binli123/dsmil-wsi
A dual-stream multiple instance learning network using vision transformers and self-supervised learning for classifying whole slide histopathology images and detecting tumors.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of DSMIL, a dual-stream multiple instance learning network designed for whole slide image (WSI) classification and tumor detection. The model employs vision transformers and self-supervised contrastive learning to handle weakly supervised learning where only bag-level (slide-level) labels are available. It processes histopathology images by extracting features from image patches and aggregating them using attention-based pooling, enabling tumor classification without pixel-level annotations.
Frequently asked
- What is binli123/dsmil-wsi?
- A dual-stream multiple instance learning network using vision transformers and self-supervised learning for classifying whole slide histopathology images and detecting tumors.
- Is dsmil-wsi open source?
- Yes — binli123/dsmil-wsi is open source, released under the MIT license.
- What language is dsmil-wsi written in?
- binli123/dsmil-wsi is primarily written in Python.
- How popular is dsmil-wsi?
- binli123/dsmil-wsi has 468 stars on GitHub.
- Where can I find dsmil-wsi?
- binli123/dsmil-wsi is on GitHub at https://github.com/binli123/dsmil-wsi.