Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

The micronucleus (MN) assay is used worldwide by regulatory bodies to evaluate chemicals for genetic toxicity. The assay can be performed in two ways: by scoring MN in once-divided, cytokinesis-blocked binucleated cells or fully divided mononucleated cells. Historically, light microscopy has been the gold standard method to score the assay, but it is laborious and subjective. Flow cytometry has been used in recent years to score the assay, but is limited by the inability to visually confirm key aspects of cellular imagery. Imaging flow cytometry (IFC) combines high-throughput image capture and automated image analysis, and has been successfully applied to rapidly acquire imagery of and score all key events in the MN assay. Recently, it has been demonstrated that artificial intelligence (AI) methods based on convolutional neural networks can be used to score MN assay data acquired by IFC. This paper describes all steps to use AI software to create a deep learning model to score all key events and to apply this model to automatically score additional data. Results from the AI deep learning model compare well to manual microscopy, therefore enabling fully automated scoring of the MN assay by combining IFC and AI.

The learning curve and safety of continuous intraoperative vagus nerve monitoring in thyroid surgery

INTRODUCTION

Continuous intraoperative nerve monitoring allows for continuous feedback on the integrity of the recurrent laryngeal nerve (RLN) and the quality of its induced myogenic potential. The aims of this study were to assess the time requirements and risks associated with vagus nerve electrode placement when learning the technique.

METHODS

This is a prospective observational study carried out in a single otolaryngology department at the start of a trainee's placement. A total of 40 vagus nerve dissections in 31 consecutive operations (22 hemithyroidectomies, 9 total thyroidectomies) using automatic periodic stimulation (APS, Medtronic) are included. Of the electrode placements, 10 were performed by the trainer and 30 by the trainee. The time required for each surgical step and complications relating to vagus nerve dissection were recorded.

RESULTS

The average (median+IQR) total additional time attributable to vagus nerve dissection, electrode placement and baseline electromyogenic assessment was 3.1mins (2.5-3.3) for the trainer and 4.8mins (4.1-5.3) for the trainee (p<0.0001). There was a downward trend in time requirement for the trainee (not statistically significant, p=0.080). Total operative time was 38min (35-45) for hemithyroidectomy and 56min (53-62) for total thyroidectomy. There was a mix of benign (74%) and malignant (26%) histology, no intraoperative complications relating to autonomic dysfunction and one (2.5%) transient nerve palsy.

CONCLUSIONS

Operative time attributable to vagus nerve electrode placement is short and the procedure is easy to learn. Appropriate surgical technique and careful anaesthetic considerations allow monitoring to be performed safely, and may reduce the rate of RLN palsy.

The in vitro micronucleus assay using imaging flow cytometry and deep learning

The in vitro micronucleus (MN) assay is a well-established assay for quantification of DNA damage, and is required by regulatory bodies worldwide to screen chemicals for genetic toxicity. The MN assay is performed in two variations: scoring MN in cytokinesis-blocked binucleated cells or directly in unblocked mononucleated cells. Several methods have been developed to score the MN assay, including manual and automated microscopy, and conventional flow cytometry, each with advantages and limitations. Previously, we applied imaging flow cytometry (IFC) using the ImageStream® to develop a rapid and automated MN assay based on high throughput image capture and feature-based image analysis in the IDEAS® software. However, the analysis strategy required rigorous optimization across chemicals and cell lines. To overcome the complexity and rigidity of feature-based image analysis, in this study we used the Amnis® AI software to develop a deep-learning method based on convolutional neural networks to score IFC data in both the cytokinesis-blocked and unblocked versions of the MN assay. We show that the use of the Amnis AI software to score imagery acquired using the ImageStream® compares well to manual microscopy and outperforms IDEAS® feature-based analysis, facilitating full automation of the MN assay.

A novel method to classify subpopulations in murine spleen and blood using multiparametric imaging flow cytometry

Being able to identify the lymphocytes, monocytes, and neutrophils (granuolcytes) subpopulations in murine spleen and peripheral blood is an important step of the analysis of the immune system. Conventionally, this task is accomplished by performing immunofluorescence staining of specific cell surface markers. However, given the distinct morphology of each of these subpopulations as well as the cell imageries obtained using the Image Stream technology, we attempt to identify 3cell types in the spleen and peripheral blood samples of C57BL/6 and BALB/c mice based solely on the Bright Field (BF), Side Scatter (SSC) and nuclear images without using any specific markers for the cell types. We will then compare the results obtained using this novel method with that obtained using immunofluorescence. We hope that the results will serve to both validate our methodology and highlight the value offered by this objective, automated, and quantitative approach towards other murine immune cell analysis, particularly in those situations where immunofluorescence based subpopulation detections are either unfeasible(due to fluorochrome conflicts) or impractical (due to high sample sizes).

Cellular image analysis and imaging by flow cytometry

Imaging flow cytometry combines the statistical power and fluorescence sensitivity of standard flow cytometry with the spatial resolution and quantitative morphology of digital microscopy. The technique is a good fit for clinical applications by providing a convenient means for imaging and analyzing cells directly in bodily fluids. Examples are provided of the discrimination of cancerous from normal mammary epithelial cells and the high-throughput quantitation of fluorescence in situ hybridization (FISH) probes in human peripheral blood mononuclear cells. The FISH application will be enhanced further by the integration of extended depth-of-field imaging technology with the current optical system.

Intracellular localization and trafficking using the ImageStream imaging flow cytometer (132.6)

Specific ligands or antibody-conjugated drugs can mediate their cellular effects by gaining entry into cells via receptor mediated endocytosis. Once internalized, molecules differ in their preferential endocytic pathway, and drug efficacy is highly dependant on the route of entry and interaction with cellular components. Evaluation of internalization and intracellular molecular trafficking events are traditionally performed using microscopy. These analyses are limited, because manual image acquistion and quantitative image analysis are time consuming processes. Here we describe a method for measuring internalized events using the ImageStream imaging flow cytometer, which automatically collects large numbers of images per data set and provides qunatitative image analysis tools. In addition, localization of internalized probes to endosomes and lysosomes is quantified in several model systems. Because the ImageStream collects multiple fluorescent images per cell, internalized marker colocalization to different cellular compartments can be done simultaneously in a quantitative manner.

Extended depth of field imaging for high speed cell analysis

BACKGROUND

Fluoresence microscopy is an extremely useful tool to analyze the intensity, location and movement of fluorescently tagged molecules on, within or between cells. However, the technique suffers from slow image acquisition rates and limited depth of field. Confocal microscopy addresses the depth of field issue via "optical sectioning and reconstruction", but only by further reducing the image acquisition rate to repeatedly scan the cell at multiple focal planes. In this paper we describe a technique to perform high speed, extended depth of field (EDF) imaging using a modified ImageStream system whereby high resolution, multimode imagery from thousands of cells is collected in less than a minute with focus maintained over a 16 microm focal range.

METHODS

A prototype EDF ImageStream system incorporating a Wavefront Coded element was used to capture imagery from fluorescently labeled beads. Bead imagery was quantitatively analyzed using photometric and morphological features to assess consistency of feature values with respect to focus position. Jurkat cells probed for chromosome Y using a fluorescence in situ hybridization in suspension protocol (FISHIS) were used to compare standard and Wavefront Coded-based EDF imaging approaches for automated chromosome enumeration.

RESULTS

Qualitative visual inspection of bead imagery reveals that the prototype ImageStream system with EDF maintains focus quality over a 16 microm focus range. Quantitative analysis shows the extended depth field collection mode has approximately ten-fold less variation in focus-sensitive feature values when compared with standard imaging. Automated chromosome enumeration from imagery of Jurkat cells probed using the FISHIS protocol is significantly more accurate using EDF imaging.

CONCLUSIONS

The use of EDF techniques may significantly enhance the quantitation of cell imagery, particularly in applications such as FISH, where small discrete signals must be detected over a wide focal range within the cell.

Preliminary analysis of the transcriptional regulation of the human beta 1-adrenergic receptor gene

One open reading frame of a 13 kb genomic clone of the human beta 1-adrenergic receptor, which lacks introns, encodes the previously isolated cDNA. Transcript(s) between 4.7 and 5.1 kb are detected in total RNA, whereas a approximately 3 kb transcript is detected only in polyadenylated RNA. The poly (A+) transcript is most highly expressed in the pancreas, liver, heart, kidney, thalamus, adrenal, and salivary glands. Primer extension and ribonuclease protection analyses suggest that the major transcriptional start site is located at -263. Transient expression of luciferase reporter gene constructs indicates that the region from -444 to -360 possesses the primary promoter, consistent with the transcriptional start site at -263. Negative transcriptional regulatory elements are located from -3118 to -2730 and -2730 to -2241, while a positive element is located between -2241 and -1790. The present study suggests that, despite similarities, the expression and transcriptional regulation of the human gene are distinct from those of the genes of other species.