Speeding Up the Line-Scan Raman Imaging of Living Cells by Deep Convolutional Neural Network

Abstract

Raman imaging is a promising technique that allows the spatial distribution of different components in the sample to be obtained using the molecular fingerprint information on individual species. However, the imaging speed is the bottleneck for the current Raman imaging methods to monitor the dynamic process of living cells. In this paper, we developed an artificial intelligence assisted fast Raman imaging method over the already fast line scan Raman imaging method. The reduced imaging time is realized by widening the slit and laser beam, and scanning the sample with a large scan step. The imaging quality is improved by a data-driven approach to train a deep convolutional neural network, which statistically learns to transform low-resolution images acquired at a high speed into high-resolution ones that previously were only possible with a low imaging speed. Accompanied with the improvement of the image resolution, the deteriorated spectral resolution as a consequence of a wide slit is also restored, thereby the fidelity of the spectral information is retained. The imaging time can be reduced to within 1 min, which is about five times faster than the state-of-the-art line scan Raman imaging techniques without sacrificing spectral and spatial resolution. We then demonstrated the reliability of the current method using fixed cells. We finally used the method to monitor the dynamic evolution process of living cells. Such an imaging speed opens a door to the label-free observation of cellular events with conventional Raman microscopy.

Surface-enhanced Raman spectroscopy: benefits, trade-offs and future developments

“…A high-deep convolutional neural network (DCNN) assisted fast Raman imaging method was introduced to investigate living cells. 129 By widening the slit and laser beam, the sample was scanned with a larger step than the one used in the typical fast-line scan Raman imaging. To improve the situation of reduced image quality due to the shorter imaging time, the spectral-data sets were processed via a DCNN regression approach to transform the low-resolution images into the highresolution ones.…”

Deep learning a boon for biophotonics?

“…In such cases, fast measurements are needed but they suffer from bad data quality, such as extremely high noise or low spectral/spatial resolution. Deep learning has shown its capability of handling this issue in recent publications . For example, an U‐net was applied to stimulated Raman spectra to reduce noise in the data and hence improve the sensitivity, which helps shorten the spectral acquisition time down to 20 μs without losing sensitivity .…”

“…For example, an U‐net was applied to stimulated Raman spectra to reduce noise in the data and hence improve the sensitivity, which helps shorten the spectral acquisition time down to 20 μs without losing sensitivity . In another investigation the authors applied a deep convolutional neural network to improve the spatial resolution of the Raman hyperspectral data. In this way, the line‐scan Raman measurement was largely accelerated.…”

A decade of alkyne-tag Raman imaging (ATRI): applications in biological systems

“…10 Recently, He et al reported fast imaging by converting a low-resolution image obtained with a few scans to a higher-resolution image using artificial intelligence, trained with a large volume of imaging data. 11 Other developments in spontaneous Raman imaging include multifocus imaging using two-dimensional array illumination, 12 selective illumination for reduced sampling, 13,14 and wide-field imaging. 15,16 Resonance Raman scattering can be employed to enhance the Raman signal of molecules with a chromophore moiety.…”