Direct Image Classification from Fourier Ptychographic Microscopy Measurements without Reconstruction

TL;DR

This paper demonstrates that convolutional neural networks can classify Fourier Ptychographic Microscopy measurements directly, bypassing the computationally intensive image reconstruction step, leading to faster and more efficient cell classification.

Contribution

It introduces a novel approach of direct classification from FPM measurements using CNNs, eliminating the need for image reconstruction and reducing data acquisition time.

Findings

CNNs outperform single image classification by up to 12%

Direct measurement classification is more efficient than image reconstruction

Multiplexing raw measurements maintains accuracy while reducing data

Abstract

The computational imaging technique of Fourier Ptychographic Microscopy (FPM) enables high-resolution imaging with a wide field of view and can serve as an extremely valuable tool, e.g. in the classification of cells in medical applications. However, reconstructing a high-resolution image from tens or even hundreds of measurements is computationally expensive, particularly for a wide field of view. Therefore, in this paper, we investigate the idea of classifying the image content in the FPM measurements directly without performing a reconstruction step first. We show that Convolutional Neural Networks (CNN) can extract meaningful information from measurement sequences, significantly outperforming the classification on a single band-limited image (up to 12 %) while being significantly more efficient than a reconstruction of a high-resolution image. Furthermore, we demonstrate that a learned multiplexing of several raw measurements allows maintaining the classification accuracy while reducing the amount of data (and consequently also the acquisition time) significantly.