Automatic unplugging detection for Ultrasound probes
From iis-projects
Contents
Short Description
Ultrasound imaging is a non-invasive imaging technique that provides visible information on the structure of musculoskeletal tissues and organs. Thanks to the increased availability of digital computation capabilities, fully-digital ultrasound systems are progressively replacing the more expensive and bulky analog solutions, offering on-probe computation capabilities. Within this framework, wearable fully-digital ultrasound probes are currently being developed. For a wearable system, low power consumption is a critical requirement. At the same time, fast data transfers via WiFi represent a significant source of energy drainage. Thus, wireless transmission of non-relevant information makes the overall system inefficient. The scope of this project is to reduce the power consumption of the WiFi transmission of a wireless ultrasound probe prototype, by adaptively reducing the frame rate of the images (hence, the transmission datarate) based on the captured signals. When the target object does not significantly change over time, the system can be operated at slower frame rates. When significant changes are detected, the system can be operated again at max speed. Upon detection of probe disconnection from the target, the system can be promptly stopped. All these will result in power saving, and thus increased operation time of the wearable system.
Goal & Tasks
In this mini-project you will tackle this problem by working on the microcontroller unit that receives the digitized ultrasound data and manages the WiFi communication. The main tasks are:
- implementing machine learning algorithms for automatic detection of disconnection of the probe from the target
- implementing algorithms to quantify the differences in successive sample acquisitions
- Microcontroller implementation of the control scheme to tune the frame rate based on the knowledge acquired by the above signal processing
Prerequisites
- C, Python
- Microcontrollers
- Machine learning
Status: Available
- Looking for Interested Students
- Supervision: Sergei Vostrikov, Andrea Cossettini
Character
- 20% Literature Study
- 40% Coding
- 40% Microcontrollers
