Cancer Modeling-on-a-Chip with Future Artificial Intelligence Integration

Abstract

Cancer is one of the leading causes of death worldwide, despite the large efforts to improve the understanding of cancer biology and development of treatments. The attempts to improve cancer treatment are limited by the complexity of the local milieu in which cancer cells exist. The tumor microenvironment (TME) consists of a diverse population of tumor cells and stromal cells with immune constituents, microvasculature, extracellular matrix components, and gradients of oxygen, nutrients, and growth factors. The TME is not recapitulated in traditional models used in cancer investigation, limiting the translation of preliminary findings to clinical practice. Advances in 3D cell culture, tissue engineering, and microfluidics have led to the development of "cancer-on-a-chip" platforms that expand the ability to model the TME in vitro and allow for high-throughput analysis. The advances in the development of cancer-on-a-chip platforms, implications for drug development, challenges to leveraging this technology for improved cancer treatment, and future integration with artificial intelligence for improved predictive drug screening models are discussed.

Keywords: artificial intelligence; cancer models; chemotherapy; microfluidics; organ-on-a-chip.

Figure 1:

Photographs and simulation of the HepaChip. (A) Image of the chip, with 8 culture chambers, fluid inlet and outlet and gold electrodes. (B) Enlarge view of single chamber, with 2 electrodes and 3 assembly ridges. (C) Simulation of the flow and cell trajectory inside of the culture chamber. (D) Live/dead staining of BxPC3, growing on the assembly ridge. (E) Live/dead staining of PANC1, spread on well channel walls and bottom. (F) Mitosis of MxPC3, observed after 16h culture. Reproduced under the terms of the Creative Commons License. ^[15] 2017 Nature.

Figure 2:

Human Orthotopic Lung Cancer-on-a-Chip Model. (A) Schematic of a cross-section through the designed microfluidic chip. (B) Micrograph of a cross-section of the two central channels of the alveolus chip taken via fluorescence micrograph. (C) Immunofluorescence micrograph of a cluster of GFP labelled NSCLC cells, implanted in the airway chip. (D) Quantification of NSCLC densities after implantation in the chip. (E) Growth pattern of GFP labelled lung cancer cells within the epithelial monolayer. (F) Lung cancer cell growth dynamics. Reproduce with permission. ^[60] 2017 Elsevier.

Figure 3:

(A) General schematic of the immune-oncology chip, whose design features six reservoirs for cells loading and culture medium replacement and four compartments for cell culture. (B) Detailed view of the four chambers. (C) Picture of the whole device. (D-F) Trajectories of FPR1 CC cells, FPR1 CA cells, and FPR1 AA cells (respectively). Reproduced under the terms of the Creative Commons License. ^[66] 2017 Nature.

Figure 4:

Microtiter cancer-on-a-chip plate for anti-cancer breast cancer drug testing. (A) Photo of the OrganoPlate platform. (B-D) Closeup, top, and side view of an individual channel, respectively. (E) Photo demonstrating the filling of an ECM channel. (F) Epifluorescence microscopy images showing morphology and viability of MDA-MB-453 in Matrigel^®, BME2rgf and collagen I, under both static and perfusion conditions. (G) Quantification of the effect of ECM composition, seeding density, and perfusion or static conditions on cell viability. Reproduced under the terms of the Creative Commons License. ^[36] 2017 BioMed Central.

Figure 5:

(A) Photograph of the bottom of an OrganoPlate, showing 40 microfluidic channel networks and the top of a 384 well plate device. (B) Zoomed in photograph of a single microfluidic channel network, with three channels joining in the center. (C, D) Horizontal and vertical cross section. (E) 3D sketch of the chip, comprised of a tubule, an extracellular matrix gel, and a perfusion lane. Reproduced under the terms of the Creative Commons License. ^[89] 2017 Nature.