Ultrafast Focus Detection for Automated Microscopy

TL;DR

This paper introduces a rapid, GPU-accelerated focus detection algorithm for electron microscopy images, enabling near-real-time quality control in automated neuroscience workflows by detecting out-of-focus images within 20ms.

Contribution

The paper presents a novel multi-scale histologic feature detection method that adapts classical computer vision techniques for ultrafast focus assessment in electron microscopy.

Findings

Detects out-of-focus images within 20ms

Operates as an on-demand service for real-time focus evaluation

Enables efficient quality control in automated microscopy workflows

Abstract

Technological advancements in modern scientific instruments, such as scanning electron microscopes (SEMs), have significantly increased data acquisition rates and image resolutions enabling new questions to be explored; however, the resulting data volumes and velocities, combined with automated experiments, are quickly overwhelming scientists as there remain crucial steps that require human intervention, for example reviewing image focus. We present a fast out-of-focus detection algorithm for electron microscopy images collected serially and demonstrate that it can be used to provide near-real-time quality control for neuroscience workflows. Our technique, \textit{Multi-scale Histologic Feature Detection}, adapts classical computer vision techniques and is based on detecting various fine-grained histologic features. We exploit the inherent parallelism in the technique to employ GPU primitives in order to accelerate characterization. We show that our method can detect of out-of-focus conditions within just 20ms. To make these capabilities generally available, we deploy our feature detector as an on-demand service and show that it can be used to determine the degree of focus in approximately 230ms, enabling near-real-time use.