12/7/2023 0 Comments Deeper con![]() ![]() Then, by combining (i) and (ii) we achieve extreme speed-ups of up to 160x in Raman imaging time while maintaining high reconstruction fidelity. Next, we (ii) train a hyperspectral residual channel attention neural network to accurately reconstruct high spatial resolution hyperspectral Raman images from corresponding low spatial resolution hyper-spectral Raman images to significantly reduce imaging times. To improve the speed of Raman spectroscopic imaging and enable high-throughput applications, we first (i) train a 1D ResUNet neural network for Raman spectral denoising to effectively reconstruct a high SNR Raman spectrum (long acquisition time) from a corresponding low SNR input spectrum (short acquisition time). DeepeR provides a foundation that will enable a host of higher-throughput Raman spectroscopy and molecular imaging applications across biomedicine.ĭeepeR is designed to operate on hyperspectral Raman images, where high information-content Raman spectra at each pixel provide detailed insight into the molecular composition of cells/tissues. Finally, transfer learning is applied to extend DeepeR from cell to tissue-scale imaging. ![]() We further demonstrate Raman imaging speed-up of 160x, useful for lower resolution imaging applications such as the rapid screening of large areas or for spectral pathology. Combining these approaches, we achieve Raman imaging speed-ups of up to 40-90x, enabling good quality cellular imaging with high resolution, high signal-to-noise ratio in under one minute. Next, we develop a neural network for robust 2–4x spatial super-resolution of hyperspectral Raman images that preserves molecular cellular information. We firstly perform denoising and re-construction of low signal-to-noise ratio Raman molecular signatures via deep learning, with a 10x improvement in mean squared error over common Raman filtering methods. Here, we present a comprehensive framework for higher-throughput molecular imaging via deep learning enabled Raman spectroscopy, termed DeepeR, trained on a large dataset of hyperspectral Raman images, with over 1.5 million spectra (400 hours of acquisition) in total. Raman spectroscopy enables non-destructive, label-free imaging with unprecedented molecular contrast but is limited by slow data acquisition, largely preventing high-throughput imaging applications. The code was implemented in Python 3.7.3 using PyTorch 1.4.0 on a desktop computer with a Core i7-8700 CPU at 3.2 GHz (Intel), 32 GB of RAM, and a Titan V GPU (NVIDIA), running Windows 10 (Microsoft). Bergholt, "High-throughput molecular imaging via deep learning enabled Raman spectroscopy", Analytical Chemistry 2021, 93, 48, 15850-15860. Horgan, Magnus Jensen, Anika Nagelkerke, Jean-Phillipe St-Pierre, Tom Vercauteren, Molly M. This repository is for DeepeR, introduced in the following paper:Ĭonor C. High-throughput molecular imaging via deep learning enabled Raman spectroscopy ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |