Project Tree
Now limiting view to projects in the following categories:
All Topics :: Biocomputational Focus :: Image Processing [Remove This Filter]
All Topics > Primary Content > Developer Tools |
Browse By: |
9 projects in result set.
MITK-GEM: Software pipeline to GEnerate Models from images
- An attempt to provide a software pipeline to interactively create finite element models from medical images. Primarily intended to model bone fracture risk.
An application with graphical user interface and image processing plugins is provided. The application is build using the MITK Workbench software framework. The following plugins are available: fast image segmentation using graph cut, volume meshing using tetgen and density to modulus conversion for bone material property assignment.
Documentation and tutorials are available on our <a href="http://araex.github.io/mitk-gem-site/">tutorial website</a>.
Along with pre-compiled executables available here, the source code is available on our <a href="https://github.com/araex/mitk-gem">github page</a>.
The graph cut segmentation plugin and the material mapping plugin were developed as part of research studies.
If you use the software or source code in your research, please cite the corresponding journal <a href="https://simtk.org/project/xml/publications.xml/?group_id=1063">publications</a>. | |
|
Registered: 2015-12-23 02:46 |
SimVascular: Examples and Clinical Cases
- We invite you to download and try these examples and clinical case projects, which are all compatible with the open source SimVascular cardiovascular modeling software package. Each case includes image data of a healthy or diseased individual, a 3D anatomic model created from the image data, and simulation job files which specify initial conditions, boundary conditions and various parameters required to run the simulation. Many of the cases are already organized as SV projects, which means you can easily load them into SimVascular and view or try out various project components. Following the guides in the SimVascular documentation website, you can also create new models and run simulations with different conditions, based on these example cases.
You are free to download the examples and cases provided that you properly reference the source. The cases are part of the academic output of the researcher cited and should be referred to as such. Permission is granted to use these cases for research purposes, but for commercial use please contact the director of the Cardiovascular Biomechanics Computation Lab, Alison Marsden (amarsden@stanford.edu).
The examples and clinical cases included are:
Example: Demo Project
Example: Cylinder Project (no image, for simulation)
Clinical Case: Coronary Normal
Clinical Case: Aortofemoral Normal 1
Clinical Case: Aortofemoral Normal 2
Clinical Case: Healthy Pulmonary
SimVascular is available for download at our project website at:
https://simtk.org/projects/simvascular
Comprehensive documentation is available on the SimVascular website at:
http://www.simvascular.org
| |
|
Activity Percentile: 93.13 Registered: 2014-03-14 20:12 |
DeepCell: Deep convolutional neural networks for image segmentation
- The assignment of a cellular identity to individual pixels in microscopy images is a key technical challenge for many live-cell experiments. Traditional approaches to this image segmentation problem have relied on standard computer vision techniques, such as thresholding, morphological operations, and the watershed transform. While these approaches have enabled the analysis of numerous experiments, they are limited in their robustness and in applicability. Here, we show that deep convolutional neural networks, a supervised machine learning method, can robustly segment the cytoplasms of individual bacterial and mammalian cells. This approach automates the analysis of thousands of bacterial cells and leads to more accurate quantification of localization based fluorescent reporters in mammalian cells. In addition, this approach can also simultaneously segment and identify different mammalian cell types in co-cultures. Deep convolutional neural networks have had a transformative impact on the problem of image classification, and we anticipate that they will have a similar impact for live-cell imaging experiments.
Visit our webpage at http://covertlab.github.io/DeepCell | |
|
Activity Percentile: 84.73 Registered: 2015-11-16 19:58 |
Matlab-Opensim Interfaces
- Matlab is a common analysis tool used for data manipulation, signal processing and function integration. These features can be used in conjunction with simulation tools provided by the Opensim interface.
This project provides tools for using different aspects of Opensim within the Matlab environment. This includes 1) using the command line tools by generating XML setup files etc (Scaling, Inverse Kinematics, Inverse Dynamics, Forward Dynamics) 2) using the Java classes that the Opensim GUI is built on to access aspects of the Opensim API.
Provided in this project are -
1) Tools for taking motion capture data from C3D files and generating the required input files (marker files {*.trc} motion files {*.mot}, GRF xml files {*.xml}) as well as setup files for each of the different tools that can be called from the command line. Example data from different models and data sets are provided including example pipelines to analyse data using Opensim. Some of this implementation has taken inspiration from Tim Dorn's excellent GaitExtract toolbox. A new page with more up-to-date tools can be found here - http://simtk-confluence.stanford.edu:8080/display/OpenSim/Tools+for+Preparing+Motion+Data
2)Matlab functions and example scripts for accessing the Opensim API through Matlab. This utilises the Java wrapping classes that the Opensim GUI is built on. Examples are shown to open and edit models as well as perform a 'Muscle Analysis'. Please now use the inbuilt support from Opensim rather than this toolbox! (http://simtk-confluence.stanford.edu:8080/display/OpenSim/Scripting+with+Matlab) | |
|
Activity Percentile: 79.39 Registered: 2011-08-06 20:22 |
Motion Analyst Software Suite
- This project is a suite of motion analysis tools that use images from common video cameras to measure 2D and 3D motions. Locations of markers in 2D space can be tracked in time using MotionAnalyst2D. When interested in 3D reconstruction, 2D analysis needs to be completer using two cameras that simultaneously capture the images. By combining the two 2D results with the camera orientation calibration data, then 3D locations for those original markers can be reconstructed using MotionAnalyst3D. | |
|
Activity Percentile: 34.73 Registered: 2011-12-01 21:24 |
Fiber Tractography for Finite-Element Modeling of Transversely Isotropic Tissues
- This project demonstrates the process for fiber tractography of complex biological tissues with transverse isotropy, such as tendon and muscle. This is important for finite element studies of these tissues, as the fiber direction must be specified in the constitutive model. This project contains code, models, and data that can be used to reproduce the results of our publication on this technique. The supplied instructional videos will enable researchers to easily and efficiently apply this method to a variety of other tissues. The software used in the fiber tractography process and demonstrated in this project is Matlab, Autodesk Inventor (free for educators), and Autodesk Simulation CFD (free for educators). Full demonstrations and process instructions can be found in the 7 videos posted at https://vimeo.com/album/3414604:
Contents:
Chapter 1: Introduction (2:35)
This video introduces the CFD fiber tractography software pipeline
<!-- This version of the embed code is no longer supported. Learn more: https://vimeo.com/s/tnm --> <object width="500" height="281"><param name="allowfullscreen" value="true" /><param name="allowscriptaccess" value="always" /><param name="movie" value="https://vimeo.com/moogaloop.swf?clip_id=129107314&force_embed=vimeo.com&fullscreen=1" /><embed src="https://vimeo.com/moogaloop.swf?clip_id=129107314&force_embed=vimeo.com&fullscreen=1" type="application/x-shockwave-flash" allowfullscreen="true" allowscriptaccess="always" width="500" height="281"></embed></object>
Chapter 2: Supplementary materials code, models and data (20:21)
This video shows the shared models, code, and data posted online at simtk.org/m3lab_cfd4fea.
Chapter 3: Finite element simulations (5:38)
This video shows finite element simulations using the fiber mapping process.
Chapter 4: Iliacus example walkthrough (21:38)
This video shows the step-by-step process for fiber mapping the iliacus muscle (a hip flexor).
Chapter 5: Bflh example walkthrough (12:09)
This video shows the step-by-step process for fiber mapping the biceps femoris longhead muscle (a hamstring).
Chapter 6: Autodesk Inventor segmentation (9:09)
This video shows how to do segmentation of medical images in Autodesk Inventor in order to simplify the solid model for the CFD and FEA software.
Chapter 7: Curved inlet surfaces (6:28)
This video shows how to create curved inlet surfaces for use in Autodesk Simulation CFD. | |
|
Activity Percentile: 24.05 Registered: 2015-05-28 18:52 |
SimVascular: Third-party open source software.
- Third party open source software needed by internal developers of the new SimVascular project. | |
|
Registered: 2013-12-10 23:33 |
3D Numerical Investigation of Endothelial Shear Stress in Arteries
- 3D numerical investigation of endothelial shear stress in coronary arteries. | |
|
Activity Percentile: 0.00 Registered: 2015-11-30 13:34 |
Autoscoper (Bone/Implant Tracking Software)
- <div align="justify">This is Autoscoper v2.7 upgraded and maintained by <a href="https://sites.google.com/view/bardiya-akhbari/">Bardiya Akhbari</a>. Autoscoper is a 2D-to-3D registration software that gives the users the ability to track bones or implants in the videoradiographs. This version supports the particle swarm optimization algorithm and active feedback on normalized cross-correlation to improve the accuracy and speed of registration. Earlier version (v 2.0) was programmed by Dr. <a href="http://bknoerlein.de/index.html">Ben Knoerlein</a>. Version 2 combined the sources of both the CUDA and OpenCL versions and allows usage of either one. Version 2 has improved processing, several bug fixes, and new functionality, e.g. multi bone, batch processing, when compared to the original versions. The first version of this software was developed by Andy Loomis (original CUDA version) and Mark Howison (OpenCL reimplementation).</div>
Please cite this article when using the latest version of Autoscoper:
<div align="justify"><a href="https://www.sciencedirect.com/science/article/abs/pii/S0021929019303847"> Akhbari, B., Morton, A. M., Moore, D. C., Weiss, A-P. C., Wolfe, W. S., Crisco, J. J., 2019. Accuracy of Biplane Videoradiography for Quantifying Dynamic Wrist Kinematics, Journal of Biomechanics.</a></div>
You can find the full protocol in the Journal of Visualized Experiment:
<div align="justify"><a href="https://www.jove.com/t/62102/biplanar-videoradiography-to-study-wrist-distal-radioulnar"> Akhbari, B., Morton, A. M., Moore, D. C., Crisco, J. J. Biplanar Videoradiography to Study the Wrist and Distal Radioulnar Joints. <em>J. Vis. Exp.</em> (168), e62102, doi:10.3791/62102 (2021).
</a></div>
To watch the tutorials, please check out our <a href="https://www.youtube.com/playlist?list=PLQkw3tZ6MA9QaVnSUyh9K-OeY9dsjb2P1">YouTube playlist</a>.
Please help us to improve this software package by responding to this <a href="https://brown.co1.qualtrics.com/jfe/form/SV_4Nq1M03vthQzigm">quick survey</a>. | |
Registered: 2019-10-09 16:21 |