Fast Mitochondria Detection for Connectomics
This addresses the need for efficient analysis of petabyte-scale connectomics data to study diseases like autism or bipolar, though it is incremental as it builds on existing U-Net architectures.
The paper tackles the problem of automatically detecting dysfunctional mitochondria in large-scale connectomics data, achieving a Jaccard index of up to 0.90 and inference times under 16ms per image tile, enabling real-time detection.
High-resolution connectomics data allows for the identification of dysfunctional mitochondria which are linked to a variety of diseases such as autism or bipolar. However, manual analysis is not feasible since datasets can be petabytes in size. We present a fully automatic mitochondria detector based on a modified U-Net architecture that yields high accuracy and fast processing times. We evaluate our method on multiple real-world connectomics datasets, including an improved version of the EPFL mitochondria benchmark. Our results show an Jaccard index of up to 0.90 with inference times lower than 16ms for a 512x512px image tile. This speed is faster than the acquisition speed of modern electron microscopes, enabling mitochondria detection in real-time. Our detector ranks first for real-time detection when compared to previous works and data, results, and code are openly available.