Search

We study a problem scenario of super-resolution (SR) algorithms in the context of whole slide imaging (WSI), a popular imaging modality in digital pathology. Instead of just one pair of high- and low-resolution images, which is typically the setup in which SR algorithms are designed, we are given multiple intermediate resolutions of the same image as well. The question remains how to best utilize such data to make the transformation learning problem inherent to SR more tractable and address the unique challenges that arises in this biomedical application. We propose a recurrent convolutional neural network model, to generate SR images from such multi-resolution WSI datasets. Specifically, we show that having such intermediate resolutions is highly effective in making the learning problem easily trainable and address large resolution difference in the low and high-resolution images common in WSI, even without the availability of a large size training data. Experimental results show state-of-the-art performance on three WSI histopathology cancer datasets, across a number of metrics.

Modern optical imaging has progressed rapidly with the ability to noninvasively image cellular and subcellular phenomena with high spatial and temporal resolution. In particular, emerging techniques such as second harmonic generation (SHG) microscopy can allow for the monitoring of intrinsic contrast, such as that from collagen, in live and fixed samples. When coupled with multiphoton fluorescence microscopy, SHG can be used to image interactions between cells and the surrounding extracellular environment. There is recent interest in using these approaches to study inflammation and wound healing in zebrafish, an important model for studying these processes. In this chapter we present the practical aspects of using second harmonic generation to image interactions between leukocytes and collagen during wound healing in zebrafish., (Copyright © 2016 Elsevier Inc. All rights reserved.)