Key result
A novel two-step machine learning algorithm using a 3D convolutional neural network achieved 90% accuracy in classifying vessel segments and an 83% overall end-to-end accuracy in automatically identifying perfused microvessels from intravital video microscopy.
Why the study?
Manual analysis of intravital video microscopy images for microvascular blood flow is challenging, time consuming, and susceptible to human error.
A novel two-step machine learning algorithm using a 3D-CNN can efficiently and accurately automate the functional analysis of microvascular blood flow in intravital video microscopy.
Answers are grounded in this paper and cite their sources.
May enable efficient microvascular analysis in animal models; leaves open clinical translation pending human validation.
Microvascular blood flow is crucial for tissue and organ function and is often severely affected by diseases. Therefore, investigating the microvasculature under different pathological circumstances is essential to understand the role of the microcirculation in health and sickness. Microvascular blood flow is generally investigated with Intravital Video Microscopy (IVM), and the captured images are stored on a computer for later off-line analysis. The analysis of these images is a manual and challenging process, evaluating experiments very time consuming and susceptible to human error. Since more advanced digital cameras are used in IVM, the experimental data volume will also increase significantly. This study presents a new two-step image processing algorithm that uses a trained Convolutional Neural Network (CNN) to functionally analyze IVM microscopic images without the need for manual analysis. While the first step uses a modified vessel segmentation algorithm to extract the location of vessel-like structures, the second step uses a 3D-CNN to assess whether the vessel-like structures have blood flowing in it or not. We demonstrate that our two-step algorithm can efficiently analyze IVM image data with high accuracy (83%). To our knowledge, this is the first application of machine learning for the functional analysis of microvascular blood flow in vivo.
No takes yet. Share an insight, caveat, or question.
Mahmoud et al. (2021) studied Microvascular blood flow analysis (n=458). Two-step machine learning algorithm (SUDCS and 3D-CNN) vs. Manual analysis and simple logistic regression was evaluated on Accuracy of identifying flowing versus non-flowing vessel segments. A novel two-step machine learning algorithm using a 3D convolutional neural network achieved 90% accuracy in classifying vessel segments and an 83% overall end-to-end accuracy in automatically identifying perfused microvessels from intravital video microscopy.
Synapse has enriched 10 related papers. Consider them for comparative context: