3D convolutional neural networks for stalled brain capillary detection

Roman A. Solovyev, Alexandr A. Kalinin, Tatiana Gabruseva

Abstract: Highlights•A state-of-the-art deep learning approach for detecting stalled capillaries in 3D microscopic brain images.•Custom 3D image augmentations and 2D-to-3D model weight transfer substantially improve performance.•Best model achieves 85% Matthews correlation coefficient, 85% sensitivity, and 99.3% specificity.•1st place in the ”Clog Loss: Advance Alzheimer's Research with Stall Catchers” machine learning competition.•3D augmentations library, trained models, and source code are publicly available at GitHub.