Deep Neural Patchworks: Coping with Large Segmentation Tasks
This addresses a critical bottleneck for researchers and practitioners in biomedical imaging and other fields dealing with large image segmentation tasks, offering an incremental improvement over existing patch-based methods.
The paper tackles the memory limitation problem in segmenting large images, especially in biomedical 3D imaging, by proposing Deep Neural Patchworks (DNP), a framework that uses hierarchical and nested stacking of patch-based networks to maintain global context while reducing memory demands.
Convolutional neural networks are the way to solve arbitrary image segmentation tasks. However, when images are large, memory demands often exceed the available resources, in particular on a common GPU. Especially in biomedical imaging, where 3D images are common, the problems are apparent. A typical approach to solve this limitation is to break the task into smaller subtasks by dividing images into smaller image patches. Another approach, if applicable, is to look at the 2D image sections separately, and to solve the problem in 2D. Often, the loss of global context makes such approaches less effective; important global information might not be present in the current image patch, or the selected 2D image section. Here, we propose Deep Neural Patchworks (DNP), a segmentation framework that is based on hierarchical and nested stacking of patch-based networks that solves the dilemma between global context and memory limitations.