title: How-to guides — 3D vision and medical imaging tasks in Python description: One page per task, titled as the question practitioners ask: download and standardize datasets, DICOM to NIfTI, raw point clouds, ICP and RANSAC that converge, CT/MR registration, masks to meshes, CT segmentation, surface reconstruction, atlas labelling, Gaussian splats, pretrained segmentation models, DINOv3 features.
How-to guides¶
Each page answers one question with runnable code on a bundled dataset, the expected output, and what to do when it fails. The code ran on 2026-10-16 with pip install "pardesline[all]".
Datasets¶
- How to download a medical imaging dataset in Python
- How to load a Hugging Face 3D dataset in Python
- How to download a TCIA collection in Python
- How to standardize a folder of medical images in Python
- How to convert a DICOM series to NIfTI in Python
- How to load raw .npy and .bin point clouds with a layout
Algorithms¶
- How to register two point clouds with ICP in Python
- How to fix ICP that does not converge
- How to fix RANSAC global registration that fails
- How to register CT and MRI of the same patient in Python
- How to turn a segmentation mask into a mesh in Python
- How to segment organs in a CT scan in Python
- How to reconstruct a surface from a point cloud in Python
- How to align two scans in Python
- How to label a scan from an atlas in Python
- How to convert a point cloud to Gaussian splats in Python