Analysis of Information Flow Through U-Nets
This addresses the need for better design and understanding of U-Nets in medical image processing, but it is incremental as it builds on existing methods without introducing a new paradigm.
The paper tackled the problem of understanding information flow in U-Nets for medical image segmentation by using information-theoretic tools, resulting in insights that can assess architectural efficiency and propose more efficient designs.
Deep Neural Networks (DNNs) have become ubiquitous in medical image processing and analysis. Among them, U-Nets are very popular in various image segmentation tasks. Yet, little is known about how information flows through these networks and whether they are indeed properly designed for the tasks they are being proposed for. In this paper, we employ information-theoretic tools in order to gain insight into information flow through U-Nets. In particular, we show how mutual information between input/output and an intermediate layer can be a useful tool to understand information flow through various portions of a U-Net, assess its architectural efficiency, and even propose more efficient designs.