Related Experiment Video
Updated: Jul 9, 2025

Near-Infrared Temperature Measurement Technique for Water Surrounding an Induction-heated Small Magnetic Sphere
Published on: April 30, 2018
A Data-Driven Approach for Estimating Temperature Variations Based on B-mode Ultrasound Images and Changes in
Luiz F R Oliveira1, Felipe M G França1,2, Wagner C A Pereira3
1Program Systems Engineering and Computer Science Program, COPPE, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil.
Accurate temperature monitoring during ultrasound thermal treatments is crucial. This study proposes a machine learning approach using B-mode ultrasound images to estimate regional temperatures, achieving high accuracy for safer patient treatments.
Area of Science:
- Medical Imaging
- Ultrasound Technology
- Machine Learning in Medicine
Background:
- Precise temperature control is essential for ultrasound thermal therapies to prevent treatment limitations or injury aggravation.
- Real-time temperature determination in targeted body regions remains a significant challenge in current medical practice.
- Machine learning is emerging as a powerful tool for enhancing ultrasound imaging and diagnostics.
Purpose of the Study:
- To develop a data-driven, supervised learning method for estimating temperature in specific regions of B-mode ultrasound images.
- To introduce a novel data modeling approach incorporating conventional B-mode images and parametric images based on changes in backscattered energy (CBE).
- To evaluate the performance of the proposed method against existing models in simulated scenarios.
Main Methods:
- Utilized a supervised learning framework to address the temperature estimation problem.
- Developed a novel data model integrating B-mode ultrasound image data with a parametric image derived from changes in backscattered energy (CBE).
- Compared the proposed approach with established machine learning models.
Main Results:
- The proposed data-driven approach, utilizing a Gradient Boosting model, demonstrated the ability to estimate temperature with a mean absolute error of approximately 0.5°C in a simulated environment.
- This level of accuracy is considered acceptable for practical applications in both physiotherapeutic treatments and high-intensity focused ultrasound (HIFU).
Conclusions:
- The developed machine learning model offers a promising solution for accurate real-time temperature estimation during ultrasound thermal treatments.
- The novel data modeling approach enhances the precision of temperature monitoring, potentially improving the safety and efficacy of ultrasound-guided therapies.
- This method holds significant potential for clinical applications, including physiotherapy and HIFU, by providing reliable temperature feedback.
Related Concept Videos
Ultrasonography
During an ultrasonography procedure, a handheld device called...
Temperature Measurement Sites
Oral: When assessing oral temperature, the thermometer tip should be placed under the tongue in the posterior sublingual pocket. It offers accurate readings and can be...
Absorption of Radiation
Assessing Blood pressure using a doppler ultrasound
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:
Equipments Used to Measure Body Temperature
Glass-bulb Thermometer:
Glass-bulb thermometers are hollow glass tubes with a bulb tip containing liquid such as ethanol or mercury. Historically, glass bulb mercury thermometers were the standard device to measure body temperature. Today, mercury thermometers are prohibited in many countries due to the hazardous effects of mercury and the risk of exposure if the glass bulb breaks. In general,...

