Skip to main content

Toolbox for histopathology image analysis

Project description

PrismToolBox

PrismToolBox is a comprehensive toolkit designed to streamline the process of working with digital pathology images. It provides a set of utilities and functionalities that simplify tasks such as reading slides, extracting patches, and embedding slides. It also provides useful functions to import/export data on QuPath.

The toolkit is still under development, and some features may not be fully implemented. If you encounter any issues or have suggestions for improvements, please open an issue or submit a pull request.

Features

  • Slide Reading: Supports multiple backends for reading slides, including OpenSlide and TiffSlide.
  • Patch Extraction: Extracts patches from slides at various magnification levels.
  • Slide Embedding: Uses pre-trained models to generate embeddings from patches, facilitating downstream tasks like clustering or classification (in progress).
  • Nuclei segmentation: Extracts nuclei using cellpose for H&E and SOP for IHC brighfield images.

Installation

To install PrismToolBox, run the following command in your terminal:

pip install prismtoolbox

To install PrismToolBox embedding and nuclei utilitaries, please run the following command:

pip install 'prismtoolbox[emb, seg]'

Usage

Here's a basic example of how to use PrismToolBox:

from prismtoolbox import WSI

# Initialize the reader
WSI_object = WSI(slide_path="path_to_your_slide", engine="openslide")

# Extract tissue contours
params_detect_tissue = {"seg_level": 4, "window_avg": 30, "window_eng": 5, "thresh": 90, "area_min": 1.5e3}

WSI_object.detect_tissue(**params_detect_tissue)

# Extract patches and save them as jpg images
params_patches = {"patch_size": 256, "patch_level": 0,"mode": "contours", "contours_mode": "four_pt_hard"}

WSI_object.extract_patches(**params_patches)
WSI_object.save_patches("path_to_folder", file_format="jpg")

For more detailed usage instructions and examples, please refer to the documentation.

Contributing

Contributions to PrismToolBox are welcome! Please open an issue or submit a pull request to propose changes or additions.

License

PrismToolBox is licensed under the BSD 3-Clause License. See LICENSE for more information.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

prismtoolbox-0.1.1.tar.gz (57.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

prismtoolbox-0.1.1-py3-none-any.whl (67.7 kB view details)

Uploaded Python 3

File details

Details for the file prismtoolbox-0.1.1.tar.gz.

File metadata

  • Download URL: prismtoolbox-0.1.1.tar.gz
  • Upload date:
  • Size: 57.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.11 Linux/6.5.0-1025-azure

File hashes

Hashes for prismtoolbox-0.1.1.tar.gz
Algorithm Hash digest
SHA256 f5323ffd569dbc9d41473edcde97acb9c335e65edede9390fae19dacc1b70e33
MD5 4b276a92ebf5bfda11f91ef3081eaf0b
BLAKE2b-256 6142c5c6acd8907c4423935b9b9c2f7847824ef2ae27b6411c96c070109671c8

See more details on using hashes here.

File details

Details for the file prismtoolbox-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: prismtoolbox-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 67.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.11 Linux/6.5.0-1025-azure

File hashes

Hashes for prismtoolbox-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 1f6dbc3cc695edcd38abe4a014bb119235355fdbcd90d8848944f3a1a5891c0c
MD5 4d9080ea16492d65286fbfd9083e9e8c
BLAKE2b-256 7bce3d3aa90541d0fa71b1767cd992174baf63ca03c7fcde5faef25b259e5dad

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page