Application of Deep Supervised Learning to Nailfold videocapillaroscopy and Red Blood Cells Velocity Approximation
Keywords: Videocapillaroscopy, Red blood cells, Semantic segmentation, Deep convolutional networks, Long short-term memory networks
Abstract: The paper deals with processing data obtained using nailfold high-speed videocapillaroscopy. To detect the red blood cells speed two approaches are used. The deterministic approach is based on pixel intensities analysis for object detection and calculation of the red blood cells displacement and velocity in a vessel. The obtained data formulate targets for machine learning. The stochastic approach is based on a sequence of artificial neural networks. The semantic segmentation network UNet is used for vessel detection. Then, the classification network GoogLeNet or ResNet18 is used as a feature extractor to convert masked video frames to a sequence of feature vectors. And finally, the long short-term memory network is used to approximate the red blood cells velocity. The results demonstrated that the accuracy of the mean velocity approximation in the time range of several seconds is up to 0.96. But the accuracy at each specific time moment is less accurate. So, the proposed algorithm allows determination of the RBCs mean velocity but it doesn’t allow the determination of the RBCs pulsations accurate enough.
Paper Type: both
Primary Subject Area: Detection and Diagnosis
Secondary Subject Area: Segmentation
Paper Status: original work, not submitted yet
Source Code Url: https://github.com/avkornaev/VCS_nail_Fold
Data Set Url: https://drive.google.com/drive/folders/1cgWhJhzVz7ios7Ki6Q9G3ikoSCfWy3UB?usp=sharing
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
3 Replies
Loading