DeepCell Kiosk: scaling deep learning-enabled cellular image analysis with Kubernetes.

Deep learning is transforming the analysis of biological images, but applying these models to large datasets remains challenging. Here we describe the DeepCell Kiosk, cloud-native software that dynamically scales deep learning workflows to accommodate large imaging datasets. To demonstrate the scalability and affordability of this software, we identified cell nuclei in 106 1-megapixel images in ~5.5 h for ~US$250, with a cost below US$100 achievable depending on cluster configuration. The DeepCell Kiosk can be downloaded at https://github.com/vanvalenlab/kiosk-console ; a persistent deployment is available at https://deepcell.org/ .

Quantitative Magnetic Separation of Particles and Cells Using Gradient Magnetic Ratcheting.

Extraction of rare target cells from biosamples is enabling for life science research. Traditional rare cell separation techniques, such as magnetic activated cell sorting, are robust but perform coarse, qualitative separations based on surface antigen expression. A quantitative magnetic separation technology is reported using high-force magnetic ratcheting over arrays of magnetically soft micropillars with gradient spacing, and the system is used to separate and concentrate magnetic beads based on iron oxide content (IOC) and cells based on surface expression. The system consists of a microchip of permalloy micropillar arrays with increasing lateral pitch and a mechatronic device to generate a cycling magnetic field. Particles with higher IOC separate and equilibrate along the miropillar array at larger pitches. A semi-analytical model is developed that predicts behavior for particles and cells. Using the system, LNCaP cells are separated based on the bound quantity of 1 µm anti-epithelial cell adhesion molecule (EpCAM) particles as a metric for expression. The ratcheting cytometry system is able to resolve a ±13 bound particle differential, successfully distinguishing LNCaP from PC3 populations based on EpCAM expression, correlating with flow cytometry analysis. As a proof-of-concept, EpCAM-labeled cells from patient blood are isolated with 74% purity, demonstrating potential toward a quantitative magnetic separation instrument.

Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning.

Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep-learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from multiplexed error-robust FISH (MERFISH), sequential fluorescence in situ hybridization (seqFISH), or in situ RNA sequencing (ISS) experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org.

Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning.

Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually-tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from MERFSIH, seqFISH, or ISS experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org.

A Foundation Model for Cell Segmentation.

Cells are a fundamental unit of biological organization, and identifying them in imaging data - cell segmentation - is a critical task for various cellular imaging experiments. While deep learning methods have led to substantial progress on this problem, most models in use are specialist models that work well for specific domains. Methods that have learned the general notion of "what is a cell" and can identify them across different domains of cellular imaging data have proven elusive. In this work, we present CellSAM, a foundation model for cell segmentation that generalizes across diverse cellular imaging data. CellSAM builds on top of the Segment Anything Model (SAM) by developing a prompt engineering approach for mask generation. We train an object detector, CellFinder, to automatically detect cells and prompt SAM to generate segmentations. We show that this approach allows a single model to achieve human-level performance for segmenting images of mammalian cells (in tissues and cell culture), yeast, and bacteria collected across various imaging modalities. We show that CellSAM has strong zero-shot performance and can be improved with a few examples via few-shot learning. We also show that CellSAM can unify bioimaging analysis workflows such as spatial transcriptomics and cell tracking. A deployed version of CellSAM is available at https://cellsam.deepcell.org/.

Continuous and Quantitative Purification of T-Cell Subsets for Cell Therapy Manufacturing Using Magnetic Ratcheting Cytometry.

T-cell-based immunotherapies represent a growing medical paradigm that has the potential to revolutionize contemporary cancer treatments. However, manufacturing bottlenecks related to the enrichment of therapeutically optimal T-cell subpopulations from leukopak samples impede scale-up and scale-out efforts. This is mainly attributed to the challenges that current cell purification platforms face in balancing the quantitative sorting capacity needed to isolate specific T-cell subsets with the scalability to meet manufacturing throughputs. In this work, we report a continuous-flow, quantitative cell enrichment platform based on a technique known as ratcheting cytometry that can perform complex, multicomponent purification targeting various subpopulations of magnetically labeled T cells directly from apheresis or peripheral blood mononuclear cell (PBMC) samples. The integrated ratcheting cytometry instrument and cartridge demonstrated enrichment of T cells directly from concentrated apheresis samples with a 97% purity and an 85% recovery of magnetically tagged cells. Magnetic sorting of different T-cell subpopulations was also accomplished on chip by multiplexing cell surface targets onto particles with differing magnetic strengths. We believe that ratcheting cytometry's quantitative capacity and throughput scalability represents an excellent technology candidate to alleviate cell therapy manufacturing bottlenecks.

Correction: Unsupervised capture and profiling of rare immune cells using multi-directional magnetic ratcheting.

Correction for 'Unsupervised capture and profiling of rare immune cells using multi-directional magnetic ratcheting' by Coleman Murray et al., Lab Chip, 2018, 18, 2396-2409.

Unsupervised capture and profiling of rare immune cells using multi-directional magnetic ratcheting.

Immunotherapies (IT) require induction, expansion, and maintenance of specific changes to a patient's immune cell repertoire which yield a therapeutic benefit. Recently, mechanistic understanding of these changes at the cellular level has revealed that IT results in complex phenotypic transitions in target cells, and that therapeutic effectiveness may be predicted by monitoring these transitions during therapy. However, monitoring will require unique tools that enable capture, manipulation, and profiling of rare immune cell populations. In this study, we introduce a method of automated and unsupervised separation and processing of rare immune cells, using high-force and multidimensional magnetic ratcheting (MR). We demonstrate capture of target immune cells using samples with up to 1 : 10 000 target cell to background cell ratios from input volumes as small as 25 microliters (i.e. a low volume and low cell frequency sample sparing assay interface). Cell capture is shown to achieve up to 90% capture efficiency and purity, and captured cell analysis is shown using both on-chip culture/activity assays and off-chip ejection and nucleic acid analysis. These results demonstrate that multi-directional magnetic ratcheting offers a unique separation system for dealing with blood cell samples that contain either rare cells or significantly small volumes, and the "sample sparing" capability leads to an expanded spectrum of parameters that can be measured. These tools will be paramount to advancing techniques for immune monitoring under conditions in which both the sample volume and number of antigen-specific target cells are often exceedingly small, including during IT and treatment of allergy, asthma, autoimmunity, immunodeficiency, cell based therapy, transplantation, and infection.

Label-free isolation of prostate circulating tumor cells using Vortex microfluidic technology.

There has been increased interest in utilizing non-invasive "liquid biopsies" to identify biomarkers for cancer prognosis and monitoring, and to isolate genetic material that can predict response to targeted therapies. Circulating tumor cells (CTCs) have emerged as such a biomarker providing both genetic and phenotypic information about tumor evolution, potentially from both primary and metastatic sites. Currently, available CTC isolation approaches, including immunoaffinity and size-based filtration, have focused on high capture efficiency but with lower purity and often long and manual sample preparation, which limits the use of captured CTCs for downstream analyses. Here, we describe the use of the microfluidic Vortex Chip for size-based isolation of CTCs from 22 patients with advanced prostate cancer and, from an enumeration study on 18 of these patients, find that we can capture CTCs with high purity (from 1.74 to 37.59%) and efficiency (from 1.88 to 93.75 CTCs/7.5 mL) in less than 1 h. Interestingly, more atypical large circulating cells were identified in five age-matched healthy donors (46-77 years old; 1.25-2.50 CTCs/7.5 mL) than in five healthy donors <30 years old (21-27 years old; 0.00 CTC/7.5 mL). Using a threshold calculated from the five age-matched healthy donors (3.37 CTCs/mL), we identified CTCs in 80% of the prostate cancer patients. We also found that a fraction of the cells collected (11.5%) did not express epithelial prostate markers (cytokeratin and/or prostate-specific antigen) and that some instead expressed markers of epithelial-mesenchymal transition, i.e., vimentin and N-cadherin. We also show that the purity and DNA yield of isolated cells is amenable to targeted amplification and next-generation sequencing, without whole genome amplification, identifying unique mutations in 10 of 15 samples and 0 of 4 healthy samples.

Label-free enumeration, collection and downstream cytological and cytogenetic analysis of circulating tumor cells.

Circulating tumor cells (CTCs) have a great potential as indicators of metastatic disease that may help physicians improve cancer prognostication, treatment and patient outcomes. Heterogeneous marker expression as well as the complexity of current antibody-based isolation and analysis systems highlights the need for alternative methods. In this work, we use a microfluidic Vortex device that can selectively isolate potential tumor cells from blood independent of cell surface expression. This system was adapted to interface with three protein-marker-free analysis techniques: (i) an in-flow automated image processing system to enumerate cells released, (ii) cytological analysis using Papanicolaou (Pap) staining and (iii) fluorescence in situ hybridization (FISH) targeting the ALK rearrangement. In-flow counting enables a rapid assessment of the cancer-associated large circulating cells in a sample within minutes to determine whether standard downstream assays such as cytological and cytogenetic analyses that are more time consuming and costly are warranted. Using our platform integrated with these workflows, we analyzed 32 non-small cell lung cancer (NSCLC) and 22 breast cancer patient samples, yielding 60 to 100% of the cancer patients with a cell count over the healthy threshold, depending on the detection method used: respectively 77.8% for automated, 60-100% for cytology, and 80% for immunostaining based enumeration.