address the challenges, we propose a novel approach that enhances the quality of synthetic images by using nuclei topology and contour regularization. The proposed approach uses the skeleton map of nuclei to integrate nuclei topology and separate touching nuclei. In the loss function, we propose two new contour regularization terms that enhance the contrast between contour and non-contour pixels and increase the similarity between contour pixels. We evaluate the proposed approach on the two datasets using image quality metrics and a downstream task (nuclei segmentation). The proposed approach outperforms Sharp-GAN in all four image quality metrics on two datasets. By integrating 6k synthetic images from the proposed approach into training, a nuclei segmentation model achieves the state-of-the-art segmentation performance on TNBC dataset and its detection quality (DQ), segmentation quality (SQ), panoptic quality (PQ), and aggregated Jaccard index (AJI) is 0.855, 0.863, 0.691, and 0.683, respectively.
Abstract (translated)
结构病理图像合成的目标是解决在训练准确检测癌症的深度学习方法所需的数据短缺问题。然而,现有的方法 struggle 去制造具有准确核边界且较少人为干涉的图像,这限制了其在后续任务中的应用。为了解决这些问题,我们提出了一种新的方法来通过使用核形态结构和轮廓Regularization来提高合成图像的质量。我们建议使用核形态结构的轮廓图来整合核形态结构并分离接触的核。在损失函数中,我们提出了两个轮廓 Regularization 术语,以增强轮廓和非轮廓像素之间的对比度并增加轮廓像素之间的相似性。我们使用两个 datasets 评估了 proposed 方法,并使用一个后续任务(核分割)进行了评估(检测质量(DQ)、分割质量(SQ)、普适质量(PQ)和聚合Jaccard指数(AJI)分别为0.855、0.863、0.691和0.683)。通过将从 proposed 方法中收集的6k 合成图像整合到训练中,一个核分割模型在TNBC数据集上实现了最先进的分割性能,其检测质量(DQ)、分割质量(SQ)、普适质量(PQ)和聚合Jaccard指数(AJI)分别为0.855、0.863、0.691和0.683。
URL
https://arxiv.org/abs/2301.10187
