Denoising of stimulated Raman scattering microscopy images via deep learning

Abstract

Stimulated Raman scattering (SRS) microscopy is a label-free quantitative chemical imaging technique that has demonstrated great utility in biomedical imaging applications ranging from real-time stain-free histopathology to live animal imaging. However, similar to many other nonlinear optical imaging techniques, SRS images often suffer from low signal to noise ratio (SNR) due to absorption and scattering of light in tissue as well as the limitation in applicable power to minimize photodamage. We present the use of a deep learning algorithm to significantly improve the SNR of SRS images. Our algorithm is based on a U-Net convolutional neural network (CNN) and significantly outperforms existing denoising algorithms. More importantly, we demonstrate that the trained denoising algorithm is applicable to images acquired at different zoom, imaging power, imaging depth, and imaging geometries that are not included in the training. Our results identify deep learning as a powerful denoising tool for biomedical imaging at large, with potential towards in vivo applications, where imaging parameters are often variable and ground-truth images are not available to create a fully supervised learning training set.

Does deep learning always outperform simple linear regression in optical imaging?

“…In recent years, deep learning receives much attention in many research fields including optical design [1,2] and optical imaging [3]. In previous works, deep learning has been extensively applied for many optical imaging problems including phase retrieval [4][5][6][7], microscopic image enhancement [8][9], scattering imaging [10][11], holography [12][13][14][15][16][17][18], single-pixel imaging [19,20], super-resolution [21][22][23][24], Fourier ptychography [25][26][27], optical interferometry [28,29], wavefront sensing [30,31], and optical fiber communications [32].…”

Deep Learning‐Based Single‐Cell Optical Image Studies

“…Deep learning can deeply explore the cellular structure and morphological information in bright‐field images . Some improved label‐free cell Raman scattering imaging techniques are used to study the cell chemical components, such as stimulated Raman scattering, surface enhanced Raman scattering and coherent antistokes Raman scattering, deep learning techniques have emerged in these studies as high‐performance and powerful analytical tools . Deep learning is also applied to other advanced label‐free cell imaging technologies, such as holographic microscopy , time stretch quantitative phase imaging , phase contrast microscopy , and hyperspectral imaging .…”

Photon Scattering Signal Amplification in Gold-Viral Particle Ligation Towards Fast Infection Screening

“…Devalla et al proposed a deep convolutional code-decode network for image denoising [23]; Bepler et al use a deeper network structure and residual learning algorithm to improve the denoising performance [24]. Manifold et al proved that neural networks can also learn to recognise self-similarity between images [25]. Inspired by work of Ledig et al [26], we used a generative adversarial network to denoise the original images.…”