Convolutional neural networks that teach microscopes how to image
This work addresses the challenge of improving microscope imaging for medical diagnostics, representing a novel integration of optical design with deep learning rather than an incremental improvement.
The researchers tackled the problem of imaging transparent biological samples by using a CNN to jointly optimize microscope illumination and image classification, achieving a 5-10% higher accuracy in identifying malaria-infected cells compared to standard methods.
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.