Sharp-GAN: Sharpness Loss Regularized GAN for Histopathology Image Synthesis
This work addresses the need for large annotated datasets in histopathology image analysis by improving synthetic image quality, though it is incremental as it builds on conditional GANs with a new loss function.
The authors tackled the problem of generating synthetic histopathology images with clear nuclei contours, which is challenging due to overlapped and touching nuclei in existing methods, and achieved realistic image synthesis as demonstrated by quantitative metrics and segmentation results on two public datasets.
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.