Related Experiment Videos
Liver steatosis classification using high-frequency ultrasound
Wen-Chun Yeh1, Yung-Ming Jeng, Cheng-Han Li
1Department of Electrical Engineering, National Taiwan University, No. 1 Sec. 4 Roosevelt Road, Taipei 106, Taiwan.
Ultrasound in Medicine & Biology
|May 4, 2005
Summary
High-frequency ultrasound significantly improves the accuracy of diagnosing liver steatosis. This advanced imaging technique offers better characterization of fatty liver disease compared to lower frequencies.
Area of Science:
- Medical Imaging
- Hepatology
- Ultrasound Technology
Background:
- Liver steatosis, or fatty liver disease, is a growing health concern.
- Accurate grading of steatosis is crucial for patient management and treatment.
- Current diagnostic methods may have limitations in precision.
Purpose of the Study:
- To evaluate the efficacy of high-frequency B-mode ultrasound in determining liver steatosis grade.
- To compare the diagnostic performance of 25 MHz ultrasound with lower frequencies.
Main Methods:
- Acquisition of high-frequency (25 MHz) B-mode ultrasound images from 19 human liver samples.
- Extraction of image features using gray-level concurrence and wavelet transform.
- Classification of steatosis grades using a support vector machine (SVM) classifier.
- Correlation of ultrasound-based classification with histologic examination results.
Main Results:
- Achieved classification accuracies of 90.5% (2 classes), 85.8% (3 classes), and 82.6% (4 classes).
- Performance was markedly superior to results obtained at 7 MHz.
- High-frequency ultrasound demonstrated enhanced accuracy in characterizing liver steatosis.
Conclusions:
- High-frequency B-mode ultrasound is a promising tool for accurate liver steatosis characterization.
- This technology offers improved diagnostic capabilities over conventional ultrasound frequencies.
- Potential limitations and solutions for clinical application of high-frequency ultrasound in liver imaging were discussed.