A One-Shot Learning Framework for Assessment of Fibrillar Collagen from Second Harmonic Generation Images of an Infarcted Myocardium

Li, Qun; Mukhopadhyay, Supratik; Rodriguez, Maria Ximena Bastidas; Fu, Xing; Sahu, Sushant; Burk, David H.; Gartia, Manas

doi:10.1109/isbi45749.2020.9098444

Cited by 5 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such data could be used in conjunction with other downstream imaging and molecular assays to maximize the use of limited tissue, such as in the case of a kidney biopsy specimen. The specificity of endogenous fluorescence to the type of tubules and structures could be leveraged for use in future machine learning applications to delineate the content of a tissue section at high resolution (Liu et al, 2020; Rivenson et al, 2019). Furthermore, our preliminary data suggest that endogenous fluorescence itself may be altered by disease and could be potentially used for disease screening (Croce et al, 2010).…”

Section: Discussionmentioning

confidence: 99%

Label‐free imaging of non‐deparaffinized sections of the human kidney to determine tissue quality and signatures of disease

Sabo

Winfree

Bledsoe

et al. 2022

Physiological Reports

View full text Add to dashboard Cite

Label‐free fluorescence imaging of kidney sections can provide important morphological information, but its utility has not been tested in a histology processing workflow. We tested the feasibility of label‐free imaging of paraffin‐embedded sections without deparaffinization and its potential usefulness in generating actionable data. Kidney tissue specimens were obtained during percutaneous nephrolithotomy or via diagnostic needle biopsy. Unstained non‐deparaffinized sections were imaged using widefield fluorescence microscopy to capture endogenous fluorescence. Some samples were also imaged with confocal microscopy and multiphoton excitation to collect second harmonic generation (SHG) signal to obtain high‐quality autofluorescence images with optical sectioning. To adjudicate the label‐free signal, the samples or corresponding contiguous sections were subsequently deparaffinized and stained with Lillie's allochrome. Label‐free imaging allowed the recognition of various kidney structures and enabled morphological qualification for adequacy. SHG and confocal imaging yielded quantifiable high‐quality images for tissue collagens and revealed specific patterns in glomeruli and various tubules. Disease specimens from patients with diabetic kidney disease and focal segmental glomerulosclerosis showed distinctive signatures compared to specimens from healthy controls with normal kidney function. Quantitative cytometry could also be performed when DAPI is added in situ before imaging. These results show that label‐free imaging of non‐deparaffinized sections provides useful information about tissue quality that could be beneficial to nephropathologists by maximizing the use of scarce kidney tissue. This approach also provides quantifiable features that could inform on the biology of health and disease.

show abstract

Section: Discussionmentioning

confidence: 99%

Label‐free imaging of non‐deparaffinized sections of the human kidney to determine tissue quality and signatures of disease

Sabo

Winfree

Bledsoe

et al. 2022

Physiological Reports

View full text Add to dashboard Cite

show abstract

“…Intrinsic signals can be viewed as label-free using a nonlinear mode of multiphoton excitation called SHG [ 189 ]. Qun and colleagues have applied the SHG effect with the help of ML methods to develop images of the samples of thick heart tissue [ 190 ].…”

Section: Nlo Processes Analyzed With MLmentioning

confidence: 99%

A Framework for Biosensors Assisted by Multiphoton Effects and Machine Learning

et al. 2022

View full text Add to dashboard Cite

The ability to interpret information through automatic sensors is one of the most important pillars of modern technology. In particular, the potential of biosensors has been used to evaluate biological information of living organisms, and to detect danger or predict urgent situations in a battlefield, as in the invasion of SARS-CoV-2 in this era. This work is devoted to describing a panoramic overview of optical biosensors that can be improved by the assistance of nonlinear optics and machine learning methods. Optical biosensors have demonstrated their effectiveness in detecting a diverse range of viruses. Specifically, the SARS-CoV-2 virus has generated disturbance all over the world, and biosensors have emerged as a key for providing an analysis based on physical and chemical phenomena. In this perspective, we highlight how multiphoton interactions can be responsible for an enhancement in sensibility exhibited by biosensors. The nonlinear optical effects open up a series of options to expand the applications of optical biosensors. Nonlinearities together with computer tools are suitable for the identification of complex low-dimensional agents. Machine learning methods can approximate functions to reveal patterns in the detection of dynamic objects in the human body and determine viruses, harmful entities, or strange kinetics in cells.

show abstract

Artificial intelligence for the discovery of novel antimicrobial agents for emerging infectious diseases

Bess

Berglind

Mukhopadhyay

et al. 2022

Drug Discovery Today

View full text Add to dashboard Cite

A One-Shot Learning Framework for Assessment of Fibrillar Collagen from Second Harmonic Generation Images of an Infarcted Myocardium

Cited by 5 publications

References 18 publications

Label‐free imaging of non‐deparaffinized sections of the human kidney to determine tissue quality and signatures of disease

Label‐free imaging of non‐deparaffinized sections of the human kidney to determine tissue quality and signatures of disease

A Framework for Biosensors Assisted by Multiphoton Effects and Machine Learning

Artificial intelligence for the discovery of novel antimicrobial agents for emerging infectious diseases

Contact Info

Product

Resources

About