Artificial Intelligence-Driven Image Analysis of Bacterial Cells and Biofilms.

The current study explores an artificial intelligence framework for measuring the structural features from microscopy images of the bacterial biofilms. Desulfovibrio alaskensis G20 (DA-G20) grown on mild steel surfaces is used as a model for sulfate reducing bacteria that are implicated in microbiologically influenced corrosion problems. Our goal is to automate the process of extracting the geometrical properties of the DA-G20 cells from the scanning electron microscopy (SEM) images, which is otherwise a laborious and costly process. These geometric properties are a biofilm phenotype that allow us to understand how the biofilm structurally adapts to the surface properties of the underlying metals, which can lead to better corrosion prevention solutions. We adapt two deep learning models: (a) a deep convolutional neural network (DCNN) model to achieve semantic segmentation of the cells, (d) a mask region-convolutional neural network (Mask R-CNN) model to achieve instance segmentation of the cells. These models are then integrated with moment invariants approach to measure the geometric characteristics of the segmented cells. Our numerical studies confirm that the Mask-RCNN and DCNN methods are 227x and 70x faster respectively, compared to the traditional method of manual identification and measurement of the cell geometric properties by the domain experts.

Modular Micro Raman Reader Instrument for Fast SERS-Based Detection of Biomarkers.

Sensitive detection of biomarkers is very critical in the diagnosis, management, and monitoring of diseases. Recent efforts have suggested that bioassays using surface-enhanced Raman scattering as a signal read-out strategy possess certain unique beneficial features in terms of sensitivity and low limits of detection which set this method apart from its counterparts such as fluorescence, phosphorescence, and radiolabeling. Surface-enhanced Raman scattering (SERS) has also emerged as an ideal choice for the development of multiplexed bioassays. Such promising features have prompted the need for the development of SERS-based tools suitable for point-of-care applications. These tools must be easy to use, portable, and automated for the screening of many samples in clinical settings if diagnostic applications are considered. The availability of such tools will result in faster and more reliable detection of disease biomarkers, improving the accessibility of point-of-care diagnostics. In this paper, we describe a modular Raman reader instrument designed to create such a portable device suitable for screening a large number of samples with minimal operator assistance. The device's hardware is mostly built with commercially available components using our unique design. Dedicated software was created to automatically run sample screening and analyze the data measured. The mRR is an imaging system specifically created to automate measurements, eliminating human bias while enhancing the rate of data collection and analysis ~2000 times. This paper presents both the design and capabilities of the custom-built modular Raman reader system (mRR) capable of automated and fast measurements of sandwich immunoassay samples on gold substrates using modified gold nanoparticles as Raman tags. The limit of detection (LOD) of the tested MUC4-specific iSERS assay was measured to be 0.41 µg/mL.