We introduce a broadband coherent anti-Stokes Raman scattering (CARS) microscope based on a 2-MHz repetition rate ytterbium laser generating 1035-nm high-energy (≈µJ level) femtosecond pulses. These features of the driving laser allow producing broadband red-shifted Stokes pulses, covering the whole fingerprint region (400–1800 cm⁻¹), employing supercontinuum generation in a bulk crystal. Our system reaches state-of-the-art acquisition speed (<1 ms/pixel) and unprecedented sensitivity of ≈14.1 mmol/L when detecting dimethyl sulfoxide in water. To further improve the performance of the system and to enhance the signal-to-noise ratio of the CARS spectra, we designed a convolutional neural network for spectral denoising, coupled with a post-processing pipeline to distinguish different chemical species of biological tissues.

Coherent anti-Stokes Raman scattering (CARS) microscopy is an emerging nonlinear vibrational imaging technique that delivers label-free chemical maps of cells and tissues. In narrowband CARS, two spatiotemporally superimposed picosecond pulses, pump and Stokes, illuminate the sample to interrogate a single vibrational mode. Broadband CARS (BCARS) combines narrowband pump pulses with broadband Stokes pulses to record broad vibrational spectra. Despite recent technological advancements, BCARS microscopes still struggle to image biological samples over the entire Raman-active region (400-3100 cm^-1). Here, we demonstrate a robust BCARS platform that answers this need. Our system is based on a femtosecond ytterbium laser at a 1035 nm wavelength and a 2 MHz repetition rate, which delivers high-energy pulses used to produce broadband Stokes pulses by white-light continuum generation in a bulk YAG crystal. Combining such pulses, pre-compressed to sub-20 fs duration, with narrowband pump pulses, we generate a CARS signal with a high (<9 cm^-1) spectral resolution in the whole Raman-active window, exploiting both the two-color and three-color excitation mechanisms. Aided by an innovative post-processing pipeline, our microscope allows us to perform high-speed (≈1 ms pixel dwell time) imaging over a large field of view, identifying the main chemical compounds in cancer cells and discriminating tumorous from healthy regions in liver slices of mouse models, paving the way for applications in histopathological settings.

The last decades saw a huge rise of artificial intelligence (AI) as a powerful tool to boost industrial and scientific research in a broad range of fields. AI and photonics are developing a promising two‐way synergy: on the one hand, AI approaches can be used to control a number of complex linear and nonlinear photonic processes, both in the classical and quantum regimes; on the other hand, photonics can pave the way for a new class of platforms to accelerate AI‐tasks. This review provides the reader with the fundamental notions of machine learning (ML) and neural networks (NNs) and presents the main AI applications in the fields of spectroscopy and chemometrics, computational imaging (CI), wavefront shaping and quantum optics. The review concludes with an overview of future developments of the promising synergy between AI and photonics.

Anticancer therapy screening in vitro identifies additional treatments and improves clinical outcomes. Systematically, although most tested cells respond to cues with apoptosis, an appreciable portion enters a senescent state, a critical condition potentially driving tumor resistance and relapse. Conventional screening protocols would strongly benefit from prompt identification and monitoring of therapy-induced senescent (TIS) cells in their native form. We combined complementary all-optical, label-free, and quantitative microscopy techniques, based on coherent Raman scattering, multiphoton absorption, and interferometry, to explore the early onset and progression of this phenotype, which has been understudied in unperturbed conditions. We identified TIS manifestations as early as 24 hours following treatment, consisting of substantial mitochondrial rearrangement and increase of volume and dry mass, followed by accumulation of lipid vesicles starting at 72 hours. This work holds the potential to affect anticancer treatment research, by offering a label-free, rapid, and accurate method to identify initial TIS in tumor cells.

Pump–probe spectroscopy is a gold standard technique to investigate ultrafast electronic dynamics of material systems. Pulsed laser sources employed to pump and probe samples feature typically high peak power, which may give rise to coherent artifacts under a wide range of experimental conditions. Among those, the Cross-Phase Modulation (XPM) artifact has gathered particular attention as it produces particularly high signal distortions, in some cases hiding a relevant portion of the dynamics of interest. Here, we present a novel approach for the removal of XPM coherent artifacts in ultrafast pump–probe spectroscopy, based on deep learning. We developed XPMnet, a convolutional neural network able to reconstruct electronic relaxation dynamics otherwise embedded in artifact distortions, thus enabling the retrieval of fundamental information to characterize the material system under investigation. We validated XPMnet on Indium Tin Oxide (ITO), a heavily doped semiconductor displaying a plasmon resonance in the near-infrared, which is a key material for the development of infrared plasmonic devices. Pump–probe measurements of ITO show strong XPM artifacts that overwhelm the electronic cooling dynamics of interest due to the low optical density of the material at near-infrared photon energies. XPMnet retrieved ITO electronic dynamics in excellent agreement with expected outcomes in terms of material-specific time constants. This artificial intelligence method constitutes a powerful solution for XPM artifact removal, providing high accuracy and short execution time. We believe that this model could be integrated in real time in pump–probe setups to increase the amount of information one can derive from ultrafast spectroscopy measurements.

Broadband Coherent anti-Stokes Raman (BCARS) microscopy is an imaging technique that can acquire full Raman spectra (400–3200 cm⁻¹) of biological samples within a few milliseconds. However, the CARS signal suffers from an undesired non-resonant background (NRB), deriving from four-wave-mixing processes, which distorts the peak line shapes and reduces the chemical contrast. Traditionally, the NRB is removed using numerical algorithms that require expert users and knowledge of the NRB spectral profile. Recently, deep-learning models proved to be powerful tools for unsupervised automation and acceleration of NRB removal. Here, we thoroughly review the existing NRB removal deep-learning models (SpecNet, VECTOR, LSTM, Bi-LSTM) and present two novel architectures. The first one combines convolutional layers with Gated Recurrent Units (CNN + GRU); the second one is a Generative Adversarial Network (GAN) that trains an encoder-decoder network and an adversarial convolutional neural network. We also introduce an improved training dataset, generalized on different BCARS experimental configurations. We compare the performances of all these networks on test and experimental data, using them in the pipeline for spectral unmixing of BCARS images. Our analyses show that CNN + GRU and VECTOR are the networks giving the highest accuracy, GAN is the one that predicts the highest number of true positive peaks in experimental data, whereas GAN and VECTOR are the most suitable ones for real-time processing of BCARS images.