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

The analysis of microcirculation images has the potential to reveal early signs of life-threatening diseases such as sepsis. Quantifying the capillary density and the capillary distribution in microcirculation images can be used as a biological marker to assist critically ill patients. The quantific...

Full description

Saved in:
Bibliographic Details
Published in:Patterns (New York, N.Y.) Vol. 4; no. 1; p. 100641
Main Authors: Helmy, Maged, Truong, Trung Tuyen, Jul, Eric, Ferreira, Paulo
Format: Journal Article
Language:English
Published: United States Elsevier Inc 13.01.2023
Elsevier
Subjects:
image analysis
literature survey
microcirculation analysis
Review
microcirculation analysis
DSML1: Concept: Basic principles of a new data science output observed and reported
image analysis
literature survey
ISSN:2666-3899, 2666-3899
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The analysis of microcirculation images has the potential to reveal early signs of life-threatening diseases such as sepsis. Quantifying the capillary density and the capillary distribution in microcirculation images can be used as a biological marker to assist critically ill patients. The quantification of these biological markers is labor intensive, time consuming, and subject to interobserver variability. Several computer vision techniques with varying performance can be used to automate the analysis of these microcirculation images in light of the stated challenges. In this paper, we present a survey of over 50 research papers and present the most relevant and promising computer vision algorithms to automate the analysis of microcirculation images. Furthermore, we present a survey of the methods currently used by other researchers to automate the analysis of microcirculation images. This survey is of high clinical relevance because it acts as a guidebook of techniques for other researchers to develop their microcirculation analysis systems and algorithms. The analysis of microcirculation images has the potential to reveal early signs of life-threatening diseases. Quantifying the capillary distribution in microcirculation images can be used as a biological marker to assist patients. The quantification of these biological markers is labor-intensive, time-consuming, and subject to interobserver variability. Moreover, manual analysis has been reported to hinder the application of microvascular microscopy in a clinical environment. Several computer vision techniques with varying performances can be used to automate the analysis of these microcirculation images. Computer vision algorithms are faster than convolutional neural networks for capillary detection but have poorer accuracy. Convolutional neural networks are more accurate but slower and require many training data. Therefore, by creating a hybrid model combining both computer vision algorithms and convolutional neural networks, one can strike a balance between accuracy and speed. The quantification of capillaries in microcirculation images can potentially reveal life-threatening diseases. The quantification of these biological markers is labor intensive, time consuming, and subject to interobserver variability. Several computer vision techniques with varying performances can be used to automate the analysis of these microcirculation images to bring microcirculation analysis closer to clinical practice.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
ObjectType-Review-3
content type line 23
ISSN:2666-3899
2666-3899
DOI:10.1016/j.patter.2022.100641