Imaging data analysis using non-negative matrix factorization

Demixing fluorescence time traces transmitted by multimode fibers

Optical methods based on thin multimode fibers (MMFs) are promising tools for measuring neuronal activity in deep brain regions of freely moving mice thanks to their small diameter. However, current methods are limited: while fiber photometry provides only ensemble activity, imaging techniques using of long multimode fibers are very sensitive to bending and have not been applied to unrestrained rodents yet. Here, we demonstrate the fundamentals of a new approach using a short MMF coupled to a miniscope. In proof-of-principle in vitro experiments, we disentangled spatio-temporal fluorescence signals from multiple fluorescent sources transmitted by a thin (200 µm) and short (8 mm) MMF, using a general unconstrained non-negative matrix factorization algorithm directly on the raw video data. Furthermore, we show that low-cost open-source miniscopes have sufficient sensitivity to image the same fluorescence patterns seen in our proof-of-principle experiment, suggesting a new avenue for novel minimally invasive deep brain studies using multimode fibers in freely behaving mice.

Beyond life: Exploring hemodynamic patterns in postmortem mice brains

We utilize Laser Speckle Contrast Imaging (LSCI) for visualizing cerebral blood flow in mice during and post-cardiac arrest. Analyzing LSCI images, we noted temporal blood flow variations across the brain surface for hours postmortem. Fast Fourier Transform (FFT) analysis depicted blood flow and microcirculation decay post-death. Continuous Wavelet Transform (CWT) identified potential cerebral hemodynamic synchronization patterns. Additionally, non-negative matrix factorization (NMF) with four components segmented LSCI images, revealing structural subcomponent alterations over time. This integrated approach of LSCI, FFT, CWT, and NMF offers a comprehensive tool for studying cerebral blood flow dynamics, metaphorically capturing the 'end of the tunnel' experience. Results showed primary postmortem hemodynamic activity in the olfactory bulbs, followed by blood microflow relocations between somatosensory and visual cortical regions via the superior sagittal sinus. This method opens new avenues for exploring these phenomena, potentially linking neuroscientific insights with mysteries surrounding consciousness and perception at life's end.

Robust self-supervised denoising of voltage imaging data using CellMincer

Voltage imaging enables high-throughput investigation of neuronal activity, yet its utility is often constrained by a low signal-to-noise ratio (SNR). Conventional denoising algorithms, such as those based on matrix factorization, impose limiting assumptions about the noise process and the spatiotemporal structure of the signal. While deep learning based denoising techniques offer greater adaptability, existing approaches fail to fully exploit the fast temporal dynamics and unique short- and long-range dependencies within voltage imaging datasets. Here, we introduce CellMincer, a novel self-supervised deep learning method designed specifically for denoising voltage imaging datasets. CellMincer operates on the principle of masking and predicting sparse sets of pixels across short temporal windows and conditions the denoiser on precomputed spatiotemporal auto-correlations to effectively model long-range dependencies without the need for large temporal denoising contexts. We develop and utilize a physics-based simulation framework to generate realistic datasets for rigorous hyperparameter optimization and ablation studies, highlighting the key role of conditioning the denoiser on precomputed spatiotemporal auto-correlations to achieve 3-fold further reduction in noise. Comprehensive benchmarking on both simulated and real voltage imaging datasets, including those with paired patch-clamp electrophysiology (EP) as ground truth, demonstrates CellMincer's state-of-the-art performance. It achieves substantial noise reduction across the entire frequency spectrum, enhanced detection of subthreshold events, and superior cross-correlation with ground-truth EP recordings. Finally, we demonstrate how CellMincer's addition to a typical voltage imaging data analysis workflow improves neuronal segmentation, peak detection, and ultimately leads to significantly enhanced separation of functional phenotypes.

Two-Dimensional SERS Sensor Array for Identifying and Visualizing the Gas Spatial Distributions of Two Distinct Odor Sources

The spatial distribution of gas emitted from an odor source provides valuable information regarding the composition, size, and localization of the odor source. Surface-enhanced Raman scattering (SERS) gas sensors exhibit ultra-high sensitivity, molecular specificity, rapid response, and large-area detection. In this paper, a SERS gas sensor array was developed for visualizing the spatial distribution of gas evaporated from benzaldehyde and 4-ethylbenzaldehyde odor sources. The SERS spectra of the gas were collected by scanning the sensor array using an automatic detection system. The non-negative matrix factorization algorithm was employed to extract feature and concentration information at each spot on the sensor array. A heatmap image was generated for visualizing the gas spatial distribution using concentration information. Gaussian fitting was applied to process the image for localizing the odor source. The size of the odor source was estimated using the processed image. Moreover, the spectra of benzaldehyde, 4-ethylbenzaldehyde, and their gas mixture were simultaneously detected using one SERS sensor array. The feature information was recognized using a convolutional neural network with an accuracy of 98.21%. As a result, the benzaldehyde and 4-ethylbenzaldehyde odor sources were identified and visualized. Our research findings have various potential applications, including odor source localization, environmental monitoring, and healthcare.

Detection of valvular heart diseases combining orthogonal non-negative matrix factorization and convolutional neural networks in PCG signals

BACKGROUND AND OBJECTIVE

Valvular heart disease (VHD) is associated with elevated mortality rates. Although transthoracic echocardiography (TTE) is the gold standard detection tool, phonocardiography (PCG) could be an alternative as it is a cost-effective and noninvasive method for cardiac auscultation. Many researchers have dedicated their efforts to improving the decision-making process and developing robust and precise approaches to assist physicians in providing reliable diagnoses of VHD.

METHODS

This research proposes a novel approach for the detection of anomalous valvular heart sounds from PCG signals. The proposed approach combines orthogonal non-negative matrix factorization (ONMF) and convolutional neural network (CNN) architectures in a three-stage cascade. The aim of the proposal is to improve the learning process by identifying the optimal ONMF temporal or spectral patterns for accurate detection. In the first stage, the time-frequency representation of the input PCG signal is computed. Next, band-pass filtering is performed to locate the spectral range that is most relevant for the presence of such cardiac abnormalities. In the second stage, the temporal and spectral cardiac structures are extracted using the ONMF approach. These structures are utilized in the third stage and fed into the CNN architecture to detect abnormal heart sounds.

RESULTS

Several state-of-the-art CNN architectures, such as LeNet5, AlexNet, ResNet50, VGG16 and GoogLeNet, have been evaluated to determine the effectiveness of using ONMF temporal features for VHD detection. The results reveal that the integration of ONMF temporal features with a CNN classifier significantly improve VHD detection. Specifically, the proposed approach achieves an accuracy improvement of approximately 45% when ONMF spectral features are used and 35% when time-frequency features from the short-time Fourier transform (STFT) spectrogram are used. Additionally, feeding ONMF temporal features into low-complexity CNN architectures yields competitive results comparable to those obtained with complex architectures.

CONCLUSIONS

The temporal structure factorized by ONMF plays a critical role in distinguishing between normal heart sounds and abnormal heart sounds since the repeatability of normal heart cycles is disrupted by the presence of cardiac abnormalities. Consequently, the results highlight the importance of appropriate input data representation in the learning process of CNN models in the biomedical field of valvular heart sound detection.