Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.12006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910993550934016 |
|---|---|
| author | Chiocchetti, Annalisa Dossena, Marco Irwin, Christopher Portinale, Luigi |
| author_facet | Chiocchetti, Annalisa Dossena, Marco Irwin, Christopher Portinale, Luigi |
| contents | This work contributes to breast cancer sub-type classification using histopathological images. We utilize masked autoencoders (MAEs) to learn a self-supervised embedding tailored for computer vision tasks in this domain. This embedding captures informative representations of histopathological data, facilitating feature learning without extensive labeled datasets. During pre-training, we investigate employing a random crop technique to generate a large dataset from WSIs automatically. Additionally, we assess the performance of linear probes for multi-class classification tasks of cancer sub-types using the representations learnt by the MAE. Our approach aims to achieve strong performance on downstream tasks by leveraging the complementary strengths of ViTs and autoencoders. We evaluate our model's performance on the BRACS dataset and compare it with existing benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12006 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Labels: A Self-Supervised Framework with Masked Autoencoders and Random Cropping for Breast Cancer Subtype Classification Chiocchetti, Annalisa Dossena, Marco Irwin, Christopher Portinale, Luigi Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning This work contributes to breast cancer sub-type classification using histopathological images. We utilize masked autoencoders (MAEs) to learn a self-supervised embedding tailored for computer vision tasks in this domain. This embedding captures informative representations of histopathological data, facilitating feature learning without extensive labeled datasets. During pre-training, we investigate employing a random crop technique to generate a large dataset from WSIs automatically. Additionally, we assess the performance of linear probes for multi-class classification tasks of cancer sub-types using the representations learnt by the MAE. Our approach aims to achieve strong performance on downstream tasks by leveraging the complementary strengths of ViTs and autoencoders. We evaluate our model's performance on the BRACS dataset and compare it with existing benchmarks. |
| title | Beyond Labels: A Self-Supervised Framework with Masked Autoencoders and Random Cropping for Breast Cancer Subtype Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.12006 |