Skip to main content
Journal cover image

Learned sensing: jointly optimized microscope hardware for accurate image classification.

Publication ,  Journal Article
Muthumbi, A; Chaware, A; Kim, K; Zhou, KC; Konda, PC; Chen, R; Judkewitz, B; Erdmann, A; Kappes, B; Horstmeyer, R
Published in: Biomedical optics express
December 2019

Since its invention, the microscope has been optimized for interpretation by a human observer. With the recent development of deep learning algorithms for automated image analysis, there is now a clear need to re-design the microscope's hardware for specific interpretation tasks. To increase the speed and accuracy of automated image classification, this work presents a method to co-optimize how a sample is illuminated in a microscope, along with a pipeline to automatically classify the resulting image, using a deep neural network. By adding a "physical layer" to a deep classification network, we are able to jointly optimize for specific illumination patterns that highlight the most important sample features for the particular learning task at hand, which may not be obvious under standard illumination. We demonstrate how our learned sensing approach for illumination design can automatically identify malaria-infected cells with up to 5-10% greater accuracy than standard and alternative microscope lighting designs. We show that this joint hardware-software design procedure generalizes to offer accurate diagnoses for two different blood smear types, and experimentally show how our new procedure can translate across different experimental setups while maintaining high accuracy.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Biomedical optics express

DOI

EISSN

2156-7085

ISSN

2156-7085

Publication Date

December 2019

Volume

10

Issue

12

Start / End Page

6351 / 6369

Related Subject Headings

  • 5102 Atomic, molecular and optical physics
  • 4003 Biomedical engineering
  • 3212 Ophthalmology and optometry
  • 0912 Materials Engineering
  • 0205 Optical Physics
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Muthumbi, A., Chaware, A., Kim, K., Zhou, K. C., Konda, P. C., Chen, R., … Horstmeyer, R. (2019). Learned sensing: jointly optimized microscope hardware for accurate image classification. Biomedical Optics Express, 10(12), 6351–6369. https://doi.org/10.1364/boe.10.006351
Muthumbi, Alex, Amey Chaware, Kanghyun Kim, Kevin C. Zhou, Pavan Chandra Konda, Richard Chen, Benjamin Judkewitz, Andreas Erdmann, Barbara Kappes, and Roarke Horstmeyer. “Learned sensing: jointly optimized microscope hardware for accurate image classification.Biomedical Optics Express 10, no. 12 (December 2019): 6351–69. https://doi.org/10.1364/boe.10.006351.
Muthumbi A, Chaware A, Kim K, Zhou KC, Konda PC, Chen R, et al. Learned sensing: jointly optimized microscope hardware for accurate image classification. Biomedical optics express. 2019 Dec;10(12):6351–69.
Muthumbi, Alex, et al. “Learned sensing: jointly optimized microscope hardware for accurate image classification.Biomedical Optics Express, vol. 10, no. 12, Dec. 2019, pp. 6351–69. Epmc, doi:10.1364/boe.10.006351.
Muthumbi A, Chaware A, Kim K, Zhou KC, Konda PC, Chen R, Judkewitz B, Erdmann A, Kappes B, Horstmeyer R. Learned sensing: jointly optimized microscope hardware for accurate image classification. Biomedical optics express. 2019 Dec;10(12):6351–6369.
Journal cover image

Published In

Biomedical optics express

DOI

EISSN

2156-7085

ISSN

2156-7085

Publication Date

December 2019

Volume

10

Issue

12

Start / End Page

6351 / 6369

Related Subject Headings

  • 5102 Atomic, molecular and optical physics
  • 4003 Biomedical engineering
  • 3212 Ophthalmology and optometry
  • 0912 Materials Engineering
  • 0205 Optical Physics