Fluorescence microscopy datasets for training deep neural networks.
Ontology highlight
ABSTRACT: Background
Fluorescence microscopy is an important technique in many areas of biological research. Two factors that limit the usefulness and performance of fluorescence microscopy are photobleaching of fluorescent probes during imaging and, when imaging live cells, phototoxicity caused by light exposure. Recently developed methods in machine learning are able to greatly improve the signal-to-noise ratio of acquired images. This allows researchers to record images with much shorter exposure times, which in turn minimizes photobleaching and phototoxicity by reducing the dose of light reaching the sample.Findings
To use deep learning methods, a large amount of data is needed to train the underlying convolutional neural network. One way to do this involves use of pairs of fluorescence microscopy images acquired with long and short exposure times. We provide high-quality datasets that can be used to train and evaluate deep learning methods under development.Conclusion
The availability of high-quality data is vital for training convolutional neural networks that are used in current machine learning approaches.
SUBMITTER: Hagen GM
PROVIDER: S-EPMC8099770 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Neural networks enjoy widespread success in both research and industry and, with the advent of quantum technology, it is a crucial challenge to design quantum neural networks for fully quantum learning tasks. Here we propose a truly quantum analogue of classical neurons, which form quantum feedforward neural networks capable of universal quantum computation. We describe the efficient training of these networks using the fidelity as a cost function, providing both classical and efficient quantum implementations. Our method allows for fast optimisation with reduced memory requirements: the number of qudits required scales with only the width, allowing deep-network optimisation. We benchmark our proposal for the quantum task of learning an unknown unitary and find remarkable generalisation behaviour and a striking robustness to noisy training data.
| S-EPMC7010779 | biostudies-literature
Project description:Deep Convolutional Neural Networks (DCNN) have recently emerged as superior for many image segmentation tasks. The DCNN performance is however heavily dependent on the availability of large amounts of problem-specific training samples. Here we show that DCNNs trained on ground truth created automatically using fluorescently labeled cells, perform similar to manual annotations.
| S-EPMC5552800 | biostudies-other
Project description:Fluorescence lifetime imaging microscopy (FLIM) is a powerful technique to probe the molecular environment of fluorophores. The analysis of FLIM images is usually performed with time consuming fitting methods. For accelerating this analysis, sophisticated deep learning architectures based on convolutional neural networks have been developed for restrained lifetime ranges but they require long training time. In this work, we present a simple neural network formed only with fully connected layers able to analyze fluorescence lifetime images. It is based on the reduction of high dimensional fluorescence intensity temporal decays into four parameters which are the phasor coordinates, the mean and amplitude-weighted lifetimes. This network called Phasor-Net has been applied for a time domain FLIM system excited with an 80 MHz laser repetition frequency, with negligible jitter and afterpulsing. Due to the restricted time interval of 12.5 ns, the training range of the lifetimes was limited between 0.2 and 3.0 ns; and the total photon number was lower than 106, as encountered in live cell imaging. From simulated biexponential decays, we demonstrate that Phasor-Net is more precise and less biased than standard fitting methods. We demonstrate also that this simple architecture gives almost comparable performance than those obtained from more sophisticated networks but with a faster training process (15 min instead of 30 min). We finally apply successfully our method to determine biexponential decays parameters for FLIM experiments in living cells expressing EGFP linked to mCherry and fused to a plasma membrane protein.
| S-EPMC8668934 | biostudies-literature
Project description:Three-dimensional microscopy is increasingly prevalent in biology due to the development of techniques such as multiphoton, spinning disk confocal, and light sheet fluorescence microscopies. These methods enable unprecedented studies of life at the microscale, but bring with them larger and more complex datasets. New image processing techniques are therefore called for to analyze the resulting images in an accurate and efficient manner. Convolutional neural networks are becoming the standard for classification of objects within images due to their accuracy and generalizability compared to traditional techniques. Their application to data derived from 3D imaging, however, is relatively new and has mostly been in areas of magnetic resonance imaging and computer tomography. It remains unclear, for images of discrete cells in variable backgrounds as are commonly encountered in fluorescence microscopy, whether convolutional neural networks provide sufficient performance to warrant their adoption, especially given the challenges of human comprehension of their classification criteria and their requirements of large training datasets. We therefore applied a 3D convolutional neural network to distinguish bacteria and non-bacterial objects in 3D light sheet fluorescence microscopy images of larval zebrafish intestines. We find that the neural network is as accurate as human experts, outperforms random forest and support vector machine classifiers, and generalizes well to a different bacterial species through the use of transfer learning. We also discuss network design considerations, and describe the dependence of accuracy on dataset size and data augmentation. We provide source code, labeled data, and descriptions of our analysis pipeline to facilitate adoption of convolutional neural network analysis for three-dimensional microscopy data.
| S-EPMC6292638 | biostudies-literature
Project description:Deep-UV (DUV) excitation fluorescence microscopy has potential to provide rapid diagnosis with simple technique comparing to conventional histopathology based on hematoxylin and eosin (H&E) staining. We established a fluorescent staining protocol for DUV excitation fluorescence imaging that has enabled clear discrimination of nucleoplasm, nucleolus, and cytoplasm. Fluorescence images of metastasis-positive/-negative lymph nodes of gastric cancer patients were used for patch-based training with a deep neural network (DNN) based on Inception-v3 architecture. The performance on small patches of the fluorescence images was comparable with that of H&E images. Gradient-weighted class activation mapping analysis revealed the areas where the trained model identified metastatic lesions in the images containing cancer cells. We extended the method to large-size image analysis enabling accurate detection of metastatic lesions. We discuss usefulness of DUV excitation fluorescence imaging with the aid of DNN analysis, which is promising for assisting pathologists in assessment of lymph node metastasis.
| S-EPMC6858352 | biostudies-literature
Project description:Immunofluorescence microscopy is routinely used to visualise the spatial distribution of proteins that dictates their cellular function. However, unspecific antibody binding often results in high cytosolic background signals, decreasing the image contrast of a target structure. Recently, convolutional neural networks (CNNs) were successfully employed for image restoration in immunofluorescence microscopy, but current methods cannot correct for those background signals. We report a new method that trains a CNN to reduce unspecific signals in immunofluorescence images; we name this method label2label (L2L). In L2L, a CNN is trained with image pairs of two non-identical labels that target the same cellular structure. We show that after L2L training a network predicts images with significantly increased contrast of a target structure, which is further improved after implementing a multiscale structural similarity loss function. Here, our results suggest that sample differences in the training data decrease hallucination effects that are observed with other methods. We further assess the performance of a cycle generative adversarial network, and show that a CNN can be trained to separate structures in superposed immunofluorescence images of two targets.
| S-EPMC8918818 | biostudies-literature
Project description:Conventional analysis of fluorescence recovery after photobleaching (FRAP) data for diffusion coefficient estimation typically involves fitting an analytical or numerical FRAP model to the recovery curve data using non-linear least squares. Depending on the model, this can be time consuming, especially for batch analysis of large numbers of data sets and if multiple initial guesses for the parameter vector are used to ensure convergence. In this work, we develop a completely new approach, DeepFRAP, utilizing machine learning for parameter estimation in FRAP. From a numerical FRAP model developed in previous work, we generate a very large set of simulated recovery curve data with realistic noise levels. The data are used for training different deep neural network regression models for prediction of several parameters, most importantly the diffusion coefficient. The neural networks are extremely fast and can estimate the parameters orders of magnitude faster than least squares. The performance of the neural network estimation framework is compared to conventional least squares estimation on simulated data, and found to be strikingly similar. Also, a simple experimental validation is performed, demonstrating excellent agreement between the two methods. We make the data and code used publicly available to facilitate further development of machine learning-based estimation in FRAP. LAY DESCRIPTION: Fluorescence recovery after photobleaching (FRAP) is one of the most frequently used methods for microscopy-based diffusion measurements and broadly used in materials science, pharmaceutics, food science and cell biology. In a FRAP experiment, a laser is used to photobleach fluorescent particles in a region. By analysing the recovery of the fluorescence intensity due to the diffusion of still fluorescent particles, the diffusion coefficient and other parameters can be estimated. Typically, a confocal laser scanning microscope (CLSM) is used to image the time evolution of the recovery, and a model is fit using least squares to obtain parameter estimates. In this work, we introduce a new, fast and accurate method for analysis of data from FRAP. The new method is based on using artificial neural networks to predict parameter values, such as the diffusion coefficient, effectively circumventing classical least squares fitting. This leads to a dramatic speed-up, especially noticeable when analysing large numbers of FRAP data sets, while still producing results in excellent agreement with least squares. Further, the neural network estimates can be used as very good initial guesses for least squares estimation in order to make the least squares optimization convergence much faster than it otherwise would. This provides for obtaining, for example, diffusion coefficients as soon as possible, spending minimal time on data analysis. In this fashion, the proposed method facilitates efficient use of the experimentalist's time which is the main motivation to our approach. The concept is demonstrated on pure diffusion. However, the concept can easily be extended to the diffusion and binding case. The concept is likely to be useful in all application areas of FRAP, including diffusion in cells, gels and solutions.
| S-EPMC8248438 | biostudies-literature
Project description:PurposeSurgery is the predominant treatment modality of human glioma but suffers difficulty on clearly identifying tumor boundaries in clinic. Conventional practice involves neurosurgeon's visual evaluation and intraoperative histological examination of dissected tissues using frozen section, which is time-consuming and complex. The aim of this study was to develop fluorescent imaging coupled with artificial intelligence technique to quickly and accurately determine glioma in real-time during surgery.MethodsGlioma patients (N = 23) were enrolled and injected with indocyanine green for fluorescence image-guided surgery. Tissue samples (N = 1874) were harvested from surgery of these patients, and the second near-infrared window (NIR-II, 1000-1700 nm) fluorescence images were obtained. Deep convolutional neural networks (CNNs) combined with NIR-II fluorescence imaging (named as FL-CNN) were explored to automatically provide pathological diagnosis of glioma in situ in real-time during patient surgery. The pathological examination results were used as the gold standard.ResultsThe developed FL-CNN achieved the area under the curve (AUC) of 0.945. Comparing to neurosurgeons' judgment, with the same level of specificity >80%, FL-CNN achieved a much higher sensitivity (93.8% versus 82.0%, P < 0.001) with zero time overhead. Further experiments demonstrated that FL-CNN corrected >70% of the errors made by neurosurgeons. FL-CNN was also able to rapidly predict grade and Ki-67 level (AUC 0.810 and 0.625) of tumor specimens intraoperatively.ConclusionOur study demonstrates that deep CNNs are better at capturing important information from fluorescence images than surgeons' evaluation during patient surgery. FL-CNN is highly promising to provide pathological diagnosis intraoperatively and assist neurosurgeons to obtain maximum resection safely.Trial registrationChiCTR ChiCTR2000029402. Registered 29 January 2020, retrospectively registered.
| S-EPMC8440289 | biostudies-literature
Project description:Spiking Neural Networks (SNNs) have recently emerged as an alternative to deep learning owing to sparse, asynchronous and binary event (or spike) driven processing, that can yield huge energy efficiency benefits on neuromorphic hardware. However, SNNs convey temporally-varying spike activation through time that is likely to induce a large variation of forward activation and backward gradients, resulting in unstable training. To address this training issue in SNNs, we revisit Batch Normalization (BN) and propose a temporal Batch Normalization Through Time (BNTT) technique. Different from previous BN techniques with SNNs, we find that varying the BN parameters at every time-step allows the model to learn the time-varying input distribution better. Specifically, our proposed BNTT decouples the parameters in a BNTT layer along the time axis to capture the temporal dynamics of spikes. We demonstrate BNTT on CIFAR-10, CIFAR-100, Tiny-ImageNet, event-driven DVS-CIFAR10 datasets, and Sequential MNIST and show near state-of-the-art performance. We conduct comprehensive analysis on the temporal characteristic of BNTT and showcase interesting benefits toward robustness against random and adversarial noise. Further, by monitoring the learnt parameters of BNTT, we find that we can do temporal early exit. That is, we can reduce the inference latency by ~5 - 20 time-steps from the original training latency. The code has been released at https://github.com/Intelligent-Computing-Lab-Yale/BNTT-Batch-Normalization-Through-Time.
| S-EPMC8695433 | biostudies-literature
Project description:Fluorescence lifetime imaging (FLIM) is widely applied to obtain quantitative information from fluorescence signals, particularly using Förster Resonant Energy Transfer (FRET) measurements to map, for example, protein-protein interactions. Extracting FRET efficiencies or population fractions typically entails fitting data to complex fluorescence decay models but such experiments are frequently photon constrained, particularly for live cell or in vivo imaging, and this leads to unacceptable errors when analysing data on a pixel-wise basis. Lifetimes and population fractions may, however, be more robustly extracted using global analysis to simultaneously fit the fluorescence decay data of all pixels in an image or dataset to a multi-exponential model under the assumption that the lifetime components are invariant across the image (dataset). This approach is often considered to be prohibitively slow and/or computationally expensive but we present here a computationally efficient global analysis algorithm for the analysis of time-correlated single photon counting (TCSPC) or time-gated FLIM data based on variable projection. It makes efficient use of both computer processor and memory resources, requiring less than a minute to analyse time series and multiwell plate datasets with hundreds of FLIM images on standard personal computers. This lifetime analysis takes account of repetitive excitation, including fluorescence photons excited by earlier pulses contributing to the fit, and is able to accommodate time-varying backgrounds and instrument response functions. We demonstrate that this global approach allows us to readily fit time-resolved fluorescence data to complex models including a four-exponential model of a FRET system, for which the FRET efficiencies of the two species of a bi-exponential donor are linked, and polarisation-resolved lifetime data, where a fluorescence intensity and bi-exponential anisotropy decay model is applied to the analysis of live cell homo-FRET data. A software package implementing this algorithm, FLIMfit, is available under an open source licence through the Open Microscopy Environment.
| S-EPMC3734241 | biostudies-literature