[](https://colab.research.google.com/github/luuleitner/deepMTJ/blob/master/mtj_tracking/predict/mtj_tracking.ipynb)
deepMTJ: Muscle-Tendon Junction Tracking in Ultrasound Images
-------------------------------------------------------------
`deepMTJ` is a machine learning approach for automatically tracking of muscle-tendon junctions (MTJ) in ultrasound images. Our method is based on a convolutional neural network trained to infer MTJ positions across various ultrasound systems from different vendors, collected in independent laboratories from diverse observers, on distinct muscles and movements. We built `deepMTJ` to support clinical biomechanists and locomotion researchers with an open-source tool for gait analyses.
![enter image description here][1]
Introduction into the deepMTJ dataset
-------------------------------------
This repository contains the full test dataset used for `deepMTJ` performance assessments, the trained TensorFlow (Keras) model and a Link to the code repository of deepMTJ. Furthermore, we provide online predictions using `deepMTJ` via a [Google Colab Notebook][3] (For multiple and large file predictions) and via [deepMTJ.org][4] (Cloud based predictions).
- The dataset comprises 1344 images of muscle-tendon junctions recorded with 3 ultrasound imaging systems (Aixplorer V6, Esaote MyLab60, Telemed ArtUs), on 2 muscles (Lateral Gastrocnemius, Medial Gastrocnemius), and 2 movements (isometric maximum voluntary contractions, passive torque movements).
- We have included the ground truth labels for each image. These reference labels are the computed mean from 4 specialist labels. Specialist annotators had 2-10 years of experience in biomechanical and clinical research investigating muscles and tendons in 2-9 ultrasound studies in the past 2 years.
Repository structure
--------------------
- `2021_Unet_deepmtj_ieeetbme_model.tf`: trained model weights of our network published in Leitner *et al.* 2021a
- `testset_frames.h5`: testset frames saved in an hdf5 file structure. The structure of the first frame corresponds to: ['testset_fullres/frame_0001'] and ['testset_256x128px/frame_0001'].
- `testset_frames.zip`: jpg-images of testset frames in full resolution and in model input resolution (256x128px)
- `testset_frames_annotated.zip`: expert annotated jpg-images of testset frames in full resolution and in model input resolution (256x128px)
- `testset_logic_labels.csv`: logic array containing following information for each frame ['Frame Nr.', 'Instrument', 'Muscle', 'Movement', 'Expert X (fullres)', 'Expert Y (fullres)', 'Expert X (256x128px)', 'Expert Y (256x128px)']
Publications
------------
```
[1] @article{deepmtj2021a,
title={A Human-Centered Machine-Learning Approach for Muscle-Tendon Junction Tracking in Ultrasound Images},
year={2021}
author={Leitner, Christoph and Jarolim, Robert and Englmair, Bernhard and Kruse, Annika and Hernandez, Karen Andrea Lara and Konrad, Andreas and Su, Eric and Schröttner, Jörg and Kelly, Luke A. and Lichtwark, Glen A. and Tilp, Markus and Baumgartner, Christian},
journal = {IEEE Transactions on Biomedical Engineering},
publisher={IEEE},
doi={10.1109/TBME.2021.3130548}
}
[2] @misc{deepmtj2021b,
title = {{deepMTJ test-set data}},
year={2021}
author={Leitner, Christoph and Jarolim, Robert and Englmair, Bernhard and Kruse, Annika and Hernandez, Karen Andrea Lara and Konrad, Andreas and Su, Eric and Schröttner, Jörg and Kelly, Luke A. and Lichtwark, Glen A. and Tilp, Markus and Baumgartner, Christian},
doi={10.6084/m9.figshare.16822978.v2}
}
[3] @inproceedings{deepmtj2020,
title={Automatic Tracking of the Muscle Tendon Junction in Healthy and Impaired Subjects using Deep Learning*},
year={2020},
author={Leitner, Christoph and Jarolim, Robert and Konrad, Andreas and Kruse, Annika and Tilp, Markus and Schröttner, Jörg and Baumgartner, Christian},
booktitle={2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC)},
publisher={IEEE},
pages={4770-4774},
doi={10.1109/EMBC44109.2020.9176145}
}
```
[1]: https://osf.io/d97cg/?direct&mode=render&action=download&public_file=False
[2]: https://mfr.de-1.osf.io/export?url=https://osf.io/bh98x/?direct%26mode=render%26action=download%26public_file=False&initialWidth=848&childId=mfrIframe&parentTitle=OSF+%7C+3dvolume.jpg&parentUrl=https://osf.io/bh98x/&format=300x300.jpeg
[3]: https://colab.research.google.com/github/luuleitner/deepMTJ/blob/master/mtj_tracking/predict/mtj_tracking.ipynb
[4]: https://deepmtj.org/
Loading...
