Summary of Transcriptomics-guided Slide Representation Learning in Computational Pathology, by Guillaume Jaume et al.
Transcriptomics-guided Slide Representation Learning in Computational Pathology
by Guillaume Jaume, Lukas Oldenburg, Anurag Vaidya, Richard J. Chen, Drew F.K. Williamson, Thomas Peeters, Andrew H. Song, Faisal Mahmood
First submitted to arxiv on: 19 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a self-supervised learning approach to learn slide embeddings from whole-slide images (WSIs) by leveraging complementary information from gene expression profiles. The method, called Tangle, uses multimodal pre-training with modality-specific encoders and contrastive learning to align slide and expression embeddings. The authors pre-train the model on samples from three organs (liver, breast, and lung) from two species (Homo sapiens and Rattus norvegicus). The results show that Tangle outperforms supervised and self-supervised baselines in few-shot performance and prototype-based classification and slide retrieval tasks. The authors also release their code on GitHub. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps create better models for learning from big images of tissues (called whole-slide images). It does this by using extra information about the tissue, like what genes are turned on or off. This extra information can help the model learn to recognize patterns in the image that it wouldn’t have found otherwise. The authors tested their method and found it worked better than other methods at recognizing different types of tissues. |
Keywords
» Artificial intelligence » Classification » Few shot » Self supervised » Supervised
