Sharp-GAN: Sharpness Loss Regularized GAN for Histopathology Image Synthesis

TL;DR

This paper introduces Sharp-GAN, a novel GAN model that uses a sharpness loss and nucleus distance maps to generate realistic histopathology images with clear nuclei contours, improving over existing methods.

Contribution

The paper presents a sharpness loss regularization and a new encoding of nuclei contours that enhance the realism and clarity of generated histopathology images.

Findings

Generated images have clearer nuclei contours.

Quantitative metrics show improved image quality.

Segmentation results are enhanced with the proposed method.

Abstract

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.