BCM3D 2.0: accurate segmentation of single bacterial cells in dense biofilms using computationally generated intermediate image representations

TLDR

Accurate segmentation of single cells in 3D fluorescence images is essential for studying bacterial biofilms, and recent machine‑learning advances have improved this capability, with BCM3D 2.0 building on the earlier BCM3D 1.0 approach. The study introduces BCM3D 2.0 to overcome low signal‑to‑background ratios and high cell density challenges in biofilm imaging. BCM3D 2.0 trains CNNs to convert 3D fluorescence images into intermediate representations that, when combined with conventional image processing, enable more accurate segmentation than voxel‑classification approaches. BCM3D 2.0 achieves superior segmentation even at low SBRs and high cell densities, enabling more accurate 3D cell tracking and facilitating time‑dependent studies of bacterial biofilms at the cellular level.

Abstract

Accurate detection and segmentation of single cells in three-dimensional (3D) fluorescence time-lapse images is essential for observing individual cell behaviors in large bacterial communities called biofilms. Recent progress in machine-learning-based image analysis is providing this capability with ever-increasing accuracy. Leveraging the capabilities of deep convolutional neural networks (CNNs), we recently developed bacterial cell morphometry in 3D (BCM3D), an integrated image analysis pipeline that combines deep learning with conventional image analysis to detect and segment single biofilm-dwelling cells in 3D fluorescence images. While the first release of BCM3D (BCM3D 1.0) achieved state-of-the-art 3D bacterial cell segmentation accuracies, low signal-to-background ratios (SBRs) and images of very dense biofilms remained challenging. Here, we present BCM3D 2.0 to address this challenge. BCM3D 2.0 is entirely complementary to the approach utilized in BCM3D 1.0. Instead of training CNNs to perform voxel classification, we trained CNNs to translate 3D fluorescence images into intermediate 3D image representations that are, when combined appropriately, more amenable to conventional mathematical image processing than a single experimental image. Using this approach, improved segmentation results are obtained even for very low SBRs and/or high cell density biofilm images. The improved cell segmentation accuracies in turn enable improved accuracies of tracking individual cells through 3D space and time. This capability opens the door to investigating time-dependent phenomena in bacterial biofilms at the cellular level.