analyzing-mitochondrial-morphology-through-simulation-supervised

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

The quantitative analysis of subcellular organelles such as mitochondria in cell fluorescence microscopy images is a demanding task because of the ...

UiT The Arctic University of Norway

This paper presents eigen-analysis of image stack of blinking fluorophores to identify the components that enable super-resolved imaging of blinking fluorophores. Eigen-analysis reveals that the contributions of spatial distribution of fluorophores and their temporal photon emission characteristics can be completely separated. While cross-emitter cross-pixel information of spatial distribution that permits super-resolution is encoded in two matrices, temporal statistics weigh the contribution of these matrices to the measured data. The properties and conditions of exploitation of these matrices are investigated. Con-temporary super-resolution imaging methods that use blinking for super-resolution are studied in the context of the presented analysis. Besides providing insight into the capabilities and limitations of existing super-resolution methods, the analysis shall help in designing better super-resolution techniques that directly exploit these matrices.

Eigen-analysis reveals components supporting super-resolution imaging of blinking fluorophores.

Localization microscopy and multiple signal classification algorithm use temporal stack of image frames of sparse emissions from fluorophores to provide super-resolution images. Localization microscopy localizes emissions in each image independently and later collates the localizations in all the frames, giving same weight to each frame irrespective of its signal-to-noise ratio. This results in a bias towards frames with low signal-to-noise ratio and causes cluttered background in the super-resolved image. User-defined heuristic computational filters are employed to remove a set of localizations in an attempt to overcome this bias. Multiple signal classification performs eigen-decomposition of the entire stack, irrespective of the relative signal-to-noise ratios of the frames, and uses a threshold to classify eigenimages into signal and null subspaces. This results in under-representation of frames with low signal-to-noise ratio in the signal space and over-representation in the null space. Thus, multiple signal classification algorithms is biased against frames with low signal-to-noise ratio resulting into suppression of the corresponding fluorophores. This paper presents techniques to automatically debias localization microscopy and multiple signal classification algorithm of these biases without compromising their resolution and without employing heuristics, user-defined criteria. The effect of debiasing is demonstrated through five datasets of invitro and fixed cell samples.

Non-heuristic automatic techniques for overcoming low signal-to-noise-ratio bias of localization microscopy and multiple signal classification algorithm.

Ultrasound based structural health monitoring of piezoelectric material is challenging if a damage changes at a microscale over time. Classifying geometrically similar damages with a difference in diameter as small as 100 μ m is difficult using conventional sensing and signal analysis approaches. Here, we use an unconventional ultrasound sensing approach that collects information of the entire bulk of the material and investigate the applicability of machine learning approaches for classifying such similar defects. Our results show that appropriate feature design combined with simple k-nearest neighbor classifier can provide up to 98% classification accuracy even though conventional features for time-series data and a variety of classifiers cannot achieve close to 70% accuracy. The newly proposed hybrid feature, which combines frequency domain information in the form of power spectral density and time domain information in the form of sign of slope change, is a suitable feature for achieving the best classification accuracy on this challenging problem.

Classification of Micro-Damage in Piezoelectric Ceramics Using Machine Learning of Ultrasound Signals.

Sperm cell motility and morphology observed under the bright field microscopy are the only criteria for selecting a particular sperm cell during Intracytoplasmic Sperm Injection (ICSI) procedure of Assisted Reproductive Technology (ART). Several factors such as oxidative stress, cryopreservation, heat, smoking and alcohol consumption, are negatively associated with the quality of sperm cell and fertilization potential due to the changing of subcellular structures and functions which are overlooked. However, bright field imaging contrast is insufficient to distinguish tiniest morphological cell features that might influence the fertilizing ability of sperm cell. We developed a partially spatially coherent digital holographic microscope (PSC-DHM) for quantitative phase imaging (QPI) in order to distinguish normal sperm cells from sperm cells under different stress conditions such as cryopreservation, exposure to hydrogen peroxide and ethanol. Phase maps of total 10,163 sperm cells (2,400 control cells, 2,750 spermatozoa after cryopreservation, 2,515 and 2,498 cells under hydrogen peroxide and ethanol respectively) are reconstructed using the data acquired from the PSC-DHM system. Total of seven feedforward deep neural networks (DNN) are employed for the classification of the phase maps for normal and stress affected sperm cells. When validated against the test dataset, the DNN provided an average sensitivity, specificity and accuracy of 85.5%, 94.7% and 85.6%, respectively. The current QPI + DNN framework is applicable for further improving ICSI procedure and the diagnostic efficiency for the classification of semen quality in regard to their fertilization potential and other biomedical applications in general.

High spatially sensitive quantitative phase imaging assisted with deep neural network for classification of human spermatozoa under stressed condition.

Optical coherence tomography (OCT) is being increasingly adopted as a label-free and non-invasive technique for biomedical applications such as cancer and ocular disease diagnosis. Diagnostic information for these tissues is manifest in textural and geometric features of the OCT images, which are used by human expertise to interpret and triage. However, it suffers delays due to the long process of the conventional diagnostic procedure and shortage of human expertise. Here, a custom deep learning architecture, LightOCT, is proposed for the classification of OCT images into diagnostically relevant classes. LightOCT is a convolutional neural network with only two convolutional layers and a fully connected layer, but it is shown to provide excellent training and test results for diverse OCT image datasets. We show that LightOCT provides 98.9% accuracy in classifying 44 normal and 44 malignant (invasive ductal carcinoma) breast tissue volumetric OCT images. Also, >96% accuracy in classifying public datasets of ocular OCT images as normal, age-related macular degeneration and diabetic macular edema. Additionally, we show ∼96% test accuracy for classifying retinal images as belonging to choroidal neovascularization, diabetic macular edema, drusen, and normal samples on a large public dataset of more than 100,000 images. The performance of the architecture is compared with transfer learning based deep neural networks. Through this, we show that LightOCT can provide significant diagnostic support for a variety of OCT images with sufficient training and minimal hyper-parameter tuning. The trained LightOCT networks for the three-classification problem will be released online to support transfer learning on other datasets.

Deep learning architecture "LightOCT" for diagnostic decision support using optical coherence tomography images of biological samples.

Image denoising or artefact removal using deep learning is possible in the availability of supervised training dataset acquired in real experiments or synthesized using known noise models. Neither of the conditions can be fulfilled for nanoscopy (super-resolution optical microscopy) images that are generated from microscopy videos through statistical analysis techniques. Due to several physical constraints, a supervised dataset cannot be measured. Further, the non-linear spatio-temporal mixing of data and valuable statistics of fluctuations from fluorescent molecules that compete with noise statistics. Therefore, noise or artefact models in nanoscopy images cannot be explicitly learned. Here, we propose a robust and versatile simulation-supervised training approach of deep learning auto-encoder architectures for the highly challenging nanoscopy images of sub-cellular structures inside biological samples. We show the proof of concept for one nanoscopy method and investigate the scope of generalizability across structures, and nanoscopy algorithms not included during simulation-supervised training. We also investigate a variety of loss functions and learning models and discuss the limitation of existing performance metrics for nanoscopy images. We generate valuable insights for this highly challenging and unsolved problem in nanoscopy, and set the foundation for the application of deep learning problems in nanoscopy for life sciences.

Artefact removal in ground truth deficient fluctuations-based nanoscopy images using deep learning.

Mitochondria play a crucial role in cellular metabolism. This paper presents a novel method to visualize mitochondria in living cells without the use of fluorescent markers. We propose a physics-guided deep learning approach for obtaining virtually labeled micrographs of mitochondria from bright-field images. We integrate a microscope's point spread function in the learning of an adversarial neural network for improving virtual labeling. We show results (average Pearson correlation 0.86) significantly better than what was achieved by state-of-the-art (0.71) for virtual labeling of mitochondria. We also provide new insights into the virtual labeling problem and suggest additional metrics for quality assessment. The results show that our virtual labeling approach is a powerful way of segmenting and tracking individual mitochondria in bright-field images, results previously achievable only for fluorescently labeled mitochondria.

Article	Year
Eigen-analysis reveals components supporting super-resolution imaging of blinking fluorophores. Scientific reports\| PubMed ID: 28667336	2017
Non-heuristic automatic techniques for overcoming low signal-to-noise-ratio bias of localization microscopy and multiple signal classification algorithm. Scientific reports\| PubMed ID: 29563529	2018
Classification of Micro-Damage in Piezoelectric Ceramics Using Machine Learning of Ultrasound Signals. Sensors (Basel, Switzerland)\| PubMed ID: 31569337	2019
High spatially sensitive quantitative phase imaging assisted with deep neural network for classification of human spermatozoa under stressed condition. Scientific reports\| PubMed ID: 32753627	2020
Deep learning architecture "LightOCT" for diagnostic decision support using optical coherence tomography images of biological samples. Biomedical optics express\| PubMed ID: 33014597	2020
Artefact removal in ground truth deficient fluctuations-based nanoscopy images using deep learning. Biomedical optics express\| PubMed ID: 33659075	2021
Virtual labeling of mitochondria in living cells using correlative imaging and physics-guided deep learning. Biomedical optics express\| PubMed ID: 36425635	2022

Dilip K. Prasad

Biography

JoVE Journal Publications

Other Publications