Skip to main content

Convolutional neural networks that teach microscopes how to image

Publication ,  Journal Article
Horstmeyer, R; Chen, RY; Kappes, B; Judkewitz, B
September 21, 2017

Deep learning algorithms offer a powerful means to automatically analyze the content of medical images. However, many biological samples of interest are primarily transparent to visible light and contain features that are difficult to resolve with a standard optical microscope. Here, we use a convolutional neural network (CNN) not only to classify images, but also to optimize the physical layout of the imaging device itself. We increase the classification accuracy of a microscope's recorded images by merging an optical model of image formation into the pipeline of a CNN. The resulting network simultaneously determines an ideal illumination arrangement to highlight important sample features during image acquisition, along with a set of convolutional weights to classify the detected images post-capture. We demonstrate our joint optimization technique with an experimental microscope configuration that automatically identifies malaria-infected cells with 5-10% higher accuracy than standard and alternative microscope lighting designs.

Duke Scholars

Publication Date

September 21, 2017
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Horstmeyer, R., Chen, R. Y., Kappes, B., & Judkewitz, B. (2017). Convolutional neural networks that teach microscopes how to image.
Horstmeyer, Roarke, Richard Y. Chen, Barbara Kappes, and Benjamin Judkewitz. “Convolutional neural networks that teach microscopes how to image,” September 21, 2017.
Horstmeyer R, Chen RY, Kappes B, Judkewitz B. Convolutional neural networks that teach microscopes how to image. 2017 Sep 21;
Horstmeyer R, Chen RY, Kappes B, Judkewitz B. Convolutional neural networks that teach microscopes how to image. 2017 Sep 21;

Publication Date

September 21, 2017