Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2023.08.01.551485

Deep Learning-Enabled, Detection of Rare Circulating Tumor Cell Clusters in Whole Blood Using Label-free, Flow Cytometry

Vora, N.·Shekhar, P.·Esmail, M.·Patra, A.·Georgakoudi, I.
View original source ↗Export metadata ↓

Abstract

Metastatic tumors have poor prognoses for progression-free and overall survival for all cancer patients. Rare circulating tumor cells (CTCs) and rarer circulating tumor cell clusters (CTCCs) are potential biomarkers of metastatic growth, with CTCCs representing an increased risk factor for metastasis. Current detection platforms are optimized for ex vivo detection of CTCs only. Microfluidic chips and size exclusion methods have been proposed for CTCC detection; however, they lack in vivo utility and real-time monitoring capability. Confocal backscatter and fluorescence flow cytometry (BSFC) has been used for label-free detection of CTCCs in whole blood based on machine learning (ML) enabled peak classification. Here, we expand to a deep-learning (DL) -based, peak detection and classification model to detect CTCCs in whole blood data. We demonstrate that DL-based BSFC has a low false alarm rate of 0.78 events/min with a high Pearson correlation coefficient of 0.943 between detected events and expected events. DL-based BSFC of whole blood maintains a detection purity of 72% and a sensitivity of 35.3% for both homotypic and heterotypic CTCCs starting at a minimum size of two cells. We also demonstrate through artificial spiking studies that DL-based BSFC is sensitive to changes in the number of CTCCs present in the samples and does not add variability in detection beyond the expected variability from Poisson statistics. The performance established by DL-based BSFC motivates its use for in vivo detection of CTCCs. Further developments of label-free BSFC to enhance throughput could lead to critical applications in the clinical detection of CTCCs and ex vivo isolation of CTCC from whole blood with minimal disruption and processing steps.

Source connections

Explore related subjects

bioengineeringPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Vora, N., Shekhar, P., Esmail, M., Patra, A., Georgakoudi, I.. 2023-08-03. Deep Learning-Enabled, Detection of Rare Circulating Tumor Cell Clusters in Whole Blood Using Label-free, Flow Cytometry. https://doi.org/10.1101/2023.08.01.551485

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Engineered microvessel networks -- Longitudinal transcriptomic profiling validates chip-grown tissues as a robust model for studying vasculature

Vascularised Organ-on-Chip (OoC) models are promising New Approach Methodologies (NAMs), but their translation requires validation for defined Contexts of Use (CoU). Here, we combine microfluidic microvessel networks (MVNs) with longitudinal bulk and single-cell RNA sequencing to determine how cell provenance influences engineered vascular phenotype. Stromal cell identity produced distinct network architectures and transcriptional trajectories, demonstrating that support cells, commonly treated as interchangeable, represent an important CoU variable. Primary human pancreatic microvascular endothelial cells failed to form stable perfusable networks, but supplementation with 10% Human Umbilical Vein Endothelial Cells (HUVECs) or Blood Outgrowth Endothelial Cells (BOECs) rescued self-assembly. Single-cell transcriptomics identified specialised endothelial populations associated with vascular morphogenesis, including tip, stalk, phalanx, endothelial to mesenchymal transition (EndMT) and pericyte-like endothelial cells. Failed networks lacked coherent endothelial specialisation, whereas rescued networks restored stabilising cell states and revealed FLRT2--UNC5B signalling within pericyte-like HUVECs, recapitulating a pathway implicated in angiogenic development in vivo. These findings establish cell provenance as a critical determinant of microvascular NAM performance and demonstrate how transcriptomic validation can define and strengthen the biological relevance of microvessel-on-chip models for specific CoUs.

bioengineering↗
bioRxiv2026

Benchmarking foundation models for resting-state functional magnetic resonance imaging time series in cognitive aging research

Foundation models trained on large neuroimaging datasets could help smaller studies investigate cognition from brain recordings. However, whether the foundation model-derived representations improve assessment of current cognition, prediction of follow-up cognition, or characterization of cognitive change remains unclear. We evaluated nine configurations from five model families that process regional resting-state functional magnetic resonance imaging time series, using 3,103 scans from 1,653 participants across two observational and five intervention aging cohorts. Primary frozen representations showed no consistent superiority over conventional functional connectivity for concurrent cognitive associations or diagnostic classification. Changing the readout improved selected concurrent cognitive associations without updating model weights, indicating that performance depended partly on how representations were extracted. Additional post-training and embedding alignment yielded gains in selected settings but did not consistently improve performance across outcomes. In the primary longitudinal analyses, imaging representations did not establish added value beyond baseline clinical measures. These findings show that readout choice influences concurrent cognitive associations, while the added value of these representations for longitudinal outcomes remains unestablished.

bioengineering↗
bioRxiv2026

PROST: An Open Toolbox, Harmonised Multi-Lab Dataset, and Meta-Analysis of Ankle-Foot Roll-Over Shape

The ankle-foot roll-over shape (ROS) is the sagittal-plane path of the centre of pressure (CoP) during the stance phase of walking, expressed in a shank-based coordinate system. It describes the effective rocker geometry that emerges from both the shape and the elastic deformation of the ankle-foot system during walking, and informs prosthetic and orthotic design. Previous studies characterised ROS in small samples with differing laboratory protocols, so they have not systematically assessed inter-individual variability or its relation to anthropometrics. We developed the open-source Public ROS Toolbox (PROST) for standardised ROS computation, and used it to harmonise marker trajectories, ground reaction forces and CoP data from four public gait datasets collected in independent laboratories. For each leg, we fitted a circular arc to the pooled ROS of all its stance phases. In a one-stage individual-participant data meta-analysis, linear mixed-effects models, with dataset as a fixed effect and participant as a random intercept, related the arc radius and the horizontal coordinate of the circle centre to anthropometrics, and, in the two self-selected-speed datasets, to walking speed. The harmonised dataset comprises 249 participants and 5,667 stance phases at walking speeds of 0.7-8.5 km/h. Circular arcs fitted the ROS closely (mean RMS radial residual 1.9 mm). The radius had a median of 410.3 mm (interquartile range, IQR, 237.6 mm), and the circle centre lay posterior to the ankle (median -20.6 mm, IQR 49.5 mm). Between-participant differences, quantified by the intraclass correlation coefficient (ICC), accounted for 42% of the variance in log radius (95% CI 25-57%) and 47% of the variance in the horizontal coordinate of the circle centre (95% CI 24-65%). Anthropometrics explained a negligible share of this variance (radius: pseudo-R2 -0.001, 95% CI -0.03 to 0.12), and height normalisation did not reduce radius variability (robust coefficient of variation 43% with and without normalisation). Faster self-selected walking was associated with a larger radius and a more posterior circle centre. To our knowledge, this study provides the first harmonised multi-lab ROS dataset. Together with the open-source toolbox, it is publicly available to support reproducible research in gait biomechanics, rehabilitation device design and clinical gait assessment. ROS geometry was participant-specific but was not predicted by age, sex, height or mass. A device ROS scaled from anthropometrics is therefore unlikely to match an individual's ROS, motivating studies of whether matching it, through device geometry and stiffness, improves gait mechanics.

bioengineering↗