SLADS-Net: Supervised Learning Approach for Dynamic Sampling using Deep Neural Networks

TL;DR

SLADS-Net introduces a deep neural network-based supervised learning method for dynamic sparse sampling in microscopy, enabling effective image acquisition with minimal prior similar data.

Contribution

The paper presents SLADS-Net, a novel deep learning approach for dynamic sampling that performs well even without similar training images, and discusses a pre-trained model for practical use.

Findings

Deep neural networks outperform other training methods in diverse image content scenarios.

SLADS-Net achieves efficient sampling with less training data.

Pre-trained SLADS-Net enables immediate application without additional training.

Abstract

In scanning microscopy based imaging techniques, there is a need to develop novel data acquisition schemes that can reduce the time for data acquisition and minimize sample exposure to the probing radiation. Sparse sampling schemes are ideally suited for such applications where the images can be reconstructed from a sparse set of measurements. In particular, dynamic sparse sampling based on supervised learning has shown promising results for practical applications. However, a particular drawback of such methods is that it requires training image sets with similar information content which may not always be available. In this paper, we introduce a Supervised Learning Approach for Dynamic Sampling (SLADS) algorithm that uses a deep neural network based training approach. We call this algorithm SLADS- Net. We have performed simulated experiments for dynamic sampling using SLADS-Net in which the training images either have similar information content or completely different information content, when compared to the testing images. We compare the performance across various methods for training such as least- squares, support vector regression and deep neural networks. From these results we observe that deep neural network based training results in superior performance when the training and testing images are not similar. We also discuss the development of a pre-trained SLADS-Net that uses generic images for training. Here, the neural network parameters are pre-trained so that users can directly apply SLADS-Net for imaging experiments.