Currently, there are several machine learning models for identifying stroke lesions in computed tomography-perfusion (CT-P) images. But they do not perform well enough for clinical applications ...

A new geometric machine learning method promises to accelerate precision drug development Peer-Reviewed Publication CeMM Research Center for Molecular Medicine of the Austrian Academy of Sciences ...

As reported in their study published in the Journal of Medical Imaging, the team built a geometric deep learning model called "Graph Fully-Convolutional Network" (GFCN).

A research team from Leipzig University, the Max Planck Institute and Heidelberg University, all in Germany, devised a new segmentation algorithm for stroke lesions that improves upon previous methods ...

AI analyzes, predicts protein–DNA structures DeepPBS employs a geometric deep learning model, a type of machine-learning approach that analyzes data using geometric structures.

A machine-learning model developed in this study was able to predict 24-hour peaks for intraocular pressure (IOP).