Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands
This addresses the need for efficient and adaptable segmentation in medical imaging, though it is incremental as it builds on existing U-Net and NODE frameworks.
The paper tackled the problem of hard-coded receptive field sizes in U-Net-based medical image segmentation by integrating Neural Ordinary Differential Equations (NODEs), resulting in improved segmentation on the GlaS dataset with reduced memory and parameters.
Automated medical image segmentation plays a key role in quantitative research and diagnostics. Convolutional neural networks based on the U-Net architecture are the state-of-the-art. A key disadvantage is the hard-coding of the receptive field size, which requires architecture optimization for each segmentation task. Furthermore, increasing the receptive field results in an increasing number of weights. Recently, Neural Ordinary Differential Equations (NODE) have been proposed, a new type of continuous depth deep neural network. This framework allows for a dynamic receptive field at a fixed memory cost and a smaller amount of parameters. We show on a colon gland segmentation dataset (GlaS) that these NODEs can be used within the U-Net framework to improve segmentation results while reducing memory load and parameter counts.