Machine intelligence-driven classification of cancer patients-derived extracellular vesicles using fluorescence correlation spectroscopy: results from a pilot study

Uthamacumaran, Abicumaran; Abdouh, Mohamed; Sengupta, Kinshuk; Gao, Zu–Hua; Forte, Stefano; Tsering, Thupten; Burnier, Julia V.; Arena, Goffredo

doi:10.1007/s00521-022-08113-4

Cited by 7 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further studies are needed to understand the variation of exosome content in different TMEs and how they could be a tool for the delivery of therapeutic molecules [137,148,149]. However, a recent pilot study demonstrated that artificial intelligence algorithms coupled with time-resolved fluorescence correlation spectroscopy power spectra can precisely distinguish complex patient-derived EVs from different cancer samples of distinct tissue subtypes [150].…”

Section: Targeting Energy Metabolism and The Microenvironment In Canc...mentioning

confidence: 99%

Cellular Adaptation Takes Advantage of Atavistic Regression Programs during Carcinogenesis

Gnocchi,

Nikolic,

Paparella

et al. 2023

Cancers

View full text Add to dashboard Cite

Adaptation of cancer cells to extreme microenvironmental conditions (i.e., hypoxia, high acidity, and reduced nutrient availability) contributes to cancer resilience. Furthermore, neoplastic transformation can be envisioned as an extreme adaptive response to tissue damage or chronic injury. The recent Systemic–Evolutionary Theory of the Origin of Cancer (SETOC) hypothesizes that cancer cells “revert” to “primitive” characteristics either ontogenically (embryo-like) or phylogenetically (single-celled organisms). This regression may confer robustness and maintain the disordered state of the tissue, which is a hallmark of malignancy. Changes in cancer cell metabolism during adaptation may also be the consequence of altered microenvironmental conditions, often resulting in a shift toward lactic acid fermentation. However, the mechanisms underlying the robust adaptive capacity of cancer cells remain largely unknown. In recent years, cancer cells’ metabolic flexibility has received increasing attention among researchers. Here, we focus on how changes in the microenvironment can affect cancer cell energy production and drug sensitivity. Indeed, changes in the cellular microenvironment may lead to a “shift” toward “atavistic” biologic features, such as the switch from oxidative phosphorylation (OXPHOS) to lactic acid fermentation, which can also sustain drug resistance. Finally, we point out new integrative metabolism-based pharmacological approaches and potential biomarkers for early detection.

show abstract

Section: Targeting Energy Metabolism and The Microenvironment In Canc...mentioning

confidence: 99%

Cellular Adaptation Takes Advantage of Atavistic Regression Programs during Carcinogenesis

Gnocchi,

Nikolic,

Paparella

et al. 2023

Cancers

View full text Add to dashboard Cite

show abstract

“…In biology specifically, deep learning has been used to augment currently available solutions in a diverse range of applications, including medical image segmentation ( 16 ), drug discovery ( 17 ), super-resolution microscopy ( 18 ), single-particle tracking ( 19 ), and protein structure prediction ( 20 ). Deep feed-forward networks coupled with wavelet spectral analysis for noise detection were used in FCS two-color experiments ( 21 ), and machine learning methods, including CNNs, were applied to analyze FCS parameters for binary classification of cancer patients in oncology research ( 22 ). A recent review ( 23 ) points toward the use of CNNs in addressing the challenges of FCS analysis.…”

Section: Introductionmentioning

confidence: 99%

Deep learning reduces data requirements and allows real-time measurements in imaging FCS

Tang,

Sim,

Aik

et al. 2024

Biophysical Journal

View full text Add to dashboard Cite

“…One of the ways of solving this classification problem in FCS is using Bayesian approaches 73 – 77 . The utility of other machine learning classifiers including multilayer perceptron, random forests, and support vector machines in FCS are under investigation 78 . In the next section, we describe how deep learning widely used in fluorescence microscopic image processing 79 – 81 is utilized for various applications in FCS.…”

Section: Introductionmentioning

confidence: 99%

“…Although publications are sparse, the most common deep learning network architecture used in FCS are Convolutional Neural Networks (CNNs) 78 , 82 – 89 . CNNs are powerful analysis tools applied to image and time-series analysis (Fig.…”

Section: Introductionmentioning

confidence: 99%

Current capabilities and future perspectives of FCS: super-resolution microscopy, machine learning, and in vivo applications

Sankaran

Wohland

2023

Commun Biol

View full text Add to dashboard Cite

Fluorescence correlation spectroscopy (FCS) is a single molecule sensitive tool for the quantitative measurement of biomolecular dynamics and interactions. Improvements in biology, computation, and detection technology enable real-time FCS experiments with multiplexed detection even in vivo. These new imaging modalities of FCS generate data at the rate of hundreds of MB/s requiring efficient data processing tools to extract information. Here, we briefly review FCS’s capabilities and limitations before discussing recent directions that address these limitations with a focus on imaging modalities of FCS, their combinations with super-resolution microscopy, new evaluation strategies, especially machine learning, and applications in vivo.

show abstract

Machine intelligence-driven classification of cancer patients-derived extracellular vesicles using fluorescence correlation spectroscopy: results from a pilot study

Cited by 7 publications

References 30 publications

Cellular Adaptation Takes Advantage of Atavistic Regression Programs during Carcinogenesis

Cellular Adaptation Takes Advantage of Atavistic Regression Programs during Carcinogenesis

Deep learning reduces data requirements and allows real-time measurements in imaging FCS

Current capabilities and future perspectives of FCS: super-resolution microscopy, machine learning, and in vivo applications

Contact Info

Product

Resources

About