Extracting Time-Frequency Features of Images for Robust LSTM-based
Classification of H&E Stained Tissue
Abstract
The importance of automated classification of histopathological images
has been increasingly recognized for effective processing of large
volumes of data in the era of digital pathology for new discovery of
disease mechanism. This paper presents a deep-learning approach that
extracts time-frequency features of H&E stained tissue images for
classification by long short-term memory networks. Using two large
public databases of colorectal-cancer and heart-failure H&E stained
tissue images, the proposed approach outperforms several
state-of-the-art benchmark classification methods, including support
vector machines and convolutional neural networks in terms of several
statistical measures.