Label-free liquid biopsy through the identification of tumor cells by machine learning-powered tomographic phase imaging flow cytometry

Abstract

Image-based identification of circulating tumor cells in microfluidic cytometry condition is one of the most challenging perspectives in the Liquid Biopsy scenario. Here we show a machine learning-powered tomographic phase imaging flow cytometry system capable to provide high-throughput 3D phase-contrast tomograms of each single cell. In fact, we show that discrimination of tumor cells against white blood cells is potentially achievable with the aid of artificial intelligence in a label-free flow-cyto-tomography method. We propose a hierarchical machine learning decision-maker, working on a set of features calculated from the 3D tomograms of the cells’ refractive index. We prove that 3D morphological features are adequately distinctive to identify tumor cells versus the white blood cell background in the first stage and, moreover, in recognizing the tumor type at the second decision step. Proof-of-concept experiments are shown, in which two different tumor cell lines, namely neuroblastoma cancer cells and ovarian cancer cells, are used against monocytes. The reported results allow claiming the identification of tumor cells with a success rate higher than 97% and with an accuracy over 97% in discriminating between the two cancer cell types, thus opening in a near future the route to a new Liquid Biopsy tool for detecting and classifying circulating tumor cells in blood by stain-free method.

Predicting Neuroblastoma Patient Risk Groups, Outcomes, and Treatment Response Using Machine Learning Methods: A Review

“…Finally, single-cell and protein biology assayed by flow cytometry can also be linked to ML in NB. For example, a study found that using ML, it is possible to provide tomographic imaging and 3D phase-contrast tomograms on single NB cells separated by flow cytometry [ 66 ], a promising method for easier detection of NB.…”

Narrative review: precision medicine applications in neuroblastoma—current status and future prospects

“…A diagnostic concept known as “liquid biopsy” has emerged, primarily involving the detection of tumor fragments that have shed into the circulatory system through the analysis of body fluids such as blood and urine. These fragments can be identified and isolated from the blood using high-throughput methods, allowing for subsequent analysis at the single-cell level ( 115 , 116 ). Compared to traditional diagnostic techniques, liquid biopsy is an attractive non-invasive method for tracking disease progression in real time ( 117 , 118 ).…”

Screening for urothelial carcinoma cells in urine based on digital holographic flow cytometry through machine learning and deep learning methods

“…They were able to classify various drug-resistant cancer cells and differentiate cancer cells from monocytes. 42,43 Some researchers have employed digital holographic flow cytometry to image the urine samples, subsequently performing phase reconstruction of red blood cells, white blood cells, and crystals in urine. 44,45…”