CABANA (CollAgen FiBre ANAlyzer) is a comprehensive toolkit for analyzing collagen fibre architecture in immunohistochemistry (IHC) and fluorescence microscopy images. It provides:
- Automated detection and quantification of collagen fibres
- Analysis of fibre orientation, length, and thickness
- Gap analysis for inter-fibre and intra-fibre spaces
- Interactive parameter optimization interface
- Batch processing for large datasets
- Tissue micro-array (TMA) preprocessing: native Olympus VSI reading, core fitting, per-core images and masks named by patient (
cabana-tma) - Optional ROI masks that confine every measurement to a region of interest
CABANA combines advanced computer vision algorithms with an intuitive user interface, making it accessible to researchers without extensive programming experience while providing detailed quantitative data for comprehensive analysis of collagen architecture.
System Requirements
- Processor (CPU): Intel Core i7, AMD Ryzen 7, or higher recommended
- Memory (RAM): Minimum 16 GB, 32 GB recommended
- GPU: NVIDIA GeForce GTX/RTX series with at least 10 GB VRAM recommended
- Python: 3.12
- Apple silicon: the segmentation network runs on the Apple GPU (MPS) automatically
Quick Installation
Install CABANA using pip:
pip install -U cabana
or install the latest version on GitHub:
pip install git+https://github.com/lxfhfut/Cabana.git
After installation, you can launch the CABANA GUI by running:
python -m cabana # or: cabana-gui
Tissue micro-array slides can also be cut into per-core images from the command line:
cabana-tma "APGI TMA 1 PicRed.vsi" out/TMA1 --array 1 # built-in ICGC/APGI array
cabana-tma "my slide.vsi" out/mine --map my_maps.csv # your own map
cabana-tma map template maps/ # a template to type or paste a map into
Alternatively, you can import CABANA in your Python code for customized analysis (see the Python API page):
from cabana import Cabana, BatchProcessor, TMAPreprocessor
Documentation
Comprehensive documentation is available at: https://cabana.readthedocs.io/en/latest/
Tutorials
We provide an interactive Jupyter notebook tutorial to help you get started: CABANA Tutorial
Citation
If you use CABANA in your research, please cite:
License
CABANA is released under the MIT License.
Contact
For questions and support, please contact:
- Xufeng Lin - x.lin@garvan.org.au
- Astrid Magenau - a.magenau@garvan.org.au
1 maintainer
Metadata
1 maintainer
Release files for cabana 0.3.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| cabana-0.3.9.tar.gz | 402.8 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| cabana-0.3.9-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 749.3 kB
Release files / cabana-0.3.9.tar.gz
| Download URL | cabana-0.3.9.tar.gz |
|---|---|
| Size | 402.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
070433e439ee847ce37cbc0a9218fd2b202cc5d4dd5dbf6721f727cf5f697437
|
|
BLAKE2b-256 checksum How to use checksums |
d22542cdebe0b445298cabbfdabc03fff3e1e61270503ba48e639d55385143a4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.11
|
Release files / cabana-0.3.9-py3-none-any.whl
| Download URL | cabana-0.3.9-py3-none-any.whl |
|---|---|
| Size | 346.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
76864f8429112fd60f46642102efe00d982428daa46a5140a4ebdb3034b15fd5
|
|
BLAKE2b-256 checksum How to use checksums |
bc5b5f0e345b5b0c6a0cbf87ef29f2d73e9415254dc57e3602e1a9b9a73778f7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.11
|
Security for cabana 0.3.9
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
