Difference between revisions of "Machine Learning for extracting Muscle features using Ultrasound"
From iis-projects
(Created page with "== Short Description == Ultrasound imaging is a non-invasive imaging technique that provides visible information on the structure of musculoskeletal tissues and organs. The de...") |
|||
(8 intermediate revisions by 2 users not shown) | |||
Line 1: | Line 1: | ||
+ | [[File:Ml_muscle_features.png|400px|thumb|right| ]] | ||
+ | |||
== Short Description == | == Short Description == | ||
Ultrasound imaging is a non-invasive imaging technique that provides visible information on the structure of musculoskeletal tissues and organs. The development of wearable ultrasound probes would enable real-time non-invasive continuous monitoring of physiological parameters during the day, which is of particular interest for medical therapies and sport science. However, efficient machine learning (ML) algorithms are required in order to automatically extract the physiological parameters of interest (i.e., the length of muscle fascicles). In the context of this thesis, you will work with the raw data acquired by a fully-digital ultrasound probe, to build ML algorithm for the extraction of such physiological features. | Ultrasound imaging is a non-invasive imaging technique that provides visible information on the structure of musculoskeletal tissues and organs. The development of wearable ultrasound probes would enable real-time non-invasive continuous monitoring of physiological parameters during the day, which is of particular interest for medical therapies and sport science. However, efficient machine learning (ML) algorithms are required in order to automatically extract the physiological parameters of interest (i.e., the length of muscle fascicles). In the context of this thesis, you will work with the raw data acquired by a fully-digital ultrasound probe, to build ML algorithm for the extraction of such physiological features. | ||
Line 6: | Line 8: | ||
The main tasks of this project are: | The main tasks of this project are: | ||
* Literature study of ultrasound imaging principles | * Literature study of ultrasound imaging principles | ||
− | + | * Neural network training and testing, based on available datasets of labeled images | |
− | + | * Possible optimization and deployment of the network on an embedded platform | |
− | * Neural network training and testing | ||
− | * | ||
=== Prerequisites === | === Prerequisites === | ||
Line 17: | Line 17: | ||
* C | * C | ||
− | ===Status: | + | ===Status: Completed=== |
− | + | Soley Hafthorsdottir | |
− | : Supervision: [[:User:Vsergei|Sergei Vostrikov]], [[:User:Cosandre|Andrea Cossettini]] | + | : Supervision: [[:User:Vsergei|Sergei Vostrikov]], [[:User:Cosandre|Andrea Cossettini]], Michael Rieder |
===Character=== | ===Character=== | ||
: 15% Literature Study | : 15% Literature Study | ||
− | : | + | : 10% Dataset processing |
: 35% Training and testing of networks | : 35% Training and testing of networks | ||
− | : | + | : 40% Deployment on FPGA or microcontroller |
===Professor=== | ===Professor=== | ||
: [http://www.iis.ee.ethz.ch/portrait/staff/lbenini.en.html Luca Benini] | : [http://www.iis.ee.ethz.ch/portrait/staff/lbenini.en.html Luca Benini] | ||
+ | |||
+ | ===Practical Details=== | ||
+ | * '''[[Project Plan]]''' | ||
+ | * '''[[Project Meetings]]''' | ||
+ | * '''[[Final Report]]''' | ||
+ | * '''[[Final Presentation]]''' | ||
+ | |||
[[#top|↑ top]] | [[#top|↑ top]] | ||
[[Category:Digital]] | [[Category:Digital]] | ||
− | [[Category: | + | [[Category:Completed]] |
[[Category:Semester Thesis]] | [[Category:Semester Thesis]] | ||
[[Category:Master Thesis]] | [[Category:Master Thesis]] | ||
[[Category:Cosandre]] | [[Category:Cosandre]] | ||
[[Category:Vsergei]] | [[Category:Vsergei]] | ||
− | |||
[[Category:LightProbe]] | [[Category:LightProbe]] | ||
+ | [[Category:Ultrasound]] | ||
+ | [[Category:UltrasoundDot]] | ||
+ | [[Category:2021]] |
Latest revision as of 16:57, 16 September 2022
Contents
Short Description
Ultrasound imaging is a non-invasive imaging technique that provides visible information on the structure of musculoskeletal tissues and organs. The development of wearable ultrasound probes would enable real-time non-invasive continuous monitoring of physiological parameters during the day, which is of particular interest for medical therapies and sport science. However, efficient machine learning (ML) algorithms are required in order to automatically extract the physiological parameters of interest (i.e., the length of muscle fascicles). In the context of this thesis, you will work with the raw data acquired by a fully-digital ultrasound probe, to build ML algorithm for the extraction of such physiological features.
Goal & Tasks
The goal of this project is to investigate the possibility of extracting relevant physiological information (the length of muscle fascicles) directly from raw Ultrasound data. The main tasks of this project are:
- Literature study of ultrasound imaging principles
- Neural network training and testing, based on available datasets of labeled images
- Possible optimization and deployment of the network on an embedded platform
Prerequisites
- Basics of Machine Learning (required) and Deep Learning (desirable)
- MATLAB
- Python (sklearn, tensorflow)
- C
Status: Completed
Soley Hafthorsdottir
- Supervision: Sergei Vostrikov, Andrea Cossettini, Michael Rieder
Character
- 15% Literature Study
- 10% Dataset processing
- 35% Training and testing of networks
- 40% Deployment on FPGA or microcontroller