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

Abstract

Accurate detection and segmentation of single cells in three-dimensional (3D) fluorescence time-lapse images is essential for measuring individual cell behaviors in large bacterial communities called biofilms. Recent progress in machine-learning-based image analysis is providing this capability with every 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 completely 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 later, 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, which opens the door to investigating time-dependent phenomena in bacterial biofilms at the cellular level.

High content quantitative imaging of Mycobacterium tuberculosis responses to acidic microenvironments within human macrophages

“…These limitations could be addressed by combining of super resolution microscopy with machine‐learning approaches that could achieve automated analysis of single mycobacterial cells in 3D overtime. Such approaches have been used recently to accurately segment and monitor single bacterial behaviour within 3D biofilms [ 49 , 50 ]. These tools will revolutionise automated segmentation and analysis to achieve single‐Mtb‐organelle segmentation and will provide new insights on the molecular and cellular mechanisms underlying the cell biology of TB infection.…”

A Systematic Literature Review of Deep Learning-Based Detection and Classification Methods for Bacterial Colonies

“…In [41], the authors build on a previously proposed BCM3D approach. BCM3D is a combination of image processing techniques and CNN to detect, count, and segment single cell bacteria from biofilms.…”

“…The authors in [29] performed supervisedlearning-based bacterial colony classification by employing TL. The authors in [37], [31], and [41] made use of supervised learning to train models. In [36], the authors propose a finetuning-based supervised learning approach for pathogenic bacteria identification.…”

“…These datasets are available for download. The authors in [41] prepared an academic dataset composed of fluorescence microscopic images to train and test deep learning models. The authors processed the images and created two types of transitional images for object localization and boundary detection.…”