Vingroup AI Engineer Program - Computer Vision Project

Project Title

Image Classification of Stroke Blood Clot Origin.
## The goal of this competition is to classify the blood clot origins in ischemic stroke. Using whole slide digital pathology images, you’ll build a model that differentiates between the two major acute ischemic stroke (AIS) etiology subtypes: cardiac and large artery atherosclerosis.

Your work will enable healthcare providers to better identify the origins of blood clots in deadly strokes, making it easier for physicians to prescribe the best post-stroke therapeutic management and reducing the likelihood of a second stroke.

ViT model

  • Split image into patchs
  • Pipeline ViT model

Video Demo

Authors

Contributors names and contact info

Acknowledgments

  • competition
  • https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6778842/
  • https://pathml.readthedocs.io/en/latest/examples/link_stain_normalization.html
  • https://wwwx.cs.unc.edu/~mn/sites/default/files/macenko2009.pdf
  • Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology
  • Tailoring automated data augmentation to H&E-stained Histopathology