Increasing segmentation performance with synthetic agar plate images.

Background: Agar plate analysis is vital for microbiological testing in industries like food, pharmaceuticals, and biotechnology. Manual inspection is slow, laborious, and error-prone, while existing automated systems struggle with the complexity of real-world agar plates. A shortage of diverse datasets hinders the development and evaluation of robust automated systems. Methods: In this paper, two new annotated datasets and a novel methodology for synthetic agar plate generation are presented. The datasets comprise 854 images of cultivated agar plates and 1,588 images of empty agar plates, encompassing various agar plate types and microorganisms. These datasets are an extension of the publicly available BRUKERCOLONY dataset, collectively forming one of the largest publicly available annotated datasets for research. The methodology is based on an efficient image generation pipeline that also simulates cultivation-related phenomena such as haemolysis or chromogenic reactions. Results: The augmentations significantly improved the Dice coefficient of trained U-Net models, increasing it from 0.671 to 0.721. Furthermore, training the U-Net model with a combination of real and 150% synthetic data demonstrated its efficacy, yielding a remarkable Dice coefficient of 0.729, a substantial improvement from the baseline of 0.518. UNet3+ exhibited the highest performance among the U-Net and Attention U-Net architectures, achieving a Dice coefficient of 0.767. Conclusions: Our experiments showed the methodology's applicability to real-world scenarios, even with highly variable agar plates. Our paper contributes to automating agar plate analysis by presenting a new dataset and effective methodology, potentially enhancing fully automated microbiological testing.

A thermostable Cas12b from Brevibacillus leverages one-pot discrimination of SARS-CoV-2 variants of concern.

BACKGROUND: Current SARS-CoV-2 detection platforms lack the ability to differentiate among variants of concern (VOCs) in an efficient manner. CRISPR/Cas (Clustered Regularly Interspaced Short Palindromic Repeats/CRISPR-associated) based detection systems have the potential to transform the landscape of COVID-19 diagnostics due to their programmability; however, most of these methods are reliant on either a multi-step process involving amplification or elaborate guide RNA designs. METHODS: Three Cas12b proteins from Alicyclobacillus acidoterrestris (AacCas12b), Alicyclobacillus acidiphilus (AapCas12b), and Brevibacillus sp. SYP-B805 (BrCas12b) were expressed and purified, and their thermostability was characterised by differential scanning fluorimetry, cis-, and trans-cleavage activities over a range of temperatures. The BrCas12b was then incorporated into a reverse transcription loop-mediated isothermal amplification (RT-LAMP)-based one-pot reaction system, coined CRISPR-SPADE (CRISPR Single Pot Assay for Detecting Emerging VOCs). FINDINGS: Here we describe a complete one-pot detection reaction using a thermostable Cas12b effector endonuclease from Brevibacillus sp. to overcome these challenges detecting and discriminating SARS-CoV-2 VOCs in clinical samples. CRISPR-SPADE was then applied for discriminating SARS-CoV-2 VOCs, including Alpha (B.1.1.7), Beta (B.1.351), Gamma (P.1), Delta (B.1.617.2), and Omicron (B.1.1.529) and validated in 208 clinical samples. CRISPR-SPADE achieved 92·8% sensitivity, 99·4% specificity, and 96·7% accuracy within 10-30 min for discriminating the SARS-CoV-2 VOCs, in agreement with S gene sequencing, achieving a positive and negative predictive value of 99·1% and 95·1%, respectively. Interestingly, for samples with high viral load (Ct value ≤ 30), 100% accuracy and sensitivity were attained. To facilitate dissemination and global implementation of the assay, a lyophilised version of one-pot CRISPR-SPADE reagents was developed and combined with an in-house portable multiplexing device capable of interpreting two orthogonal fluorescence signals. INTERPRETATION: This technology enables real-time monitoring of RT-LAMP-mediated amplification and CRISPR-based reactions at a fraction of the cost of a qPCR system. The thermostable Brevibacillus sp. Cas12b offers relaxed primer design for accurately detecting SARS-CoV-2 VOCs in a simple and robust one-pot assay. The lyophilised reagents and simple instrumentation further enable rapid deployable point-of-care diagnostics that can be easily expanded beyond COVID-19. FUNDING: This project was funded in part by the United States-India Science & Technology Endowment Fund- COVIDI/247/2020 (P.K.J.), Florida Breast Cancer Foundation- AGR00018466 (P.K.J.), National Institutes of Health- NIAID 1R21AI156321-01 (P.K.J.), Centers for Disease Control and Prevention- U01GH002338 (R.R.D., J.A.L., & P.K.J.), University of Florida, Herbert Wertheim College of Engineering (P.K.J.), University of Florida Vice President Office of Research and CTSI seed funds (M.S.), and University of Florida College of Veterinary Medicine and Emerging Pathogens Institute (R.R.D.).

A Thermostable Cas12b from Brevibacillus Leverages One-pot Detection of SARS-CoV-2 Variants of Concern.

Current SARS-CoV-2 detection platforms lack the ability to differentiate among variants of concern (VOCs) in an efficient manner. CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats) has the potential to transform diagnostics due to its programmability. However, many of the CRISPR-based detection methods are reliant on either a multi-step process involving amplification or elaborate guide RNA designs. A complete one-pot detection reaction using alternative Cas effector endonucleases has been proposed to overcome these challenges. Yet, current approaches using Alicyclobacillus acidiphilus Cas12b (AapCas12b) are limited by its thermal instability at optimum reverse transcription loop-mediated isothermal amplification (RT-LAMP) reaction temperatures. Herein, we demonstrate that a novel Cas12b from Brevibacillus sp. SYP-B805 (referred to as BrCas12b) has robust trans-cleavage activity at ideal RT-LAMP conditions. A competitive profiling study of BrCas12b against Cas12b homologs from other bacteria genera underscores the potential of BrCas12b in the development of new diagnostics. As a proof-of-concept, we incorporated BrCas12b into an RT-LAMP-mediated one-pot reaction system, coined CRISPR-SPADE (CRISPR Single Pot Assay for Detecting Emerging VOCs) to enable rapid, differential detection of SARS-CoV-2 VOCs, including Alpha (B.1.1.7), Beta (B.1.351), Gamma (P.1), and Delta (B.1.617.2) in 205 clinical samples. Notably, a BrCas12b detection signal was observed within 1-3 minutes of amplification, achieving an overall 98.1% specificity, 91.2% accuracy, and 88.1% sensitivity within 30 minutes. Significantly, for samples with high viral load (C t value ≤ 30), 100% accuracy and sensitivity were attained. To facilitate dissemination and global implementation of the assay, we combined the lyophilized one-pot reagents with a portable multiplexing device capable of interpreting fluorescence signals at a fraction of the cost of a qPCR system. With relaxed design requirements, one-pot detection, and simple instrumentation, this assay has the capability to advance future diagnostics.

Automatically designed machine vision system for the localization of CCA transverse section in ultrasound images.

The common carotid artery (CCA) is a source of important information that doctors can use to evaluate the patients' health. The most often measured parameters are arterial stiffness, lumen diameter, wall thickness, and other parameters where variation with time is usually measured. Unfortunately, the manual measurement of dynamic parameters of the CCA is time consuming, and therefore, for practical reasons, the only alternative is automatic approach. The initial localization of artery is important and must precede the main measurement. This article describes a novel method for the localization of CCA in the transverse section of a B-mode ultrasound image. The novel method was designed automatically by using the grammar-guided genetic programming (GGGP). The GGGP searches for the best possible combination of simple image processing tasks (independent building blocks). The best possible solution is represented with the highest detection precision. The method is tested on a validation database of CCA images that was specially created for this purpose and released for use by other scientists. The resulting success of the proposed solution was 82.7%, which exceeded the current state of the art by 4% while the computation time requirements were acceptable. The paper also describes an automatic method that was used in designing the proposed solution. This automatic method provides a universal approach to designing complex solutions with the support of evolutionary algorithms.