Tumor diagnostics with a combination of machine learning and biochip
October 2020
University of California Irvine, Irvine, USA
Performing single-cell analysis is essential to identify and classify cancer cell types and study cellular heterogeneity. This study combines powerful machine learning techniques with easily accessible inkjet printing and microfluidics technology and integrates a nanoparticle-printed biochip for single-cell analysis. The biochip is simple to prototype, miniaturized and cost-effective, potentially capable of differentiating between a variety of cell types in a label-free manner. Feature classifiers are established and their performance metrics are evaluated. The biochip’s ability to discriminate noncancerous cells from cancerous cells at the single-cell level and to classify cancer sub-type cells is demonstrated. It is envisioned that such a chip has potential applications in single-cell studies, tumour heterogeneity studies, and perhaps in point-of-care cancer diagnostics.
A machine learning-assisted nanoparticle-printed biochip for real-time single cancer cell analysis
Rahim Esfandyarpour
Added on: 11-11-2020
[1] https://onlinelibrary.wiley.com/doi/pdf/10.1002/adbi.202000160[2] https://www.technologynetworks.com/informatics/news/biochip-innovation-combines-ai-and-nanoparticles-to-analyze-tumors-341387
