Label-free metabolic clustering through unsupervised pixel classification of multiparametric fluorescent images

Brain tumor segmentation using neuro-technology enabled intelligence-cascaded U-Net model

According to experts in neurology, brain tumours pose a serious risk to human health. The clinical identification and treatment of brain tumours rely heavily on accurate segmentation. The varied sizes, forms, and locations of brain tumours make accurate automated segmentation a formidable obstacle in the field of neuroscience. U-Net, with its computational intelligence and concise design, has lately been the go-to model for fixing medical picture segmentation issues. Problems with restricted local receptive fields, lost spatial information, and inadequate contextual information are still plaguing artificial intelligence. A convolutional neural network (CNN) and a Mel-spectrogram are the basis of this cough recognition technique. First, we combine the voice in a variety of intricate settings and improve the audio data. After that, we preprocess the data to make sure its length is consistent and create a Mel-spectrogram out of it. A novel model for brain tumor segmentation (BTS), Intelligence Cascade U-Net (ICU-Net), is proposed to address these issues. It is built on dynamic convolution and uses a non-local attention mechanism. In order to reconstruct more detailed spatial information on brain tumours, the principal design is a two-stage cascade of 3DU-Net. The paper's objective is to identify the best learnable parameters that will maximize the likelihood of the data. After the network's ability to gather long-distance dependencies for AI, Expectation-Maximization is applied to the cascade network's lateral connections, enabling it to leverage contextual data more effectively. Lastly, to enhance the network's ability to capture local characteristics, dynamic convolutions with local adaptive capabilities are used in place of the cascade network's standard convolutions. We compared our results to those of other typical methods and ran extensive testing utilising the publicly available BraTS 2019/2020 datasets. The suggested method performs well on tasks involving BTS, according to the experimental data. The Dice scores for tumor core (TC), complete tumor, and enhanced tumor segmentation BraTS 2019/2020 validation sets are 0.897/0.903, 0.826/0.828, and 0.781/0.786, respectively, indicating high performance in BTS.

Applications of machine learning in time-domain fluorescence lifetime imaging: a review

Many medical imaging modalities have benefited from recent advances in Machine Learning (ML), specifically in deep learning, such as neural networks. Computers can be trained to investigate and enhance medical imaging methods without using valuable human resources. In recent years, Fluorescence Lifetime Imaging (FLIm) has received increasing attention from the ML community. FLIm goes beyond conventional spectral imaging, providing additional lifetime information, and could lead to optical histopathology supporting real-time diagnostics. However, most current studies do not use the full potential of machine/deep learning models. As a developing image modality, FLIm data are not easily obtainable, which, coupled with an absence of standardisation, is pushing back the research to develop models which could advance automated diagnosis and help promote FLIm. In this paper, we describe recent developments that improve FLIm image quality, specifically time-domain systems, and we summarise sensing, signal-to-noise analysis and the advances in registration and low-level tracking. We review the two main applications of ML for FLIm: lifetime estimation and image analysis through classification and segmentation. We suggest a course of action to improve the quality of ML studies applied to FLIm. Our final goal is to promote FLIm and attract more ML practitioners to explore the potential of lifetime imaging.

Probing organoid metabolism using fluorescence lifetime imaging microscopy (FLIM): The next frontier of drug discovery and disease understanding

Organoid models have been used to address important questions in developmental and cancer biology, tissue repair, advanced modelling of disease and therapies, among other bioengineering applications. Such 3D microenvironmental models can investigate the regulation of cell metabolism, and provide key insights into the mechanisms at the basis of cell growth, differentiation, communication, interactions with the environment and cell death. Their accessibility and complexity, based on 3D spatial and temporal heterogeneity, make organoids suitable for the application of novel, dynamic imaging microscopy methods, such as fluorescence lifetime imaging microscopy (FLIM) and related decay time-assessing readouts. Several biomarkers and assays have been proposed to study cell metabolism by FLIM in various organoid models. Herein, we present an expert-opinion discussion on the principles of FLIM and PLIM, instrumentation and data collection and analysis protocols, and general and emerging biosensor-based approaches, to highlight the pioneering work being performed in this field.

Evaluating Differentiation Status of Mesenchymal Stem Cells by Label-Free Microscopy System and Machine Learning

Mesenchymal stem cells (MSCs) play a crucial role in tissue engineering, as their differentiation status directly affects the quality of the final cultured tissue, which is critical to the success of transplantation therapy. Furthermore, the precise control of MSC differentiation is essential for stem cell therapy in clinical settings, as low-purity stem cells can lead to tumorigenic problems. Therefore, to address the heterogeneity of MSCs during their differentiation into adipogenic or osteogenic lineages, numerous label-free microscopic images were acquired using fluorescence lifetime imaging microscopy (FLIM) and stimulated Raman scattering (SRS), and an automated evaluation model for the differentiation status of MSCs was built based on the K-means machine learning algorithm. The model is capable of highly sensitive analysis of individual cell differentiation status, so it has great potential for stem cell differentiation research.

The Need for Artificial Intelligence Based Risk Factor Analysis for Age-Related Macular Degeneration: A Review

In epidemiology, a risk factor is a variable associated with increased disease risk. Understanding the role of risk factors is significant for developing a strategy to improve global health. There is strong evidence that risk factors like smoking, alcohol consumption, previous cataract surgery, age, high-density lipoprotein (HDL) cholesterol, BMI, female gender, and focal hyper-pigmentation are independently associated with age-related macular degeneration (AMD). Currently, in the literature, statistical techniques like logistic regression, multivariable logistic regression, etc., are being used to identify AMD risk factors by employing numerical/categorical data. However, artificial intelligence (AI) techniques have not been used so far in the literature for identifying risk factors for AMD. On the other hand, artificial intelligence (AI) based tools can anticipate when a person is at risk of developing chronic diseases like cancer, dementia, asthma, etc., in providing personalized care. AI-based techniques can employ numerical/categorical and/or image data thus resulting in multimodal data analysis, which provides the need for AI-based tools to be used for risk factor analysis in ophthalmology. This review summarizes the statistical techniques used to identify various risk factors and the higher benefits that AI techniques provide for AMD-related disease prediction. Additional studies are required to review different techniques for risk factor identification for other ophthalmic diseases like glaucoma, diabetic macular edema, retinopathy of prematurity, cataract, and diabetic retinopathy.

Diabetic Macular Edema: Current Understanding, Molecular Mechanisms and Therapeutic Implications

Diabetic retinopathy (DR), with increasing incidence, is the major cause of vision loss and blindness worldwide in working-age adults. Diabetic macular edema (DME) remains the main cause of vision impairment in diabetic patients, with its pathogenesis still not completely elucidated. Vascular endothelial growth factor (VEGF) plays a pivotal role in the pathogenesis of DR and DME. Currently, intravitreal injection of anti-VEGF agents remains as the first-line therapy in DME treatment due to the superior anatomic and functional outcomes. However, some patients do not respond satisfactorily to anti-VEGF injections. More than 30% patients still exist with persistent DME even after regular intravitreal injection for at least 4 injections within 24 weeks, suggesting other pathogenic factors, beyond VEGF, might contribute to the pathogenesis of DME. Recent advances showed nearly all the retinal cells are involved in DR and DME, including breakdown of blood-retinal barrier (BRB), drainage dysfunction of Müller glia and retinal pigment epithelium (RPE), involvement of inflammation, oxidative stress, and neurodegeneration, all complicating the pathogenesis of DME. The profound understanding of the changes in proteomics and metabolomics helps improve the elucidation of the pathogenesis of DR and DME and leads to the identification of novel targets, biomarkers and potential therapeutic strategies for DME treatment. The present review aimed to summarize the current understanding of DME, the involved molecular mechanisms, and the changes in proteomics and metabolomics, thus to propose the potential therapeutic recommendations for personalized treatment of DME.

Investigation of DHA-Induced Regulation of Redox Homeostasis in Retinal Pigment Epithelium Cells through the Combination of Metabolic Imaging and Molecular Biology

Diabetes-induced oxidative stress leads to the onset of vascular complications, which are major causes of disability and death in diabetic patients. Among these, diabetic retinopathy (DR) often arises from functional alterations of the blood-retinal barrier (BRB) due to damaging oxidative stress reactions in lipids, proteins, and DNA. This study aimed to investigate the impact of the ω3-polyunsaturated docosahexaenoic acid (DHA) on the regulation of redox homeostasis in the human retinal pigment epithelial (RPE) cell line (ARPE-19) under hyperglycemic-like conditions. The present results show that the treatment with DHA under high-glucose conditions activated erythroid 2-related factor Nrf2, which orchestrates the activation of cellular antioxidant pathways and ultimately inhibits apoptosis. This process was accompanied by a marked increase in the expression of NADH (Nicotinamide Adenine Dinucleotide plus Hydrogen) Quinone Oxidoreductase 1 (Nqo1), which is correlated with a contextual modulation and intracellular re-organization of the NAD+/NADH redox balance. This investigation of the mechanisms underlying the impairment induced by high levels of glucose on redox homeostasis of the BRB and the subsequent recovery provided by DHA provides both a powerful indicator for the detection of RPE cell impairment as well as a potential metabolic therapeutic target for the early intervention in its treatment.

Unsupervised Clustering of Heartbeat Dynamics Allows for Real Time and Personalized Improvement in Cardiovascular Fitness

VO₂max index has a significant impact on overall health. Its estimation through wearables notifies the user of his level of fitness but cannot provide a detailed analysis of the time intervals in which heartbeat dynamics are changed and/or fatigue is emerging. Here, we developed a multiple modality biosignal processing method to investigate running sessions to characterize in real time heartbeat dynamics in response to external energy demand. We isolated dynamic regimes whose fraction increases with the VO₂max and with the emergence of neuromuscular fatigue. This analysis can be extremely valuable by providing personalized feedback about the user’s fitness level improvement that can be realized by developing personalized exercise plans aimed to target a contextual increase in the dynamic regime fraction related to VO₂max increase, at the expense of the dynamic regime fraction related to the emergence of fatigue. These strategies can ultimately result in the reduction in cardiovascular risk.

Robustness of the Krebs Cycle under Physiological Conditions and in Cancer: New Clues for Evaluating Metabolism-Modifying Drug Therapies

The Krebs cycle in cells that contain mitochondria is necessary for both energy production and anabolic processes. In given cell/condition, the Krebs cycle is dynamic but remains at a steady state. In this article, we first aimed at comparing the properties of a closed cycle versus the same metabolism in a linear array. The main finding is that, unlike a linear metabolism, the closed cycle can reach a steady state (SS) regardless of the nature and magnitude of the disturbance. When the cycle is modeled with input and output reactions, the “open” cycle is robust and reaches a steady state but with exceptions that lead to sustained accumulation of intermediate metabolites, i.e., conditions at which no SS can be achieved. The modeling of the cycle in cancer, trying to obtain marked reductions in flux, shows that these reductions are limited and therefore the Warburg effect is moderate at most. In general, our results of modeling the cycle in different conditions and looking for the achievement, or not, of SS, suggest that the cycle may have a regulation, not yet discovered, to go from an open cycle to a closed one. Said regulation could allow for reaching the steady state, thus avoiding the unwanted effects derived from the aberrant accumulation of metabolites in the mitochondria. The information in this paper might be useful to evaluate metabolism-modifying medicines.

The Active Segmentation Platform for Microscopic Image Classification and Segmentation

Image segmentation still represents an active area of research since no universal solution can be identified. Traditional image segmentation algorithms are problem-specific and limited in scope. On the other hand, machine learning offers an alternative paradigm where predefined features are combined into different classifiers, providing pixel-level classification and segmentation. However, machine learning only can not address the question as to which features are appropriate for a certain classification problem. The article presents an automated image segmentation and classification platform, called Active Segmentation, which is based on ImageJ. The platform integrates expert domain knowledge, providing partial ground truth, with geometrical feature extraction based on multi-scale signal processing combined with machine learning. The approach in image segmentation is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application we demonstrate whole image classification functionality based on the same principles. The approach is exemplified using the HeLa and HEp-2 data sets. Obtained results indicate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches. In summary, differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical invariant objects.

Genetically encoded biosensors for evaluating NAD+/NADH ratio in cytosolic and mitochondrial compartments

The ratio of oxidized to reduced NAD (NAD+/NADH) sets intracellular redox balance and antioxidant capacity. Intracellular NAD is compartmentalized and the mitochondrial NAD+/NADH ratio is intricately linked to cellular function. Here, we report the monitoring of the NAD+/NADH ratio in mitochondrial and cytosolic compartments in live cells by using a modified genetic biosensor (SoNar). The fluorescence signal of SoNar targeted to mitochondria (mt-SoNar) or cytosol (ct-SoNar) responded linearly to physiological NAD+/NADH ratios in situ. NAD+/NADH ratios in cytosol versus mitochondria responded rapidly, but differently, to acute metabolic perturbations, indicating distinct NAD pools. Subcellular NAD redox balance regained homeostasis via communications through malate-aspartate shuttle. Mitochondrial and cytosolic NAD+/NADH ratios are influenced by NAD+ precursor levels and are distinctly regulated under pathophysiological conditions. Compartment-targeted biosensors and real-time imaging allow assessment of subcellular NAD+/NADH redox signaling in live cells, enabling future mechanistic research of NAD redox in cell biology and disease development.

Recent innovations in fluorescence lifetime imaging microscopy for biology and medicine

SIGNIFICANCE

Fluorescence lifetime imaging microscopy (FLIM) measures the decay rate of fluorophores, thus providing insights into molecular interactions. FLIM is a powerful molecular imaging technique that is widely used in biology and medicine.

AIM

This perspective highlights some of the major advances in FLIM instrumentation, analysis, and biological and clinical applications that we have found impactful over the last year.

APPROACH

Innovations in FLIM instrumentation resulted in faster acquisition speeds, rapid imaging over large fields of view, and integration with complementary modalities such as single-molecule microscopy or light-sheet microscopy. There were significant developments in FLIM analysis with machine learning approaches to enhance processing speeds, fit-free techniques to analyze images without a priori knowledge, and open-source analysis resources. The advantages and limitations of these recent instrumentation and analysis techniques are summarized. Finally, applications of FLIM in the last year include label-free imaging in biology, ophthalmology, and intraoperative imaging, FLIM of new fluorescent probes, and lifetime-based Förster resonance energy transfer measurements.

CONCLUSIONS

A large number of high-quality publications over the last year signifies the growing interest in FLIM and ensures continued technological improvements and expanding applications in biomedical research.