Metadata-Version: 2.4
Name: toposv
Version: 0.1.1
Summary: TOPOS: Target Organ Prediction of Scout Views for Automated CT Scan Planning
Home-page: https://github.com/sziegelmayer/TOPOS
Author: Sebastian Ziegelmayer, Tristan Lemke
Author-email: sziegelmayer@tum.de, tristan.lemke@tum.de
License: Apache-2.0
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.0
Requires-Dist: numpy>=1.24
Requires-Dist: nibabel>=5.0
Requires-Dist: nnunetv2>=1.0.0
Requires-Dist: blosc2
Requires-Dist: huggingface_hub>=0.17.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# TOPOS

**Target Organ Prediction of Scout Views for Automated CT Scan Planning**

TOPOS is a deep learning-based tool for anatomical region detection and localization from scout scans. It uses a trained nnUNet v2 model to segment 26 anatomical labels from 2D radiographic scout views.

This package provides a simple Python interface for inference and post-processing, and automatically downloads the model checkpoint from Hugging Face.

---

## Features

- Deep learning-based organ localization
- 26 anatomical structures supported
- Compatible with nnUNet v2 (2D configuration)
- Automatically downloads the pretrained checkpoint
- Outputs per-label `.nii.gz` segmentations

---

## Installation

```bash

# Install TOPOS
pip install topos
