-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
3bfa539
commit bddb349
Showing
1 changed file
with
17 additions
and
17 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,34 +1,34 @@ | ||
![Title_Image](https://user-images.githubusercontent.com/71383228/148084248-5e169761-a075-4c86-836a-e9b2cec56ef6.jpg) | ||
|
||
# DeepACSA | ||
*Automatic analysis of human lower limb ultrasonography images* | ||
|
||
DeepACSA is an open-source tool to evaluate the anatomical cross-sectional area of muscles in ultrasound images using deep learning. | ||
More information about the usage of DeepACSA can be found in the instructional [video](https://youtu.be/It9CqVSNc9M) | ||
Our trained models can be accessed at [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.6953924.svg)](https://doi.org/10.5281/zenodo.6953924). | ||
Anonymized panoramic ultrasound images are available at [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5799204.svg)](https://doi.org/10.5281/zenodo.5799204). | ||
More information about the installtion and usage of DeepACSA can be found in the online [documentation](https://deepacsa.readthedocs.io/en/latest/index.html). You can find information about contributing, issues and bug reports there as well. | ||
Our trained models, training data, an executable as well as example files can be accessed at [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.7498630.svg)](https://doi.org/10.5281/zenodo.7498630). | ||
If you find this work useful, please remember to cite the corresponding [paper](https://journals.lww.com/acsm-msse/Abstract/9900/DeepACSA__Automatic_Segmentation_of.87.aspx), where more information about the model architecture and performance can be found as well. | ||
|
||
## Descriptive figure of the model used | ||
## Quickstart | ||
|
||
![Figure2_VGG16Unet](https://user-images.githubusercontent.com/71383228/182554020-2c8bad75-7f08-4194-8f5f-0a521a70781c.jpg) | ||
To quickly start the DeepACSA either open the executable or type | ||
|
||
DeepACSA workflow. aFigure 2: DeepACSA workflow. a) Original ultrasound image of the m. rectus femoris (RF) at 50% of femur length that serves as input for the model. b) Detailed U-net CNN architecture (modified from Ronneberger et al. (19) and Cronin et al. (15)) with a VGG16 encoder (left path). c) Model prediction of muscle area following post-processing (shown as a binary image). | ||
``python -m Deep_ACSA`` | ||
|
||
in your prompt once the package was installed locally with | ||
|
||
## Results of comparing DeepACSA analysis to manual analysis | ||
``python -m pip install -e .`` | ||
|
||
![Figure3_BAP](https://user-images.githubusercontent.com/71383228/182554096-c5fde7cd-a137-4cc4-ad73-a819368d13ec.jpg) | ||
when navigated at the DeepACSA/DeepACSA folder. | ||
Irrespective of the way the software was started, the GUI should open and is ready to be used. | ||
|
||
Bland-Altman plots of all muscles plotting the difference between manual and DeepACSA with incorrect predictions removed (rm), manual and DeepACSA as well as manual and ACSAuto area segmentation measurements against the mean of both measures. Dotted and solid lines illustrate 95% limits of agreement and bias. M. rectus femoris (RF) and m. vastus lateralis (VL), mm. gastrocnemius medialis (GM), and lateralis (GL). | ||
## Descriptive figure of the model used | ||
|
||
## Examples | ||
![Figure2_VGG16Unet](https://user-images.githubusercontent.com/71383228/182554020-2c8bad75-7f08-4194-8f5f-0a521a70781c.jpg) | ||
|
||
This is an example command making use of the implemented GUI: | ||
```sh | ||
python deep_acsa_gui.py | ||
``` | ||
DeepACSA workflow. a) Original ultrasound image of the m. rectus femoris (RF) at 50% of femur length that serves as input for the model. b) Detailed U-net CNN architecture with a VGG16 encoder (left path). c) Model prediction of muscle area following post-processing (shown as a binary image). | ||
|
||
## Literature | ||
Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv150504597 Cs (2015). | ||
## Results of comparing DeepACSA analysis to manual analysis | ||
|
||
Cronin, N. J., Finni, T. & Seynnes, O. Fully automated analysis of muscle architecture from B-mode ultrasound images with deep learning. ArXiv200904790 Cs Eess (2020). | ||
![Figure3_BAP](https://user-images.githubusercontent.com/71383228/182554096-c5fde7cd-a137-4cc4-ad73-a819368d13ec.jpg) | ||
|
||
Bland-Altman plots of all muscles plotting the difference between manual and DeepACSA with incorrect predictions removed (rm), manual and DeepACSA as well as manual and ACSAuto area segmentation measurements against the mean of both measures. Dotted and solid lines illustrate 95% limits of agreement and bias. M. rectus femoris (RF) and m. vastus lateralis (VL), mm. gastrocnemius medialis (GM), and lateralis (GL). |