https://github.com/kevinhongzl/medaset
A collection of pre-built dataset classes for medical datasets.
https://github.com/kevinhongzl/medaset
deep-learning medical-image-processing monai python3 pytorch
Last synced: 1 day ago
JSON representation
A collection of pre-built dataset classes for medical datasets.
- Host: GitHub
- URL: https://github.com/kevinhongzl/medaset
- Owner: kevinhongzl
- License: mit
- Created: 2023-10-10T19:41:34.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-02-05T21:43:34.000Z (over 1 year ago)
- Last Synced: 2025-04-15T10:38:56.440Z (6 months ago)
- Topics: deep-learning, medical-image-processing, monai, python3, pytorch
- Language: Python
- Homepage:
- Size: 116 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Medaset
> A collection of pre-built dataset classes for **MED**ical dat**ASET**s.
[](https://www.python.org) [](https://github.com/project-monai/monai) [](https://pytorch.org) [](https://github.com/psf/black)
**Objectives**
* Compatible to [`PyTorch`](https://pytorch.org/docs/stable/index.html) and [`MONAI`](https://monai.io/)
* Providing some off-the-shelf features to the `Dataset` class, including but not limited to, dataset extracting, loading and visualization.
### Getting started
`git clone` this repo and install it using
```bash
pip install -e .
```
> [!CAUTION]
> Naming convention changed!! For the sake of readibility, only the first letters in each acronym are now capitalized.
## Currently Supported Datasets
* **AMOS (Abdominal Multi-Organ Segmentation)**
[[Grand Challenge]](https://amos22.grand-challenge.org/) [[Arxiv]](https://arxiv.org/abs/2206.08023)
* AMOS provides 500 CT and 100 MRI scans collected from multi-center, multi-vendor, multi-modality, multi-phase, multi-disease patients, each with voxel-level annotations of 15 abdominal organs.
* Structure: spleen, right kidney, left kidney, gallbladder, esophagus, liver, stomach, aorta, inferior vena cava, pancreas, right adrenal gland, left adrenal gland, duodenum, bladder, prostate/uterus.
* Dataset classes: `AmosDataset`, `SimpleAmosDataset`
---
* **CHAOS (Combined (CT-MR) Healthy Abdominal Organ Segmentation)**
[[Grand Challenge]](https://chaos.grand-challenge.org/) [[Arxiv]](https://arxiv.org/abs/2001.06535)
* The CHAOS challenge data contains 40 CT scans and 40 MR scans of upper abdomen area.
* Structure (Modality): Liver (CT/MR), Kidneys (MR), Spleen (MR)
* Dataset classes: `ChaosCtDataset`, `ChaosT2spirDataset` (The T1-DUAL sequence is not supported currently)
---
* **SMAT (Skeletal Muscle and Adipose Tissue)**
* Private dataset
* Dataset classes: `SmatCtDataset`, `SmatMrDataset`, `SmatDataset`
## Useful Links
**Metadata Desciptions**
* [NIfTI file header discriptions](https://brainder.org/2012/09/23/the-nifti-file-format/)
* [DICOM Standard Browser](https://dicom.innolitics.com/ciods)
**Medical Image Coordinate Systems**
* [An Introduction from 3D Slicer](https://slicer.readthedocs.io/en/latest/user_guide/coordinate_systems.html)
* [An Introduction of coordinate systems and affines from nipy.org](https://nipy.org/nibabel/coordinate_systems.html)
* [Defining the DICOM orientation](https://nipy.org/nibabel/dicom/dicom_orientation.html)
* [Geometry in Medical Imaging: DICOM and NIfTI formats](https://discovery.ucl.ac.uk/id/eprint/10146893/1/geometry_medim.pdf)
* [The First Step for Neuroimaging Data Analysis: DICOM to NIfTI conversion](https://core.ac.uk/download/pdf/79518053.pdf)