Metadata-Version: 2.4
Name: TMAx
Version: 0.1.4.2
Summary: Module for segmenting pathological images of tissue microarrays
Author-email: BOSCH Valentin <val.bosch2001@gmail.com>
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: torch
Requires-Dist: numpy
Requires-Dist: huggingface_hub
Requires-Dist: opencv-python
Requires-Dist: pillow
Requires-Dist: torchvision

# TMAx 
This project proposes an image segmentation model for histopathological images, specifically designed for Tissue MicroArrays (TMA) used in pathological anatomy.

The goal is to automatically segment structures of interest in digital slides, particularly in the context of lymphomas.

# Documentation
def predict_mask(imagePath, output_path=None, save_image=False)
Parameters
- imagePath (str): Local path to the input image to be segmented (supports standard formats and TIFF).
- output_path (str, optional): Destination path for saving the mask. Required only if save_image is True. Default: None.
- save_image (bool, optional): If True, exports the generated mask as an image to the location specified by output_path. Default: False.

Return
- predMask (numpy.ndarray): A NumPy array of type uint8 representing the binary mask (values 0 or 255). The size of the array exactly matches the dimensions of the original image.
