Deep Manifold Preserving Autoencoder for Classifying Breast Cancer Histopathological Images

Abstract

Classifying breast cancer histopathological images automatically is an important task in computer assisted pathology analysis. However, extracting informative and non-redundant features for histopathological image classification is challenging due to the appearance variability caused by the heterogeneity of the disease, the tissue preparation, and staining processes. In this paper, we propose a new feature extractor, called deep manifold preserving autoencoder, to learn discriminative features from unlabeled data. Then, we integrate the proposed feature extractor with a softmax classifier to classify breast cancer histopathology images. Specifically, it learns hierarchal features from unlabeled image patches by minimizing the distance between its input and output, and simultaneously preserving the geometric structure of the whole input data set. After the unsupervised training, we connect the encoder layers of the trained deep manifold preserving autoencoder with a softmax classifier to construct a cascade model and fine-tune this deep neural network with labeled training data. The proposed method learns discriminative features by preserving the structure of the input datasets from the manifold learning view and minimizing reconstruction error from the deep learning view from a large amount of unlabeled data. Extensive experiments on the public breast cancer dataset (BreaKHis) demonstrate the effectiveness of the proposed method.

Accurate diagnosis of colorectal cancer based on histopathology images using artificial intelligence

“…The performance of the new architectures on pathology images analysis and cancer diagnosis deserves more focused dedicated research for more detailed technical comparison. Moreover, we identify other techniques that may extend the current study, such as the semi- and unsupervised learning [ 49 , 50 ], which can learn from more WSIs with and without labels efficiently, and the multiscale decision aggregation and data augmentation [ 51 ], which can work in the presence of limited data. Given the highly accurate performance already achieved in the current approach presented, we can investigate if and how these new techniques might attain the current prediction performance with less data collection and labelling effort in future studies.…”

Deep Spatio-Temporal Representation and Ensemble Classification for Attention Deficit/Hyperactivity Disorder

“…In recent years, extracting features of unlabeled samples through autoencoder has achieved encouraging results with the rapid development of unsupervised learning [24], [25]. Therefore, 3D convolutional denoising autoencoder was used to extract the features of fMRI in this article.…”

Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy

“…In addition to a patch-level model, we also developed a model based on a convolutional auto-encoder that is capable of classifying the entire whole-slide image rather than independent patches, more closely aligning with how a human pathologist diagnoses a slide. Such models have shown success in other applications such as breast malignancy 27 , but to our knowledge this work is the first to apply them to whole-slide image classification in esophageal dysplasia. The whole-slide classification model based on a deep convolutional auto-encoder 5 was designed as a two-step clustering process in order to decrease the dimensionality of whole-slide images by extracting key features and preserving core information.…”