Skip to Content

Machine learning enabled cell imaging

Red Blood Cells (RBCs) are the most abundant cell type in blood, with their primary function being the transport of oxygen throughout the body. RBCs extracted from donors diagnosed with pathological diseases tend to exhibit morphological abnormalities, which can be measured and characterized. The goal of this project is to develop an unconventional imaging platform for the reliable and rapid fingerprinting of pathological diseases by monitoring the shape, size and morphological changes occurring in RBCs. Our unique approach relies upon the combination of high-throughput live cell imaging with high resolution scanning electron microscopy and scanning probe microscopy methodologies. The data obtained from these state-of-the-art techniques will be collected and analyzed using Machine Learning (ML) algorithms. ML-based data analytics will provide an automated and more standardized approach for RBC classification in health and blood related diseases, with the goal of supporting clinicians in improving early detection, prognosis and the development of more effective treatment strategies. This project strives for the realization of digital pathology and its implementation in the advancements of precision medicine.

(a) Schematic of the 3D Cell Explorer (Nanolive SA), a holo-tomographic microscopy tool for quantitative, non-invasive and label-free 3D live cell imaging. (b) Refractive index-based image of RBCs from a healthy donor - left - and 3D reconstruction of a single RBC - right. (c) Overview of RBCs morphological classification. (d) Schematic of neural network for RBC classification.


Transport at Nanoscale Interfaces Laboratory

Contact us

Quick Access

The latest EmpaQuarterly:
Focus: Energy revolution