An ML-integrated approach that incorporates a convolutional neural network that was trained to distinguish CTC peaks from artifacts by analyzing peak amplitude and temporal shape characteristics improves DiFC CTC enumeration, enabling robustness against artifacts in noisy conditions.
Abstract
Abstract. Significance Diffuse in vivo flow cytometry (DiFC) is an emerging technique for enumerating rare, fluorescently labeled circulating tumor cells (CTCs) in small animals without drawing blood samples. DiFC uses detection of transient fluorescent peaks in time-series data. Previously, we used a simple amplitude threshold-based method for identifying peak candidates, but this ignored potentially useful information in peak shape that could reduce false-positive detections and increase detection efficiency of lower-amplitude peaks. Aim Our aim is to develop a machine learning (ML)-integrated signal processing approach for DiFC that improves CTC enumeration by better discriminating CTC peaks from artifacts. Approach We developed an ML-integrated approach that incorporates a convolutional neural network (CNN) classifier. The CNN was trained to distinguish CTC peaks from artifacts by analyzing peak amplitude and temporal shape characteristics. Performance was evaluated on in silico, control, and CTC-bearing mouse datasets. Results The CNN classifier achieved accuracy, precision, sensitivity, and specificity exceeding 94% on test data. Compared with our previously published threshold-based approach, the ML-integrated method increased the number of correctly identified CTCs and their flow direction while reducing false detections across evaluation datasets. Conclusions The ML-integrated approach substantially improves DiFC CTC enumeration, enabling robustness against artifacts in noisy conditions.
The detection of minimal residual disease (MRD) has emerged as a crucial biomarker for assessing therapeutic response and predicting prognosis. The U.S. FDA has recently emphasized the potential of MRD as a future clinical endpoint and biomarker. A study involving 126 AML patients demonstrated a strong correlatio...
Min-Ho Lee, Anna Go, Ye-Bin Jung· Clinical Chemistry· 0 citations
Summary Reliable non-invasive biomarkers are needed to optimize treatment selection and enable real-time monitoring of pancreatic cancer (PC). We developed a bead-calibrated, multiparametric flow cytometry (FC) protocol to detect, enumerate, and subtype circulating intact extracellular vesicles (EVs) in blood. Among 12...
Rosalba Florio, L. de Lellis, S. Veschi et al.· iScience· 0 citations
Circulating tumor cells (CTCs) and CTC clusters are promising liquid biopsy biomarkers for hepatocellular carcinoma (HCC). Evaluation of both enumeration and morphology remains an important challenge. Flow cytometry (FACS) enables high-throughput quantification and multiparametric analysis, whereas artificial int...
Juan Lyu, Takuto Nosaka, Hirotaka Nomiya et al.· BMC Cancer· 0 citations
BACKGROUND
Circulating tumor cells (CTCs), which detach from primary tumors and enter the peripheral blood, serve as biomarkers for monitoring a patient's status following cancer therapy.
METHODS
In this study, we developed a microfluidic platform integrating dielectrophoresis and image recognition for the capture an...
Background Circulating tumour cells (CTCs) are promising minimally invasive biomarkers of tumour dissemination and disease biology, but low abundance and phenotypic heterogeneity make them challenging to isolate, particularly in non-small cell lung cancer (NSCLC). Physical cell-selection approaches based on size and de...
Volga M. Saini, E. Oner, C. Cahill et al.· The journal of liquid biopsy· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.