Increasing a microscope's effective field of view via overlapped imaging and machine learning.

Journal Article (Journal Article)

This work demonstrates a multi-lens microscopic imaging system that overlaps multiple independent fields of view on a single sensor for high-efficiency automated specimen analysis. Automatic detection, classification and counting of various morphological features of interest is now a crucial component of both biomedical research and disease diagnosis. While convolutional neural networks (CNNs) have dramatically improved the accuracy of counting cells and sub-cellular features from acquired digital image data, the overall throughput is still typically hindered by the limited space-bandwidth product (SBP) of conventional microscopes. Here, we show both in simulation and experiment that overlapped imaging and co-designed analysis software can achieve accurate detection of diagnostically-relevant features for several applications, including counting of white blood cells and the malaria parasite, leading to multi-fold increase in detection and processing throughput with minimal reduction in accuracy.

Full Text

Duke Authors

Cited Authors

  • Yao, X; Pathak, V; Xi, H; Chaware, A; Cooke, C; Kim, K; Xu, S; Li, Y; Dunn, T; Chandra Konda, P; Zhou, KC; Horstmeyer, R

Published Date

  • January 2022

Published In

Volume / Issue

  • 30 / 2

Start / End Page

  • 1745 - 1761

PubMed ID

  • 35209329

Pubmed Central ID

  • PMC8970696

Electronic International Standard Serial Number (EISSN)

  • 1094-4087

International Standard Serial Number (ISSN)

  • 1094-4087

Digital Object Identifier (DOI)

  • 10.1364/oe.445001

Language

  • eng