RepE: unsupervised representation learning for image enhancement in nonlinear optical microscopy

Abstract

We present an unsupervised learning denoising method, RepE (representation and enhancement), designed for nonlinear optical microscopy images, such as second harmonic generation (SHG) and two-photon fluorescence (TPEF). Addressing the challenge of effectively denoising images with various noise types, RepE employs an encoder network to learn noise-free representations and a reconstruction network to generate denoised images. It offers several key advantages, including its ability to (i) operate without restrictive statistic assumptions, (ii) eliminate the need for clean-noisy pairs, and (iii) requires only a few training images. Comparative evaluations on real-world SHG and TPEF images from esophageal cancer tissue slides (ESCC) demonstrate that our method outperforms existing techniques in image quality metrics. The proposed method provides a practical, robust solution for denoising nonlinear optical microscopy images, and it has the potential to be extended to other nonlinear optical microscopy modalities.