Efficient, high-performance pancreatic segmentation using multi-scale feature extraction

09/02/2020

∙

by   Moritz Knolle, et al.

∙

16

∙

share

For artificial intelligence-based image analysis methods to reach clinical applicability, the development of high-performance algorithms is crucial. For example, existent segmentation algorithms based on natural images are neither efficient in their parameter use nor optimized for medical imaging. Here we present MoNet, a highly optimized neural-network-based pancreatic segmentation algorithm focused on achieving high performance by efficient multi-scale image feature utilization.