Impact of specific electromagnetic radiation on wakefulness in mice.

Electromagnetic radiation (EMR) in the environment, particularly in the microwave range, may constitute a public health concern. Exposure to 2.4 GHz EMR modulated by 100 Hz square pulses was recently reported to markedly increase wakefulness in mice. Here, we demonstrate that a similar wakefulness increase can be induced by the modulation frequency of 1,000 Hz, but not 10 Hz. In contrast to the carrier frequency of 2.4 GHz, 935 MHz EMR of the same power density has little impact on wakefulness irrespective of modulation frequency. Notably, the replacement of the 100 Hz square-pulsed modulation by sinusoidal-pulsed modulation of 2.4 GHz EMR still allows a marked increase of wakefulness. In contrast, continuous sinusoidal amplitude modulation of 100 Hz with the same time-averaged power output fails to trigger any detectable change of wakefulness. Therefore, alteration of sleep behavior by EMR depends upon not just carrier frequency but also frequency and mode of the modulation. These results implicate biological sensing mechanisms for specific EMR in animals.

Interactions between electromagnetic radiation and biological systems.

Even though the bioeffects of electromagnetic radiation (EMR) have been extensively investigated during the past several decades, our understandings of the bioeffects of EMR and the mechanisms of the interactions between the biological systems and the EMRs are still far from satisfactory. In this article, we introduce and summarize the consensus, controversy, limitations, and unsolved issues. The published works have investigated the EMR effects on different biological systems including humans, animals, cells, and biochemical reactions. Alternative methodologies also include dielectric spectroscopy, detection of bioelectromagnetic emissions, and theoretical predictions. In many studies, the thermal effects of the EMR are not properly controlled or considered. The frequency of the EMR investigated is limited to the commonly used bands, particularly the frequencies of the power line and the wireless communications; far fewer studies were performed for other EMR frequencies. In addition, the bioeffects of the complex EM environment were rarely discussed. In summary, our understanding of the bioeffects of the EMR is quite restrictive and further investigations are needed to answer the unsolved questions.

Compressed single-shot 3D photoacoustic imaging with a single-element transducer.

Three-dimensional (3D) photoacoustic imaging (PAI) can provide rich information content and has gained increasingly more attention in various biomedical applications. However, current 3D PAI methods either involves pointwise scanning of the 3D volume using a single-element transducer, which can be time-consuming, or requires an array of transducers, which is known to be complex and expensive. By utilizing a 3D encoder and compressed sensing techniques, we develop a new imaging modality that is capable of single-shot 3D PAI using a single-element transducer. The proposed method is validated with phantom study, which demonstrates single-shot 3D imaging of different objects and 3D tracking of a moving object. After one-time calibration, while the system could perform single-shot 3D imaging for different objects, the calibration could remain effective over 7 days, which is highly beneficial for practical translation. Overall, the experimental results showcase the potential of this technique for both scientific research and clinical applications.

Expression and Activity of the Transcription Factor CCAAT/Enhancer-Binding Protein ß (C/EBPß) Is Regulated by Specific Pulse-Modulated Radio Frequencies in Oligodendroglial Cells.

The rapid growth of wireless electronic devices has raised concerns about the harmful effects of leaked electromagnetic radiation (EMR) on human health. Even though numerous studies have been carried out to explore the biological effects of EMR, no clear conclusions have been drawn about the effect of radio frequency (RF) EMR on oligodendrocytes. To this end, we exposed oligodendroglia and three other types of brain cells to 2.4 GHz EMR for 6 or 48 h at an average input power of 1 W in either a continuous wave (CW-RF) or a pulse-modulated wave (PW-RF, 50 Hz pulse frequency, 1/3 duty cycle) pattern. RNA sequencing, RT-qPCR, and Western blot were used to examine the expression of C/EBPß and its related genes. Multiple reaction monitoring (MRM) was used to examine the levels of expression of C/EBPß-interacting proteins. Our results showed that PW-RF EMR significantly increased the mRNA level of C/EBPß in oligodendroglia but not in other types of cells. In addition, the expression of three isoforms and several interacting proteins and targeted genes of C/EBPß were markedly changed after 6-h PW-RF but not CW-RF. Our results indicated that RF EMR regulated the expression and functions of C/EBPß in a waveform- and cell-type-dependent manner.

Analysis of electromagnetic response of cells and lipid membranes using a model-free method.

Electromagnetic radiation (EMR) is omnipresent on earth and may interact with the biological systems in diverse manners. But the scope and nature of such interactions remain poorly understood. In this study, we have measured the permittivity of cells and lipid membranes over the EMR frequency range of 20 Hz to 4.35 × 1010 Hz. To identify EMR frequencies that display physically intuitive permittivity features, we have developed a model-free method that relies on a potassium chloride reference solution of direct-current (DC) conductivity equal to that of the target sample. The dielectric constant, which reflects the capacity to store energy, displays a characteristic peak at 105-106 Hz. The dielectric loss factor, which represents EMR absorption, is markedly enhanced at 107-109 Hz. The fine characteristic features are influenced by the size and composition of these membraned structures. Mechanical disruption results in abrogation of these characteristic features. Enhanced energy storage at 105-106 Hz and energy absorption at 107-109 Hz may affect certain membrane activity relevant to cellular function.

Single-shot photoacoustic imaging with single-element transducer through a spatiotemporal encoder.

Significance: Current photoacoustic (PA) imaging modalities typically require either serial detection with a single-element transducer or parallel detections with an ultrasonic array, indicating a dilemma between system cost and imaging throughput. PA topography through ergodic relay (PATER) was recently developed to address this bottleneck. However, PATER requires object-specific calibration due to varied boundary condition and must be recalibrated through pointwise scanning for each object before measurements, which is time-consuming and severely limits practical application. Aim: We aim to develop a new single-shot PA imaging technique that only requires a one-time calibration for imaging different objects using a single-element transducer. Approach: We develop an imaging method, PA imaging through a spatiotemporal encoder (PAISE), to address the above issue. The spatial information is effectively coded into unique temporal features by the spatiotemporal encoder, which allows for compressive image reconstruction. An ultrasonic waveguide is proposed as a critical element to guide the PA waves from the object into the prism, which effectively accounts for the varied boundary condition of different objects. We further add irregular-shaped edges on the prism to introduce randomized internal reflections and further facilitate the scrambling of acoustic waves. Results: The proposed technique is validated through comprehensive numerical simulations and experiments, and it is demonstrated that PAISE can successfully overcome the changed boundary condition and can image different samples given a single calibration. Conclusions: The proposed PAISE technique is capable of single-shot widefield PA imaging with a single-element transducer and does not require sample-specific calibration, which successfully overcomes the major limitation of previous PATER technology.

Quantitative spatial mapping of tissue water and lipid content using spatial frequency domain imaging in the 900- to 1000-nm wavelength region.

Significance: Water and lipid are key participants of many biological processes, but there are few label-free, non-contact optical methods that can spatially map these components in-vivo. Shortwave infrared meso-patterned imaging (SWIR-MPI) is an emerging technique that successfully addresses this need. However, it requires a dedicated SWIR camera to probe the 900- to 1300-nm wavelength region, which hinders practical translation of the technology. Aim: Compared with SWIR-MPI, we aim to develop a new technique that can dramatically reduce the cost in detector while maintaining high accuracy for the quantification of tissue water and lipid content. Approach: By utilizing water and lipid absorption features in the 900- to 1000-nm wavelength region as well as optimal wavelength and spatial frequency combinations, we develop a new imaging technique based on spatial frequency domain imaging to quantitatively map tissue water and lipid content using a regular silicon-based camera. Results: The proposed method is validated with a phantom study, which shows average error of 0.9 ± 1.2 % for water content estimation, and -0.4 ± 0.7 % for lipid content estimation, respectively. The proposed method is also demonstrated for ex vivo porcine tissue lipid mapping as well as in-vivo longitudinal water content monitoring. Conclusions: The proposed technique enables spatial mapping of tissue water and lipid content with the cost in detector reduced by two orders of magnitude compared with SWIR-MPI while maintaining high accuracy. The experimental results highlight the potential of this technique for substantial impact in both scientific and industrial applications.

Structure of the cytoplasmic ring of the Xenopus laevis nuclear pore complex.

INTRODUCTION The nuclear pore complex (NPC) resides on the nuclear envelope (NE) and mediates nucleocytoplasmic cargo transport. As one of the largest cellular machineries, a vertebrate NPC consists of cytoplasmic filaments, a cytoplasmic ring (CR), an inner ring, a nuclear ring, a nuclear basket, and a luminal ring. Each NPC has eight repeating subunits. Structure determination of NPC is a prerequisite for understanding its functional mechanism. In the past two decades, integrative modeling, which combines x-ray structures of individual nucleoporins and subcomplexes with cryo-electron tomography reconstructions, has played a crucial role in advancing our knowledge about the NPC. The CR has been a major focus of structural investigation. The CR subunit of human NPC was reconstructed by cryo-electron tomography through subtomogram averaging to an overall resolution of ~20 Å, with local resolution up to ~15 Å. Each CR subunit comprises two Y-shaped multicomponent complexes known as the inner and outer Y complexes. Eight inner and eight outer Y complexes assemble in a head-to-tail fashion to form the proximal and distal rings, respectively, constituting the CR scaffold. To achieve higher resolution of the CR, we used single-particle cryo-electron microscopy (cryo-EM) to image the intact NPC from the NE of Xenopus laevis oocytes. Reconstructions of the core region and the Nup358 region of the X. laevis CR subunit had been achieved at average resolutions of 5 to 8 Å, allowing identification of secondary structural elements. RATIONALE Packing interactions among the components of the CR subunit were poorly defined by all previous EM maps. Additional components of the CR subunit are strongly suggested by the EM maps of 5- to 8-Å resolution but remain to be identified. Addressing these issues requires improved resolution of the cryo-EM reconstruction. Therefore, we may need to enhance sample preparation, optimize image acquisition, and develop an effective data-processing strategy. RESULTS To reduce conformational heterogeneity of the sample, we spread the opened NE onto the grids with minimal force and used the chemical cross-linker glutaraldehyde to stabilize the NPC. To alleviate orientation bias of the NPC, we tilted sample grids and imaged the sample with higher electron dose at higher angles. We improved the image-processing protocol. With these efforts, the average resolutions for the core and the Nup358 regions have been improved to 3.7 and 4.7 Å, respectively. The highest local resolution of the core region reaches 3.3 Å. In addition, a cryo-EM structure of the N-terminal α-helical domain of Nup358 has been resolved at 3.0-Å resolution. These EM maps allow the identification of five copies of Nup358, two copies of Nup93, two copies of Nup205, and two copies of Y complexes in each CR subunit. Relying on the EM maps and facilitated by AlphaFold prediction, we have generated a final model for the CR of the X. laevis NPC. Our model of the CR subunit includes 19,037 amino acids in 30 nucleoporins. A previously unknown C-terminal fragment of Nup160 was found to constitute a key part of the vertex, in which the short arm, long arm, and stem of the Y complex meet. The Nup160 C-terminal fragment directly binds the ß-propeller proteins Seh1 and Sec13. Two Nup205 molecules, which do not contact each other, bind the inner and outer Y complexes through distinct interfaces. Conformational elasticity of the two Nup205 molecules may underlie their versatility in binding to different nucleoporins in the proximal and distal CR rings. Two Nup93 molecules, each comprising an N-terminal extended helix and an ACE1 domain, bridge the Y complexes and Nup205. Nup93 and Nup205 together play a critical role in mediating the contacts between neighboring CR subunits. Five Nup358 molecules, each in the shape of a shrimp tail and named "the clamp," hold the stems of both Y complexes. The innate conformational elasticity allows each Nup358 clamp to adapt to a distinct local environment for optimal interactions with neighboring nucleoporins. In each CR subunit, the α-helical nucleoporins appear to provide the conformational elasticity; the 12 ß-propellers may strengthen the scaffold. CONCLUSION Our EM map-based model of the X. laevis CR subunit substantially expands the molecular mass over the reported composite models of vertebrate CR subunit. In addition to the Y complexes, five Nup358, two Nup205, and two Nup93 molecules constitute the key components of the CR. The improved EM maps reveal insights into the interfaces among the nucleoporins of the CR. [Figure: see text].

Transcriptome changes in ERGIC3-knockdown hepatocellular carcinoma cells: ERGIC3 is a novel immune function related gene.

Objective: The expression of ERGIC3 is increased in a variety of tumors and promotes the growth and metastasis of liver cancer, but the molecular mechanism needs to be further studied.In this study, we aimed to analyze the molecular mechanism of ERGIC3 regulating the proliferation of human hepatocellular carcinoma (HCC) SMMC-7721 cells using transcriptomics. Methods: ERGIC3 was knocked down in SMMC-7721 cells by RNAi technique, and the expression of ERGIC3 was detected by Q-RT-PCR and Western Blot. RNA sequencing was performed in the Illumina HiSeq platform in the control group and the ERGIC3i group and bioinformatics methods were selected to analyze the data. Results: The expression of ERGIC3 was reduced to 10% in SMMC-7721 cells by RNAi technique, and 176 genes were up-regulated and 34 genes were down-regulated in ERGIC3i group compared with the control group. Analysis of the pathways and biological processes that enrich the function of differentially expressed genes showed thatthese differentially expressed genes were mainly involved in vesicular transport, growth factors, PI3K-Akt, NOD-like, Jak-STAT, NF-kappa B and other protein kinase-coupled receptors mediated signal transduction pathways, tumor immune response, collagen-integrin receptor-actin axis, and miRNA pathways. More importantly, most of the significantly altered pathways were related to immunity. ERGIC3 may be a key immune-related gene. Conclusion: Based on the transcriptomic analysis, the mechanism of ERGIC3 promoting the growth of HCC is link with the transport of growth factor receptor, cytokine receptor and collagen. Then it is involved in signal transduction pathways mediated by protein kinase-coupled receptors, PI3K-Akt, NOD-like, Jak-STAT and NF-kappa B. In particular, the mechanism is also involved in the ERGIC3-dependent immune pathways. ERGIC3 is a potential target for prevention and treatment of HCC.

Categorizing objects from MEG signals using EEGNet.

Magnetoencephalography (MEG) signals have demonstrated their practical application to reading human minds. Current neural decoding studies have made great progress to build subject-wise decoding models to extract and discriminate the temporal/spatial features in neural signals. In this paper, we used a compact convolutional neural network-EEGNet-to build a common decoder across subjects, which deciphered the categories of objects (faces, tools, animals, and scenes) from MEG data. This study investigated the influence of the spatiotemporal structure of MEG on EEGNet's classification performance. Furthermore, the EEGNet replaced its convolution layers with two sets of parallel convolution structures to extract the spatial and temporal features simultaneously. Our results showed that the organization of MEG data fed into the EEGNet has an effect on EEGNet classification accuracy, and the parallel convolution structures in EEGNet are beneficial to extracting and fusing spatial and temporal MEG features. The classification accuracy demonstrated that the EEGNet succeeds in building the common decoder model across subjects, and outperforms several state-of-the-art feature fusing methods.

Cryo-EM structure of the inner ring from the Xenopus laevis nuclear pore complex.

Nuclear pore complex (NPC) mediates nucleocytoplasmic shuttling. Here we present single-particle cryo-electron microscopy structure of the inner ring (IR) subunit from the Xenopus laevis NPC at an average resolution of 4.2 Å. A homo-dimer of Nup205 resides at the center of the IR subunit, flanked by two molecules of Nup188. Four molecules of Nup93 each places an extended helix into the axial groove of Nup205 or Nup188, together constituting the central scaffold. The channel nucleoporin hetero-trimer of Nup62/58/54 is anchored on the central scaffold. Six Nup155 molecules interact with the central scaffold and together with the NDC1-ALADIN hetero-dimers anchor the IR subunit to the nuclear envelope and to outer rings. The scarce inter-subunit contacts may allow sufficient latitude in conformation and diameter of the IR. Our structure reveals the molecular basis for the IR subunit assembly of a vertebrate NPC.

Cryo-EM structure of the nuclear ring from Xenopus laevis nuclear pore complex.

Nuclear pore complex (NPC) shuttles cargo across the nuclear envelope. Here we present single-particle cryo-EM structure of the nuclear ring (NR) subunit from Xenopus laevis NPC at an average resolution of 5.6 Å. The NR subunit comprises two 10-membered Y complexes, each with the nucleoporin ELYS closely associating with Nup160 and Nup37 of the long arm. Unlike the cytoplasmic ring (CR) or inner ring (IR), the NR subunit contains only one molecule each of Nup205 and Nup93. Nup205 binds both arms of the Y complexes and interacts with the stem of inner Y complex from the neighboring subunit. Nup93 connects the stems of inner and outer Y complexes within the same NR subunit, and places its N-terminal extended helix into the axial groove of Nup205 from the neighboring subunit. Together with other structural information, we have generated a composite atomic model of the central ring scaffold that includes the NR, IR, and CR. The IR is connected to the two outer rings mainly through Nup155. This model facilitates functional understanding of vertebrate NPC.

Halftone spatial frequency domain imaging enables kilohertz high-speed label-free non-contact quantitative mapping of optical properties for strongly turbid media.

The ability to quantify optical properties (i.e., absorption and scattering) of strongly turbid media has major implications on the characterization of biological tissues, fluid fields, and many others. However, there are few methods that can provide wide-field quantification of optical properties, and none is able to perform quantitative optical property imaging with high-speed (e.g., kilohertz) capabilities. Here we develop a new imaging modality termed halftone spatial frequency domain imaging (halftone-SFDI), which is approximately two orders of magnitude faster than the state-of-the-art, and provides kilohertz high-speed, label-free, non-contact, wide-field quantification for the optical properties of strongly turbid media. This method utilizes halftone binary patterned illumination to target the spatial frequency response of turbid media, which is then mapped to optical properties using model-based analysis. We validate the halftone-SFDI on an array of phantoms with a wide range of optical properties as well as in vivo human tissue. We demonstrate with an in vivo rat brain cortex imaging study, and show that halftone-SFDI can longitudinally monitor the absolute concentration as well as spatial distribution of functional chromophores in tissue. We also show that halftone-SFDI can spatially map dual-wavelength optical properties of a highly dynamic flow field at kilohertz speed. Together, these results highlight the potential of halftone-SFDI to enable new capabilities in fundamental research and translational studies including brain science and fluid dynamics.

Specific electromagnetic radiation in the wireless signal range increases wakefulness in mice.

Electromagnetic radiation (EMR) in the environment has increased sharply in recent decades. The effect of environmental EMR on living organisms remains poorly characterized. Here, we report the impact of wireless-range EMR on the sleep architecture of mouse. Prolonged exposure to 2.4-GHz EMR modulated by 100-Hz square pulses at a nonthermal output level results in markedly increased time of wakefulness in mice. These mice display corresponding decreased time of nonrapid eye movement (NREM) and rapid eye movement (REM). In contrast, prolonged exposure to unmodulated 2.4-GHz EMR at the same time-averaged output level has little impact on mouse sleep. These observations identify alteration of sleep architecture in mice as a specific physiological response to prolonged wireless-range EMR exposure.

Anti-scattering light focusing by fast wavefront shaping based on multi-pixel encoded digital-micromirror device.

Speed and enhancement are the two most important metrics for anti-scattering light focusing by wavefront shaping (WS), which requires a spatial light modulator with a large number of modulation modes and a fast speed of response. Among the commercial modulators, the digital-micromirror device (DMD) is the sole solution providing millions of modulation modes and a pattern rate higher than 20 kHz. Thus, it has the potential to accelerate the process of anti-scattering light focusing with a high enhancement. Nevertheless, modulating light in a binary mode by the DMD restricts both the speed and enhancement seriously. Here, we propose a multi-pixel encoded DMD-based WS method by combining multiple micromirrors into a single modulation unit to overcome the drawbacks of binary modulation. In addition, to efficiently optimize the wavefront, we adopted separable natural evolution strategies (SNES), which could carry out a global search against a noisy environment. Compared with the state-of-the-art DMD-based WS method, the proposed method increased the speed of optimization and enhancement of focus by a factor of 179 and 16, respectively. In our demonstration, we achieved 10 foci with homogeneous brightness at a high speed and formed W- and S-shape patterns against the scattering medium. The experimental results suggest that the proposed method will pave a new avenue for WS in the applications of biomedical imaging, photon therapy, optogenetics, dynamic holographic display, etc.

Cryo-EM structure of human Wntless in complex with Wnt3a.

Wntless (WLS), an evolutionarily conserved multi-pass transmembrane protein, is essential for secretion of Wnt proteins. Wnt-triggered signaling pathways control many crucial life events, whereas aberrant Wnt signaling is tightly associated with many human diseases including cancers. Here, we report the cryo-EM structure of human WLS in complex with Wnt3a, the most widely studied Wnt, at 2.2 Å resolution. The transmembrane domain of WLS bears a GPCR fold, with a conserved core cavity and a lateral opening. Wnt3a interacts with WLS at multiple interfaces, with the lipid moiety on Wnt3a traversing a hydrophobic tunnel of WLS transmembrane domain and inserting into membrane. A ß-hairpin of Wnt3a containing the conserved palmitoleoylation site interacts with WLS extensively, which is crucial for WLS-mediated Wnt secretion. The flexibility of the Wnt3a loop/hairpin regions involved in the multiple binding sites indicates induced fit might happen when Wnts are bound to different binding partners. Our findings provide important insights into the molecular mechanism of Wnt palmitoleoylation, secretion and signaling.

Laser curve extraction of a train wheelset based on an encoder-decoder network.

An algorithm of laser curve segmentation for a train wheelset based on an encoder- decoder network is proposed. Aiming at the rich local features and simple semantic features of the train wheelset laser curve image, a neural network with shallow depth, high resolution, and good detail performance was designed. The proposed neural network makes full use of the dense connection mechanism and the upsampling module to enhance feature reuse and feature propagation. It can extract context semantic information at multiple scales with fewer parameters. Experimental results show that the encoder-decoder network has better performance than other neural networks in laser curve extraction of train wheelset. Based on the encoder-decoder neural network, mIOU, Recall, Accuracy, and F1_score of the laser curve dataset of the train wheelset, the score index reached 86.5%, 89.2%, 99.9%, and 85.0%, which can accurately extract the laser stripe of the train wheelset. Additionally, the encoder-decoder network can diminish the influence of noise on the extraction of laser fringes of a train wheelset to a certain extent. Therefore, it has good application in railway safety.

A highly selective ratiometric fluorescent probe for doxycycline based on the sensitization effect of bovine serum albumin.

Fluorescent probes with in-situ visual feature have received numerous attentions for detecting doxycycline (DC), a semisynthetic tetracycline antibiotic widely used in animal husbandry. However, reported fluorescent probes commonly fail to selectively detect DC among tetracycline antibiotics due to their structural similarity. In this work, bovine serum albumin-capped gold nanoclusters (BSA-AuNCs) were ingeniously used as the ratiometric fluorescent probe for detecting DC over other tetracycline antibiotics through the selective sensitization effect of BSA on DC. After adding DC, the red fluorescence of BSA-AuNCs almost remained unchanged, while the green fluorescence of DC also emerged under the sensitization of BSA. BSA-AuNCs showed the highest response toward DC among tetracycline antibiotics ascribed to the strongest sensitization effect of BSA on DC. BSA-AuNCs also displayed the features of simple synthesis, short response time (1 min) and low detection limit (36 nM). BSA-AuNCs were finally applied to detecting DC in fish samples, and further fabricated into test strips for ease of carrying. Thus, this work proposes an efficient strategy to design fluorescent probe for selectively detecting DC among tetracycline antibiotics.

Gradient-assisted focusing light through scattering media.

Focusing light through a scattering medium is a longstanding challenge in biomedical optics, to which wavefront shaping is a powerful solution. The state-of-the-art feedback-based approach is the widely used genetic algorithm method. However, it can only achieve relatively low enhancement of the focus, and the genetic algorithm is known to be time-consuming. To tackle those issues, we propose a gradient-assisted strategy for wavefront shaping. The proposed method conducts optimization in the function distribution space. Specifically, when optimizing the parameters along each iteration, the consequent function distribution changes within a distance as measured by the Kullback-Leibler divergence. Taking advantage of the gradient information, the proposed method is over 60× faster to obtain the same peak-to-background ratio (PBR) level. Compared with the genetic algorithm that is able to optimize a number of 64×64 phase segments, the proposed gradient strategy is able to optimize 256×256 phase segments, and gives 20× higher focus enhancement as quantified by the PBR.

Direct mapping from diffuse reflectance to chromophore concentrations in multi-fx spatial frequency domain imaging (SFDI) with a deep residual network (DRN).

Spatial frequency domain imaging (SFDI) is an emerging technology that enables label-free, non-contact, and wide-field mapping of tissue chromophore contents, such as oxy- and deoxy-hemoglobin concentrations. It has been shown that the use of more than two spatial frequencies (multi-fx ) can vastly improve measurement accuracy and reduce chromophore estimation uncertainties, but real-time multi-fx SFDI for chromophore monitoring has been limited in practice due to the slow speed of available chromophore inversion algorithms. Existing inversion algorithms have to first convert the multi-fx diffuse reflectance to optical absorptions, and then solve a set of linear equations to estimate chromophore concentrations. In this work, we present a deep learning framework, noted as a deep residual network (DRN), that is able to directly map from diffuse reflectance to chromophore concentrations. The proposed DRN is over 10x faster than the state-of-the-art method for chromophore inversion and enables 25x improvement on the frame rate for in vivo real-time oxygenation mapping. The proposed deep learning model will help enable real-time and highly accurate chromophore monitoring with multi-fx SFDI.