Cost-efficient segmentation of electron microscopy images using active learning
This addresses the expensive labeling problem for researchers in biomedical imaging, though it is incremental as it adapts existing active learning techniques to a new task.
The paper tackles the high cost of labeling for electron microscopy image segmentation by applying active learning to deep CNNs, achieving a 10-15% improvement in Jaccard score compared to randomized sampling.
Over the last decade, electron microscopy has improved up to a point that generating high quality gigavoxel sized datasets only requires a few hours. Automated image analysis, particularly image segmentation, however, has not evolved at the same pace. Even though state-of-the-art methods such as U-Net and DeepLab have improved segmentation performance substantially, the required amount of labels remains too expensive. Active learning is the subfield in machine learning that aims to mitigate this burden by selecting the samples that require labeling in a smart way. Many techniques have been proposed, particularly for image classification, to increase the steepness of learning curves. In this work, we extend these techniques to deep CNN based image segmentation. Our experiments on three different electron microscopy datasets show that active learning can improve segmentation quality by 10 to 15% in terms of Jaccard score compared to standard randomized sampling.