FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics
This work addresses the need for scalable image analysis algorithms in connectomics research, which is crucial for studying brain connectivity maps with minimal user intervention, though it appears incremental as it builds on existing deep learning techniques.
The authors tackled the problem of automatically segmenting neuronal structures in connectomics data by introducing FusionNet, a deep fully residual convolutional neural network, which achieved competitive performance compared to state-of-the-art methods in the ISBI EM segmentation challenge.
Electron microscopic connectomics is an ambitious research direction with the goal of studying comprehensive brain connectivity maps by using high-throughput, nano-scale microscopy. One of the main challenges in connectomics research is developing scalable image analysis algorithms that require minimal user intervention. Recently, deep learning has drawn much attention in computer vision because of its exceptional performance in image classification tasks. For this reason, its application to connectomic analyses holds great promise, as well. In this paper, we introduce a novel deep neural network architecture, FusionNet, for the automatic segmentation of neuronal structures in connectomics data. FusionNet leverages the latest advances in machine learning, such as semantic segmentation and residual neural networks, with the novel introduction of summation-based skip connections to allow a much deeper network architecture for a more accurate segmentation. We demonstrate the performance of the proposed method by comparing it with state-of-the-art electron microscopy (EM) segmentation methods from the ISBI EM segmentation challenge. We also show the segmentation results on two different tasks including cell membrane and cell body segmentation and a statistical analysis of cell morphology.