CapillaryNet: An automated system to quantify skin capillary density and red blood cell velocity from handheld vital microscopy

Helmy, Maged; A, Dykyy; Truong, Tu T.; Ferreira, Paulo H.; E, Jul

doi:10.1016/j.artmed.2022.102287

Cited by 5 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has also been shown to be the best method among the three for background selection in the CapillaryNet paper. 36 …”

Section: Traditional Computer Vision Object Detection Techniquesmentioning

confidence: 99%

“… 165 deep neural networks accuracy of 83.3% reported uses a non-linear support vector machine Javia et al. 166 deep neural networks accuracy of 89.45% reported uses a ResNet architecture CapillaryNet 36 mixture of traditional computer vision techniques and deep neural networks accuracy of 93% reported uses a combination of traditional computer vision techniques, including image background subtraction, image enchantment, and shallow convolutional neural networks …”

Section: State-of-the-art Microcirculation Image Analysis Techniquesmentioning

confidence: 99%

“…Recently, the microvascular community has been focused on standardizing the analysis of microcirculation images 33 by using automated methods 34 , 35 , 36 (see state-of-the-art microcirculation image analysis techniques ). This is of exceptionally high importance as, currently, the gold standard for microvascular analysis is manual analysis by a trained researcher.…”

Section: Introductionmentioning

confidence: 99%

“…That being said, we believe that a combination of both of these methods will be the future of microcirculation analysis in the clinical setting. 36 …”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep learning and computer vision techniques for microcirculation analysis: A review

et al. 2023

Self Cite

View full text Add to dashboard Cite

“…This has also been shown to be the best method among the three for background selection in the CapillaryNet paper. 36 …”

Section: Traditional Computer Vision Object Detection Techniquesmentioning

confidence: 99%

Section: State-of-the-art Microcirculation Image Analysis Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…That being said, we believe that a combination of both of these methods will be the future of microcirculation analysis in the clinical setting. 36 …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning and computer vision techniques for microcirculation analysis: A review

et al. 2023

Self Cite

View full text Add to dashboard Cite

“…In CapillaryNet [16], the capillary density is quantified and red blood cell velocity is computed from videos obtained from handheld microscope. This also measures several novel microvascular parameters like capillary hematocrit and intra-capillary flow velocity heterogeneity.…”

Section: Object Detectionmentioning

confidence: 99%

Deep learning based object detection in nailfold capillary images

Venkatapathiah

Selvan

Nanda

et al. 2023

IJ-AI

View full text Add to dashboard Cite

Microcirculation in a subject can be examined and pathological changes can be assessed by utilizing capillaroscopy, which is a very safe, convenient and non-invasive approach. Using a microscope, doctors view the capillaries by looking through nailfold epidermis. Nailfold anatomy is ideal to evaluate the microcirculation and detect various diseases caused by vascular damages. Rheumatologists evaluate systemic diseases which involve damage in vasculature, by analyzing the red blood cells within the capillaries. Sometimes, capillary morphology may be useful as an early indicator while, severity of damage in capillary architecture may indicate internal organ involvement. Thus, in a capillaroscopic assessment, the doctor examines modifications in morphological and functional aspects of capillaries. These comprise of capillary diameter, visibility, distribution, length, microhemorrhages, blood flow and density. In this paper, a novel object detection algorithm is proposed based on deep learning architectures for detecting and locating various capillary loops in the nailfold region. Various characteristic features are extracted from the capillaries through image processing algorithms and in turn an attempt is made to differentiate between images of diseased subjects and healthy controls.

show abstract

The potential role of ischaemia–reperfusion injury in chronic, relapsing diseases such as rheumatoid arthritis, Long COVID, and ME/CFS: evidence, mechanisms, and therapeutic implications

Kell

2022

Biochemical Journal

View full text Add to dashboard Cite

Ischaemia–reperfusion (I–R) injury, initiated via bursts of reactive oxygen species produced during the reoxygenation phase following hypoxia, is well known in a variety of acute circumstances. We argue here that I–R injury also underpins elements of the pathology of a variety of chronic, inflammatory diseases, including rheumatoid arthritis, ME/CFS and, our chief focus and most proximally, Long COVID. Ischaemia may be initiated via fibrin amyloid microclot blockage of capillaries, for instance as exercise is started; reperfusion is a necessary corollary when it finishes. We rehearse the mechanistic evidence for these occurrences here, in terms of their manifestation as oxidative stress, hyperinflammation, mast cell activation, the production of marker metabolites and related activities. Such microclot-based phenomena can explain both the breathlessness/fatigue and the post-exertional malaise that may be observed in these conditions, as well as many other observables. The recognition of these processes implies, mechanistically, that therapeutic benefit is potentially to be had from antioxidants, from anti-inflammatories, from iron chelators, and via suitable, safe fibrinolytics, and/or anti-clotting agents. We review the considerable existing evidence that is consistent with this, and with the biochemical mechanisms involved.

show abstract

CapillaryNet: An automated system to quantify skin capillary density and red blood cell velocity from handheld vital microscopy

Cited by 5 publications

References 53 publications

Deep learning and computer vision techniques for microcirculation analysis: A review

Deep learning and computer vision techniques for microcirculation analysis: A review

Deep learning based object detection in nailfold capillary images

The potential role of ischaemia–reperfusion injury in chronic, relapsing diseases such as rheumatoid arthritis, Long COVID, and ME/CFS: evidence, mechanisms, and therapeutic implications

Contact Info

Product

Resources

About