Sparse autoencoder for unsupervised nucleus detection and representation in histopathology images

• Published in: Pattern recognition Vol. 86; pp. 188 - 200
• Main Authors: Hou, Le, Nguyen, Vu, Kanevsky, Ariel B., Samaras, Dimitris, Kurc, Tahsin M., Zhao, Tianhao, Gupta, Rajarsi R., Gao, Yi, Chen, Wenjin, Foran, David, Saltz, Joel H.
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.02.2019
• Subjects: Convolutional neural network; Pathology image analysis; Semi-supervised learning; Unsupervised learning; Pathology image analysis; Semi-supervised learning; Convolutional neural network; Unsupervised learning; pathology image analysis; semi-supervised learning; convolutional neural network; unsupervised learning
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2018.09.007

We propose a sparse Convolutional Autoencoder (CAE) for simultaneous nucleus detection and feature extraction in histopathology tissue images. Our CAE detects and encodes nuclei in image patches in tissue images into sparse feature maps that encode both the location and appearance of nuclei. A primary contribution of our work is the development of an unsupervised detection network by using the characteristics of histopathology image patches. The pretrained nucleus detection and feature extraction modules in our CAE can be fine-tuned for supervised learning in an end-to-end fashion. We evaluate our method on four datasets and achieve state-of-the-art results. In addition, we are able to achieve comparable performance with only 5% of the fully-supervised annotation cost.