Ultrasound Entropy Imaging Based on the Kernel Density Estimation: A New Approach to Hepatic Steatosis Characterization
In this paper, we present the kernel density estimation (KDE)-based parallelized ultrasound entropy imaging and apply it for hepatic steatosis characterization. A KDE technique was used to estimate the probability density function (PDF) of ultrasound backscattered signals. The estimated PDF was util...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/24/3646 |
| _version_ | 1797381368945049600 |
|---|---|
| author | Ruiyang Gao Po-Hsiang Tsui Shuicai Wu Dar-In Tai Guangyu Bin Zhuhuang Zhou |
| author_facet | Ruiyang Gao Po-Hsiang Tsui Shuicai Wu Dar-In Tai Guangyu Bin Zhuhuang Zhou |
| author_sort | Ruiyang Gao |
| collection | DOAJ |
| description | In this paper, we present the kernel density estimation (KDE)-based parallelized ultrasound entropy imaging and apply it for hepatic steatosis characterization. A KDE technique was used to estimate the probability density function (PDF) of ultrasound backscattered signals. The estimated PDF was utilized to estimate the Shannon entropy to construct parametric images. In addition, the parallel computation technique was incorporated. Clinical experiments of hepatic steatosis were conducted to validate the feasibility of the proposed method. Seventy-two participants and 204 patients with different grades of hepatic steatosis were included. The experimental results show that the KDE-based entropy parameter correlates with log<sub>10</sub> (hepatic fat fractions) measured by magnetic resonance spectroscopy in the 72 participants (Pearson’s <i>r</i> = 0.52, <i>p</i> < 0.0001), and its areas under the receiver operating characteristic curves for diagnosing hepatic steatosis grades ≥ mild, ≥moderate, and ≥severe are 0.65, 0.73, and 0.80, respectively, for the 204 patients. The proposed method overcomes the drawbacks of conventional histogram-based ultrasound entropy imaging, including limited dynamic ranges and histogram settings dependence, although the diagnostic performance is slightly worse than conventional histogram-based entropy imaging. The proposed KDE-based parallelized ultrasound entropy imaging technique may be used as a new ultrasound entropy imaging method for hepatic steatosis characterization. |
| first_indexed | 2024-03-08T20:51:24Z |
| format | Article |
| id | doaj.art-1e0c1fce3fbd4b678cc4da9a045bf65b |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-08T20:51:24Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-1e0c1fce3fbd4b678cc4da9a045bf65b2023-12-22T14:03:11ZengMDPI AGDiagnostics2075-44182023-12-011324364610.3390/diagnostics13243646Ultrasound Entropy Imaging Based on the Kernel Density Estimation: A New Approach to Hepatic Steatosis CharacterizationRuiyang Gao0Po-Hsiang Tsui1Shuicai Wu2Dar-In Tai3Guangyu Bin4Zhuhuang Zhou5Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, ChinaDepartment of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan 333323, TaiwanDepartment of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, ChinaDepartment of Gastroenterology and Hepatology, Chang Gung Memorial Hospital at Linkou, Chang Gung University, Taoyuan 333423, TaiwanDepartment of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, ChinaDepartment of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, ChinaIn this paper, we present the kernel density estimation (KDE)-based parallelized ultrasound entropy imaging and apply it for hepatic steatosis characterization. A KDE technique was used to estimate the probability density function (PDF) of ultrasound backscattered signals. The estimated PDF was utilized to estimate the Shannon entropy to construct parametric images. In addition, the parallel computation technique was incorporated. Clinical experiments of hepatic steatosis were conducted to validate the feasibility of the proposed method. Seventy-two participants and 204 patients with different grades of hepatic steatosis were included. The experimental results show that the KDE-based entropy parameter correlates with log<sub>10</sub> (hepatic fat fractions) measured by magnetic resonance spectroscopy in the 72 participants (Pearson’s <i>r</i> = 0.52, <i>p</i> < 0.0001), and its areas under the receiver operating characteristic curves for diagnosing hepatic steatosis grades ≥ mild, ≥moderate, and ≥severe are 0.65, 0.73, and 0.80, respectively, for the 204 patients. The proposed method overcomes the drawbacks of conventional histogram-based ultrasound entropy imaging, including limited dynamic ranges and histogram settings dependence, although the diagnostic performance is slightly worse than conventional histogram-based entropy imaging. The proposed KDE-based parallelized ultrasound entropy imaging technique may be used as a new ultrasound entropy imaging method for hepatic steatosis characterization.https://www.mdpi.com/2075-4418/13/24/3646quantitative ultrasoundbackscatter envelope statisticsultrasound entropy imagingkernel density estimationprobability density functionultrasound tissue characterization |
| spellingShingle | Ruiyang Gao Po-Hsiang Tsui Shuicai Wu Dar-In Tai Guangyu Bin Zhuhuang Zhou Ultrasound Entropy Imaging Based on the Kernel Density Estimation: A New Approach to Hepatic Steatosis Characterization Diagnostics quantitative ultrasound backscatter envelope statistics ultrasound entropy imaging kernel density estimation probability density function ultrasound tissue characterization |
| title | Ultrasound Entropy Imaging Based on the Kernel Density Estimation: A New Approach to Hepatic Steatosis Characterization |
| title_full | Ultrasound Entropy Imaging Based on the Kernel Density Estimation: A New Approach to Hepatic Steatosis Characterization |
| title_fullStr | Ultrasound Entropy Imaging Based on the Kernel Density Estimation: A New Approach to Hepatic Steatosis Characterization |
| title_full_unstemmed | Ultrasound Entropy Imaging Based on the Kernel Density Estimation: A New Approach to Hepatic Steatosis Characterization |
| title_short | Ultrasound Entropy Imaging Based on the Kernel Density Estimation: A New Approach to Hepatic Steatosis Characterization |
| title_sort | ultrasound entropy imaging based on the kernel density estimation a new approach to hepatic steatosis characterization |
| topic | quantitative ultrasound backscatter envelope statistics ultrasound entropy imaging kernel density estimation probability density function ultrasound tissue characterization |
| url | https://www.mdpi.com/2075-4418/13/24/3646 |
| work_keys_str_mv | AT ruiyanggao ultrasoundentropyimagingbasedonthekerneldensityestimationanewapproachtohepaticsteatosischaracterization AT pohsiangtsui ultrasoundentropyimagingbasedonthekerneldensityestimationanewapproachtohepaticsteatosischaracterization AT shuicaiwu ultrasoundentropyimagingbasedonthekerneldensityestimationanewapproachtohepaticsteatosischaracterization AT darintai ultrasoundentropyimagingbasedonthekerneldensityestimationanewapproachtohepaticsteatosischaracterization AT guangyubin ultrasoundentropyimagingbasedonthekerneldensityestimationanewapproachtohepaticsteatosischaracterization AT zhuhuangzhou ultrasoundentropyimagingbasedonthekerneldensityestimationanewapproachtohepaticsteatosischaracterization |