Precisely Enumerating Circulating Tumor Cells Utilizing a Multi-Functional Microfluidic Chip and Unique Image Interpretation Algorithm

Circulating Tumor Cell Identification Based on Deep Learning

As a major reason for tumor metastasis, circulating tumor cell (CTC) is one of the critical biomarkers for cancer diagnosis and prognosis. On the one hand, CTC count is closely related to the prognosis of tumor patients; on the other hand, as a simple blood test with the advantages of safety, low cost and repeatability, CTC test has an important reference value in determining clinical results and studying the mechanism of drug resistance. However, the determination of CTC usually requires a big effort from pathologist and is also error-prone due to inexperience and fatigue. In this study, we developed a novel convolutional neural network (CNN) method to automatically detect CTCs in patients’ peripheral blood based on immunofluorescence in situ hybridization (imFISH) images. We collected the peripheral blood of 776 patients from Chifeng Municipal Hospital in China, and then used Cyttel to delete leukocytes and enrich CTCs. CTCs were identified by imFISH with CD45+, DAPI+ immunofluorescence staining and chromosome 8 centromeric probe (CEP8+). The sensitivity and specificity based on traditional CNN prediction were 95.3% and 91.7% respectively, and the sensitivity and specificity based on transfer learning were 97.2% and 94.0% respectively. The traditional CNN model and transfer learning method introduced in this paper can detect CTCs with high sensitivity, which has a certain clinical reference value for judging prognosis and diagnosing metastasis.

ALICE: a hybrid AI paradigm with enhanced connectivity and cybersecurity for a serendipitous encounter with circulating hybrid cells

A fully automated and accurate assay of rare cell phenotypes in densely-packed fluorescently-labeled liquid biopsy images remains elusive. Methods: Employing a hybrid artificial intelligence (AI) paradigm that combines traditional rule-based morphological manipulations with modern statistical machine learning, we deployed a next generation software, ALICE (Automated Liquid Biopsy Cell Enumerator) to identify and enumerate minute amounts of tumor cell phenotypes bestrewed in massive populations of leukocytes. As a code designed for futurity, ALICE is armed with internet of things (IOT) connectivity to promote pedagogy and continuing education and also, an advanced cybersecurity system to safeguard against digital attacks from malicious data tampering. Results: By combining robust principal component analysis, random forest classifier and cubic support vector machine, ALICE was able to detect synthetic, anomalous and tampered input images with an average recall and precision of 0.840 and 0.752, respectively. In terms of phenotyping enumeration, ALICE was able to enumerate various circulating tumor cell (CTC) phenotypes with a reliability ranging from 0.725 (substantial agreement) to 0.961 (almost perfect) as compared to human analysts. Further, two subpopulations of circulating hybrid cells (CHCs) were serendipitously discovered and labeled as CHC-1 (DAPI+/CD45+/E-cadherin+/vimentin-) and CHC-2 (DAPI+ /CD45+/E-cadherin+/vimentin+) in the peripheral blood of pancreatic cancer patients. CHC-1 was found to correlate with nodal staging and was able to classify lymph node metastasis with a sensitivity of 0.615 (95% CI: 0.374-0.898) and specificity of 1.000 (95% CI: 1.000-1.000). Conclusion: This study presented a machine-learning-augmented rule-based hybrid AI algorithm with enhanced cybersecurity and connectivity for the automatic and flexibly-adapting enumeration of cellular liquid biopsies. ALICE has the potential to be used in a clinical setting for an accurate and reliable enumeration of CTC phenotypes.

A New Method for CTC Images Recognition Based on Machine Learning

Circulating tumor cells (CTCs) derived from primary tumors and/or metastatic tumors are markers for tumor prognosis, and can also be used to monitor therapeutic efficacy and tumor recurrence. Circulating tumor cells enrichment and screening can be automated, but the final counting of CTCs currently requires manual intervention. This not only requires the participation of experienced pathologists, but also easily causes artificial misjudgment. Medical image recognition based on machine learning can effectively reduce the workload and improve the level of automation. So, we use machine learning to identify CTCs. First, we collected the CTC test results of 600 patients. After immunofluorescence staining, each picture presented a positive CTC cell nucleus and several negative controls. The images of CTCs were then segmented by image denoising, image filtering, edge detection, image expansion and contraction techniques using python’s openCV scheme. Subsequently, traditional image recognition methods and machine learning were used to identify CTCs. Machine learning algorithms are implemented using convolutional neural network deep learning networks for training. We took 2300 cells from 600 patients for training and testing. About 1300 cells were used for training and the others were used for testing. The sensitivity and specificity of recognition reached 90.3 and 91.3%, respectively. We will further revise our models, hoping to achieve a higher sensitivity and specificity.

Detection of HER2+ Breast Cancer Cells using Bioinspired DNA-Based Signal Amplification

Circulating tumor cells (CTC) are promising biomarkers for metastatic cancer detection and monitoring progression. However, detection of CTCs remains challenging due to their low frequency and heterogeneity. Herein, we report a bioinspired approach to detect individual cancer cells, based on a signal amplification cascade using a programmable DNA hybridization chain reaction (HCR) circuit. We applied this approach to detect HER2⁺ cancer cells using the anti‐HER2 antibody (trastuzumab) coupled to initiator DNA eliciting a HCR cascade that leads to a fluorescent signal at the cell surface. At 4 °C, this HCR detection scheme resulted in highly efficient, specific and sensitive signal amplification of the DNA hairpins specifically on the membrane of the HER2⁺ cells in a background of HER2⁻ cells and peripheral blood leukocytes, which remained almost non‐fluorescent. The results indicate that this system offers a new strategy that may be further developed toward an in vitro diagnostic platform for the sensitive and efficient detection of CTC.

Metastasis-on-a-chip mimicking the progression of kidney cancer in the liver for predicting treatment efficacy

Metastasis is one of the most important factors that lead to poor prognosis in cancer patients, and effective suppression of the growth of primary cancer cells in a metastatic site is paramount in averting cancer progression. However, there is a lack of biomimetic three-dimensional (3D) in vitro models that can closely mimic the continuous growth of metastatic cancer cells in an organ-specific extracellular microenvironment (ECM) for assessing effective therapeutic strategies. Methods: In this metastatic tumor progression model, kidney cancer cells (Caki-1) and hepatocytes (i.e., HepLL cells) were co-cultured at an increasing ratio from 1:9 to 9:1 in a decellularized liver matrix (DLM)/gelatin methacryloyl (GelMA)-based biomimetic liver microtissue in a microfluidic device. Results:Via this model, we successfully demonstrated a linear anti-cancer relationship between the concentration of anti-cancer drug 5-Fluorouracil (5-FU) and the percentage of Caki-1 cells in the co-culture system (R2 = 0.89). Furthermore, the Poly(lactide-co-glycolide) (PLGA)-poly(ethylene glycol) (PEG)-based delivery system showed superior efficacy to free 5-FU in killing Caki-1 cells. Conclusions: In this study, we present a novel 3D metastasis-on-a-chip model mimicking the progression of kidney cancer cells metastasized to the liver for predicting treatment efficacy. Taken together, our study proved that the tumor progression model based on metastasis-on-a-chip with organ-specific ECM would provide a valuable tool for rapidly assessing treatment regimens and developing new chemotherapeutic agents.

A high-throughput liquid biopsy for rapid rare cell separation from large-volume samples

Liquid biopsy techniques for rare tumor cell separation from body fluids have shown enormous promise in cancer detection and prognosis monitoring. This work established a high-throughput liquid biopsy platform with a high recovery rate and a high cell viability based on a previously reported 2.5D micropore-arrayed filtration membrane. Thanks to its high porosity (>40.2%, edge-to-edge space between the adjacent micropores <4 μm), the achieved filtration throughputs can reach >110 mL min-1 for aqueous samples and >17 mL min-1 for undiluted whole blood, only driven by gravity with no need for any extra pressure loading. The recoveries of rare lung tumor cells (A549s) spiked in PBS (10 mL), unprocessed BALF (10 mL) and whole blood (5 mL) show high recovery rates (88.0 ± 3.7%, 86.0 ± 5.3% and 83.2 ± 6.2%, respectively, n = 5 for every trial) and prove the high performance of this platform. Successful detection of circulating tumor cells (CTCs) from whole blood samples (5 mL) of lung cancer patients (n = 5) was demonstrated. In addition, it was both numerically and experimentally proved that a small edge-to-edge space was significant to improve the viability of the recovered cells and the purity of the target cell recovery, which was reported for the first time to the best of the authors' knowledge. This high-throughput technique will expand the detecting targets of liquid biopsy from the presently focused CTCs in whole blood to the exfoliated tumor cells (ETCs) in other large-volume clinical samples, such as BALF, urine and pleural fluid. Meanwhile, the technique is easy to operate and ready for integration with other separation and analysis tools to fulfill a powerful system for practical clinical applications of liquid biopsy.