Data

Tools

Indexes

Applications

Experiments

Open Source Science

dd3d-eit

Data-Driven 3D Reconstruction for Electrical Impedance Tomography

https://github.com/jacobth98/dd3d-eit

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 1 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: ieee.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.9%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Data-Driven 3D Reconstruction for Electrical Impedance Tomography

Basic Info
  • Host: GitHub
  • Owner: JacobTh98
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 11.3 MB
Statistics
  • Stars: 3
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created about 2 years ago · Last pushed about 1 year ago
Metadata Files
Readme Citation

README.md

DD3D-EIT

Repository for the Paper: https://ieeexplore.ieee.org/abstract/document/10781524

Three networks are trained: a VAE $\mathbb{VAE}$, a mapper $\Xi$, and a material classifier $\Upsilon$.

The final architecture of the reconstruction network is defined by

$$ \Gamma := \Xi \circ \Psi : \mathbf{u} \mapsto \mathbf{z} \mapsto \hat{\gamma} $$

in parallel with the material classification network

$$ \Upsilon : \mathbf{u} \mapsto m $$

Here, $\mathbf{u}$ represents the EIT data, and $\hat{\gamma}$ is the reconstructed conductivity in a three-dimensional domain by the final reconstruction network architecture.

Hyperparametertuning $\beta$-VAE

Finally, model iteration 21 was selected (also marked with a green dashed line).

Last 25 VAE hyperparameter tunings with accuracy history of position and volume error (1.5 whisker rule). The three dashed lines mark the three best VAEs, with model 21 being the best.

Hyperparametertuning Mapper $\Xi$

| VAE | Iteration | Predictable (%) | Median volume error (%) | Median position error (%) | |---------|---------------|---------------------|-----------------------------|-------------------------------| | 21 | 1 | 92.19 | 0.16 | 4.14 | | 21 | 2 | 90.94 | 0.16 | 4.31 | | 21 | 3 | 92.09 | 0.14 | 4.39 | | 21 | 4 | 92.77 | 0.15 | 4.12 | | 21 | 5 | 54.65 | -0.10 | 8.73 | | 21 | 6 | 92.54 | 0.09 | 4.72 | | 21 | 7 | 92.58 | 0.14 | 4.58 | | 21 | 8 | 96.01 | 0.13 | 4.55 | | 21 | 9 | 90.83 | 0.12 | 4.44 |

Final reconstruction network architecture results

Five randomly selected EIT measurements were taken from the test data. The test data was not used throughout the training phases. The presented graph provides a proof of concept and shows the feasibility of reconstructing different objects within a phantom tank using a data-driven reconstruction approach.

The top row is the true conductivity distribution $\gamma$. The lower row represents the predictions of the reconstruction model $\hat{\gamma}$.

Please also cite:

@INPROCEEDINGS{10781524,
  author={Thönes, Jacob and Spors, Sascha},
  booktitle={2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)}, 
  title={Data-Driven 3D Reconstruction for Electrical Impedance Tomography}, 
  year={2024},
  volume={},
  number={},
  pages={1-4},
  keywords={Electrical impedance tomography;Solid modeling;Three-dimensional displays;Inverse problems;Conductivity;Reconstruction algorithms;Market research;Robustness;Numerical models;Image reconstruction},
  doi={10.1109/EMBC53108.2024.10781524}}

Environment

To install the used Python (3.11.2) environment, use

conda env create -f environment.yml

Owner

  • Login: JacobTh98
  • Kind: user

Citation (citation.cff) 

cff-version: 1.2.0
title: >-
  DD3D-EIT
message: >-
  If you use this repository, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Jacob Peter
    family-names: Thönes
    email: jacob.thoenes@uni-rostock.de
    affiliation: Universität Rostock
    orcid: 'https://orcid.org/0000-0003-2826-5281'
repository-code: 'https://github.com/JacobTh98/DD3D-EIT'
url: 'https://github.com/JacobTh98/DD3D-EIT'
keywords:
  - Machine learning
  - Electrical Impedance Tomography
  - DataDriven
  - Inverse problems
  - Image reconstruction
license: MIT
version: 0.1.0
date-released: '2024-06-13'

GitHub Events

Total
  • Watch event: 3
  • Push event: 2
Last Year
  • Watch event: 3
  • Push event: 2

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 5
  • Total Committers: 1
  • Avg Commits per committer: 5.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 3
  • Committers: 1
  • Avg Commits per committer: 3.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
JacobTh98 6****8 5

Issues and Pull Requests

Last synced: 8 months ago

All Time
  • Total issues: 0
  • Total pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • JacobTh98 (1)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

environment.yml pypi
  • absl-py ==1.4.0
  • astunparse ==1.6.3
  • black ==23.1.0
  • cachetools ==5.3.0
  • click ==8.1.7
  • cloudpickle ==2.2.1
  • deepxde ==1.11.0
  • dm-tree ==0.1.8
  • flatbuffers ==23.5.26
  • gast ==0.4.0
  • google-auth ==2.17.1
  • google-auth-oauthlib ==1.0.0
  • google-pasta ==0.2.0
  • grpcio ==1.53.0
  • h5py ==3.10.0
  • imageio ==2.34.1
  • jax ==0.4.8
  • keras ==3.1.1
  • keras-core ==0.1.7
  • keras-tuner ==1.4.5
  • kt-legacy ==1.0.5
  • libclang ==16.0.0
  • markdown ==3.4.3
  • markdown-it-py ==3.0.0
  • markupsafe ==2.1.2
  • mdurl ==0.1.2
  • ml-dtypes ==0.3.2
  • mypy-extensions ==1.0.0
  • namex ==0.0.7
  • numpy ==1.23.5
  • nvidia-cublas-cu12 ==12.2.5.6
  • nvidia-cuda-cupti-cu12 ==12.2.142
  • nvidia-cuda-nvcc-cu12 ==12.2.140
  • nvidia-cuda-nvrtc-cu12 ==12.2.140
  • nvidia-cuda-runtime-cu12 ==12.2.140
  • nvidia-cudnn-cu12 ==8.9.4.25
  • nvidia-cufft-cu12 ==11.0.8.103
  • nvidia-curand-cu12 ==10.3.3.141
  • nvidia-cusolver-cu12 ==11.5.2.141
  • nvidia-cusparse-cu12 ==12.1.2.141
  • nvidia-nccl-cu12 ==2.16.5
  • nvidia-nvjitlink-cu12 ==12.2.140
  • oauthlib ==3.2.2
  • opt-einsum ==3.3.0
  • optree ==0.11.0
  • pandas ==2.1.1
  • pathspec ==0.12.1
  • protobuf ==4.22.1
  • pyaml ==23.12.0
  • pyasn1 ==0.4.8
  • pyasn1-modules ==0.2.8
  • pyeit ==1.2.4
  • pyftdi ==0.55.0
  • pyserial ==3.5
  • pytz ==2023.3.post1
  • pyusb ==1.2.1
  • pyyaml ==6.0.1
  • requests-oauthlib ==1.3.1
  • rich ==13.6.0
  • rsa ==4.9
  • scikit-optimize ==0.9.0
  • sciopy ==0.7.1
  • seaborn ==0.13.0
  • shapely ==2.0.2
  • sounddevice ==0.4.6
  • tensorboard ==2.16.2
  • tensorboard-data-server ==0.7.0
  • tensorboard-plugin-wit ==1.8.1
  • tensorflow ==2.16.1
  • tensorflow-estimator ==2.14.0
  • tensorflow-io ==0.37.0
  • tensorflow-io-gcs-filesystem ==0.37.0
  • tensorflow-probability ==0.19.0
  • tensorrt-libs ==8.6.1
  • termcolor ==2.2.0
  • theano ==1.0.5
  • tikzplotlib ==0.10.1
  • tokenize-rt ==5.2.0
  • tqdm ==4.66.1
  • trimesh ==4.0.0
  • tzdata ==2023.3
  • webcolors ==1.13
  • werkzeug ==2.2.3
  • wrapt ==1.14.1