On September 19, Zach Eaton-Rosen, a Researcher at the School of Biomedical Engineering & Imaging Sciences, won the 2018 MICCAI Education Challenge. The 21st conference on Medical Image Computing and Computer Assisted Intervention hosted the world’s leading biomedical scientists, engineers, and clinicians from a wide range of disciplines in the medical imaging and computer assisted intervention field.
Eaton-Rosen, whose research at King’s focuses on using deep learning for improved treatment of brain cancer, received the ‘Best Tutorial Award’ for his work on using NiftyNet to train U-net for cell segmentation. NiftyNet, of which Eaton-Rosen is a core developer, is an open-source convolutional neural networks (CNNs) software platform that aims to enable high-quality, reproducible research in medical imaging and deep learning. NiftyNet is used by a wide range of people in the medical imaging field from research scientists to hospitals to improve clinical workflow.
Eaton-Rosen’s work at King’s is currently focused on providing clinicians with quality checks that can highlight where a computational model is uncertain. This will lead to more informed treatment decisions and enable better human-computer collaboration.