# Self-Supervised Similarity Learning for Digital Pathology

arXiv: https://arxiv.org/abs/1905.08139 · HTML: https://mlsanity.com/paper/1905.08139/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2019.

## Built on by (most cited first, 22 of 22)

- [Benchmarking Self-Supervised Learning on Diverse Pathology Datasets](https://mlsanity.com/paper/2212.04690/) (2022)
- [Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers](https://mlsanity.com/paper/2109.05819/) (2021)
- [Rotation-Agnostic Image Representation Learning for Digital Pathology](https://mlsanity.com/paper/2311.08359/) (2023)
- [Learning to Predict RNA Sequence Expressions from Whole Slide Images with Applications for Search and Classification](https://mlsanity.com/paper/2203.13997/) (2022)
- [Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications](https://mlsanity.com/paper/2112.05760/) (2021)
- [Resolution-Based Distillation for Efficient Histology Image Classification](https://mlsanity.com/paper/2101.04170/) (2021)
- [A Review of Predictive and Contrastive Self-supervised Learning for Medical Images](https://mlsanity.com/paper/2302.05043/) (2023)
- [Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection](https://mlsanity.com/paper/2108.09178/) (2021)
- [DPA-P2PNet: Deformable Proposal-aware P2PNet for Accurate Point-based Cell Detection](https://mlsanity.com/paper/2303.02602/) (2023)
- [EXAONEPath 1.0 Patch-level Foundation Model for Pathology](https://mlsanity.com/paper/2408.00380/) (2024)
- [Self-supervised Tumor Segmentation through Layer Decomposition](https://mlsanity.com/paper/2109.03230/) (2021)
- [Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI](https://mlsanity.com/paper/2401.17207/) (2024)
- [Multi-modal Masked Autoencoders Learn Compositional Histopathological Representations](https://mlsanity.com/paper/2209.01534/) (2022)
- [Pan-cancer Histopathology WSI Pre-training with Position-aware Masked Autoencoder](https://mlsanity.com/paper/2407.07504/) (2024)
- [Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations: a COVID-19 case-study](https://mlsanity.com/paper/2107.07761/) (2021)
- [CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network](https://mlsanity.com/paper/2203.15078/) (2022)
- [HistoPerm: A Permutation-Based View Generation Approach for Improving Histopathologic Feature Representation Learning](https://mlsanity.com/paper/2209.06185/) (2022)
- [A Similarity Measure of Histopathology Images by Deep Embeddings](https://mlsanity.com/paper/2107.13703/) (2021)
- [CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation](https://mlsanity.com/paper/2310.03981/) (2023)
- [Classification of Microscopy Images of Breast Tissue: Region Duplication based Self-Supervision vs. Off-the Shelf Deep Representations](https://mlsanity.com/paper/2202.06073/) (2022)
- [Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities](https://mlsanity.com/paper/2312.03812/) (2023)
- [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](https://mlsanity.com/paper/2312.06697/) (2023)

## Abstract (arXiv)

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.