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

Abstract

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.

Relevance of circulating hybrid cells as a non-invasive biomarker for myriad solid tumors

“…In patients with pancreatic cancer, CHCs significantly outnumbered CTCs at every stage of disease, with levels capable of providing a prognostic indicator for overall survival 14 . Further, detection of CHCs with ECAD expression correlates with PDAC nodal staging 21 , indicating subpopulations of CHCs with differential protein expression may provide a predictive biomarker. However, as a newly defined population, the functional tumor-initiating capacity and expression of stem cell attributes of CHCs is unexplored.…”

An algorithm-assisted automated identification and enumeration system for sensitive hydrogen sulfide sensing under dark field microscopy

“…Then, excess sulfuric acid was added to the tube. Owing to the low pH value, almost all sulfides form H 2 S molecules rather than HS − or S. 2–49 The low solubility made the H 2 S molecule volatilize and come into contact with AuNPs-N 3 -Alk and further reduced the azido group to an amino group, which has been proven by many works. 50–53 Therefore, the cuprous-catalysed click chemistry reaction was blocked, resulting in single AuNPs in the solution.…”

“…With the rapid development of artificial intelligence technology, intelligence algorithms for image processing have caught many researchers' eyes owing to their high throughput, high accuracy, and time savings for characteristic information extraction in a picture. To date, intelligence algorithms have been employed for identifying and gathering feature information in photographs of mass spectrometry imaging, 36,37 electron microscopy, 38,39 fluorescence microscopy, 40,41 Raman imaging, 42 and DFM. 25,43 Particularly for DFM detection, an intelligence algorithm is helpful for improving the counting accuracy in image processing and data collection.…”

Label-free enrichment of rare unconventional circulating neoplastic cells using a microfluidic dielectrophoretic sorting device

“…CHCs are described as having hybrid phenotypes of a neoplastic cell and a leukocyte with dual expression of CD45 and tumor markers such as EpCAM or CK [10], [13], [14]. In PDAC patients, CHCs have shown better prognostic value than CTCs as their enumeration correlated with stage and survival [15]. While CHCs are more abundant, their physical and phenotypic similarity to PBMCs makes their isolation and analysis a challenge [8], [16]- [20].…”