Label-free scattering snapshot classification for living cell identification

¹ Interdisciplinary Research Centre on Biomaterials (CRIB) and Dipartimento di Ingegneria Chimica, dei Materiali e della Produzione Industriale, University of Naples “Federico II”, 80125 Naples, Italy
² Center for Advanced Biomaterials for Healthcare@CRIB, Istituto Italiano di Tecnologia, 80125 Naples, Italy

^* Corresponding author: david.dannhauser@unina.it

Published online: 31 October 2024

Abstract

A scattering snapshot hold an enormous potential for cell class and state classification, allowing to avoid costly fluorescence labelling. Beside convolutional neural networks show outstanding image classification performance compared to other state-of-the-art methods, regarding accuracy and speed. Therefore, we combined the two techniques (Light Scattering and Deep Learning) to identify living cells with high precision. Neural Networks show high prediction performance for known classes but struggles when unknown classes need to be identified. In such a scenario no prior knowledge of the unknown cell class can be used for the model training, which inevitably results in a misclassification. To overcome the hurdle, of identifying unknown cell classes, we must first define an in-distribution of known snapshots to afterwards detect out of distribution snapshots as unknowns. Ones, such a new cell class is identified, we can retrain our cell classifier with the obtained knowledge, so we dynamically update the cell class database. We applied this measurement approach to scattering pattern snapshots of different classes of living cells. Our outcome shows a precise cell classification, which can be applied to a wide range of single cell classification approaches.