Camp Charles H, Bender John S, Lee Young Jong
Opt Express. 2020 Jul 6;28(14):20422-20437. doi: 10.1364/OE.397606.
We present a new collection of processing techniques, collectively "factorized Kramers-Kronig and error correction" (fKK-EC), for (a) Raman signal extraction, (b) denoising, and (c) phase- and scale-error correction in coherent anti-Stokes Raman scattering (CARS) hyperspectral imaging and spectroscopy. These new methods are orders-of-magnitude faster than conventional methods and are capable of real-time performance, owing to the unique core concept: performing all processing on a small basis vector set and using matrix/vector multiplication afterwards for direct and fast transformation of the entire dataset. Experimentally, we demonstrate that a 703026 spectra image of chicken cartilage can be processed in 70 s (≈ 0.1 ms / spectrum), which is ≈ 70 times faster than with the conventional workflow (≈7.0 ms / spectrum). Additionally, we discuss how this method may be used for machine learning (ML) by re-using the transformed basis vector sets with new data. Using this ML paradigm, the same tissue image was processed (post-training) in ≈ 33 s, which is a speed-up of ≈ 150 times when compared with the conventional workflow.
我们提出了一组新的处理技术，统称为“因式分解的克拉默斯-克勒尼希变换与误差校正”（fKK-EC），用于（a）拉曼信号提取、（b）去噪以及（c）相干反斯托克斯拉曼散射（CARS）高光谱成像和光谱中的相位和尺度误差校正。这些新方法比传统方法快几个数量级，并且能够实现实时性能，这得益于其独特的核心概念：在一个小的基向量集上执行所有处理，然后使用矩阵/向量乘法对整个数据集进行直接快速变换。在实验中，我们证明了一张包含703026个光谱的鸡软骨图像可以在70秒内处理完成（≈0.1毫秒/光谱），这比传统工作流程快约70倍（≈7.0毫秒/光谱）。此外，我们还讨论了如何通过将变换后的基向量集与新数据重新使用，将该方法用于机器学习（ML）。使用这种ML范式，同一组织图像在训练后处理时间约为33秒，与传统工作流程相比，速度提高了约150倍。
