SAMHI/README.md

SAMHI

This repository contains the code of SAMHI, a deep learning-based method for the automatic and interactive segmentation of cells and glands in histological images. SAMHI uses SAM and CellViT and is fine-tuned on large-scale segmentation datasets of histological images.

Key Features

• Automatic Segmentation: SAMHI allows users to automatically segment cells in histological images.
• Interactive Segmentation: SAMHI allows users to interactively segment cells and glands in histological images.

Setup

1. Clone the repository with: git clone https://github.com/philippendres/SAMHI.git
2. Create a new conda environment with the provided environment.yml file:

   conda env create -f environment.yml
   conda activate histo3.10
   

3. Install the resources:

   cd resources
   cd CellViT
   git submodule init
   git submodule update
   pip install -e .
   cd ..
   cd SimpleClick
   git submodule init
   git submodule update
   pip install -e .
   cd ..
   cd ..
   

4. Install our package:

   pip install -e .
   

5. • For inference: Download the weights of the SAMHI model and the CellViT model: SAMHI, CellViT
   • For training: Download the weights of the SAM model: SAM
   • For model comparisons: Download the weights of the SimpleClick and the MedSAM model: SimpleClick, MedSAM

Usage

App

Run the gradio webapplication with the following command:

python app.py --model_dir <model_dir> --model_name <model_name> --cellvit_model <cellvit_model>

The app has the following arguments:

• model_dir: The directory where the SAMHI and the CellViT model are stored.
• model_name: The name of the SAMHI model.
• cellvit_model: The name of the CellViT model.

The command above will generate a link to a webapplication where you can upload your own images and segment them with SAMHI. The app will look like this: The app has the following features:

• Upload Image: Upload your own image to segment in the upper left corner.
• Auto Segment: Automatically segment the uploaded image with SAMHI.
• Add Mask: Interactively add a mask with SAMHI by drawing points and bounding boxes on the image.
• Refine Mask: Refine an existing mask by drawing points and bounding boxes on the image.
• Remove Mask: Remove an existing mask by clicking on it.
• Move the Image: Move the image with the arrow symbols.
• Zoom the Image: Zoom the image with the zoom bar.