Self-Supervised Similarity Learning for Digital Pathology

Abstract

Using features extracted from networks pretrained on ImageNet is a common practice in applications of deep learning for digital pathology. However it presents the downside of missing domain specific image information. In digital pathology, supervised training data is expensive and difficult to collect. We propose a self-supervised method for feature extraction by similarity learning on whole slide images (WSI) that is simple to implement and allows creation of robust and compact image descriptors. We train a siamese network, exploiting image spatial continuity and assuming spatially adjacent tiles in the image are more similar to each other than distant tiles. Our network outputs feature vectors of length 128, which allows dramatically lower memory storage and faster processing than networks pretrained on ImageNet. We apply the method on digital pathology WSIs from the Camelyon16 train set and assess and compare our method by measuring image retrieval of tumor tiles and descriptor pair distance ratio for distant/near tiles in the Camelyon16 test set. We show that our method yields better retrieval task results than existing ImageNet based and generic self-supervised feature extraction methods. To the best of our knowledge, this is also the first published method for self-supervised learning tailored for digital pathology.

References in corpus (7)

• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Deep Learning for Identifying Metastatic Breast Cancer
• Deep Learning is Robust to Massive Label Noise
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Terabyte-scale Deep Multiple Instance Learning for Classification and Localization in Pathology
• Cell Detection in Microscopy Images with Deep Convolutional Neural Network and Compressed Sensing
• Generalizing multistain immunohistochemistry tissue segmentation using one-shot color deconvolution deep neural networks

Cited by in corpus (8)

• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• A Review of Predictive and Contrastive Self-supervised Learning for Medical Images
• Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities
• Performance of externally validated machine learning models based on histopathology images for the diagnosis, classification, prognosis, or treatment outcome prediction in female breast cancer: A systematic review
• Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers
• Self-supervised Tumor Segmentation through Layer Decomposition
• Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI
• Self-similarity Student for Partial Label Histopathology Image Segmentation