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

Code

• github.com/TUM-AIMED/MoNet
  OfficialIn papertf★ 1

Abstract

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.

Tasks

Reproductions