xai4mri is designed for advanced MRI analysis using deep learning combined with explainable A.I. (XAI).
Project description
xai4mri
Explainable A.I. for MRI research using deep learning.
What is xai4mri
xai4mri
is designed for advanced MRI analysis combining deep learning with explainable A.I. (XAI).
It offers the following key functionalities:
- Data Integration: Effortlessly import new MRI datasets and apply the models to generate accurate predictions.
- Model Loading: load (pretrained) 3D-convolutional neural network models tailored for MRI predictions.
- Interpretation Tools: Utilize analyzer tools, such as Layer-wise Relevance Propagation (LRP), to interpret model predictions through intuitive heatmaps.
With xai4mri, you can complement your MRI analysis pipeline, ensuring precise predictions and insightful interpretations.
Quick-start
pip install -U xai4mri
Get started with xai4mri
in Python:
import xai4mri as xai
Visit the documentation, for detailed information.
Citation
When using xai4mri
, please cite the following papers:
[toolbox paper in prep
] and Hofmann et al. (2022, NeuroImage).
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file xai4mri-0.0.1.tar.gz
.
File metadata
- Download URL: xai4mri-0.0.1.tar.gz
- Upload date:
- Size: 73.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9eb772b0e35fb152b34e2d50448f616f3a349fb7dd1560ca23f925b786ad0bf1 |
|
MD5 | a777818613365e605f223596f4dbb4a0 |
|
BLAKE2b-256 | 83454aa3b41fb8236aade0971ecc8f918b92a6b8e3cbb437ac1277cc1a39274f |
File details
Details for the file xai4mri-0.0.1-py3-none-any.whl
.
File metadata
- Download URL: xai4mri-0.0.1-py3-none-any.whl
- Upload date:
- Size: 67.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7a506a094ba360467cb9f64fdd60cc9c5c2198bb21d287a104010514e4519d0b |
|
MD5 | 04cabec5c4dbb5d1a8fc266f495cfecb |
|
BLAKE2b-256 | ef9e730e508101304ee75b51c8b4bacac300f78013e724c64359ac453922b5af |