1
|
Liu Y, He B, Zhang Y, Lang X, Yao R, Pan L. A Study on a Parameter Estimator for the Homodyned K Distribution Based on Table Search for Ultrasound Tissue Characterization. ULTRASOUND IN MEDICINE & BIOLOGY 2023; 49:970-981. [PMID: 36631331 DOI: 10.1016/j.ultrasmedbio.2022.11.019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/18/2022] [Revised: 11/27/2022] [Accepted: 11/30/2022] [Indexed: 06/17/2023]
Abstract
OBJECTIVE The homodyned K (HK) distribution is considered to be the most suitable distribution in the context of tissue characterization; therefore, the search for a rapid and reliable parameter estimator for HK distribution is important. METHODS We propose a novel parameter estimator based on a table search (TS) for HK parameter estimates. The TS estimator can inherit the strength of conventional estimators by integrating various features and taking advantage of the TS method in a rapid and easy operation. Performance of the proposed TS estimator was evaluated and compared with that of XU (the estimation method based on X and U statistics) and artificial neural network (ANN) estimators. DISCUSSION The simulation results revealed that the TS estimator is superior to the XU and ANN estimators in terms of normalized standard deviations and relative root mean squared errors of parameter estimation, and is faster. Clinical experiments found that the area under the receiver operating curve for breast lesion classification using the parameters estimated by the TS estimator could reach 0.871. CONCLUSION The proposed TS estimator is more accurate, reliable and faster than the state-of-the-art XU and ANN estimators and has great potential for ultrasound tissue characterization based on the HK distribution.
Collapse
Affiliation(s)
- Yang Liu
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Bingbing He
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China.
| | - Yufeng Zhang
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Xun Lang
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Ruihan Yao
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Lingrui Pan
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| |
Collapse
|
2
|
Goryachev I, Tresansky AP, Ely GT, Chrzanowski SM, Nagy JA, Rutkove SB, Anthony BW. Comparison of Quantitative Ultrasound Methods to Classify Dystrophic and Obese Models of Skeletal Muscle. ULTRASOUND IN MEDICINE & BIOLOGY 2022; 48:1918-1932. [PMID: 35811236 DOI: 10.1016/j.ultrasmedbio.2022.05.022] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/25/2021] [Revised: 05/15/2022] [Accepted: 05/17/2022] [Indexed: 06/15/2023]
Abstract
In this study, we compared multiple quantitative ultrasound metrics for the purpose of differentiating muscle in 20 healthy, 10 dystrophic and 10 obese mice. High-frequency ultrasound scans were acquired on dystrophic (D2-mdx), obese (db/db) and control mouse hindlimbs. A total of 248 image features were extracted from each scan, using brightness-mode statistics, Canny edge detection metrics, Haralick features, envelope statistics and radiofrequency statistics. Naïve Bayes and other classifiers were trained on single and pairs of features. The a parameter from the Homodyned K distribution at 40 MHz achieved the best univariate classification (accuracy = 85.3%). Maximum classification accuracy of 97.7% was achieved using a logistic regression classifier on the feature pair of a2 (K distribution) at 30 MHz and brightness-mode variance at 40MHz. Dystrophic and obese mice have muscle with distinct acoustic properties and can be classified to a high level of accuracy using a combination of multiple features.
Collapse
Affiliation(s)
- Ivan Goryachev
- Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Anne Pigula Tresansky
- Harvard-MIT Program in Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Gregory Tsiang Ely
- Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Stephen M Chrzanowski
- Department of Neurology, Boston Children's Hospital, Boston, Massachusetts, USA; Department of Neurology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA
| | - Janice A Nagy
- Department of Neurology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA
| | - Seward B Rutkove
- Department of Neurology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA
| | - Brian W Anthony
- Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
| |
Collapse
|
3
|
Liu Y, Zhang Y, He B, Li Z, Lang X, Liang H, Chen J. An Improved Parameter Estimator of the Homodyned K Distribution Based on the Maximum Likelihood Method for Ultrasound Tissue Characterization. ULTRASONIC IMAGING 2022; 44:142-160. [PMID: 35674146 DOI: 10.1177/01617346221097867] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
The homodyned K distribution (HK) can generally describe the ultrasound backscatter envelope statistics distribution with parameters that have specific physical meaning. However, creating robust and reliable HK parameter estimates remains a crucial concern. The maximum likelihood estimator (MLE) usually yields a small variance and bias in parameter estimation. Thus, two recent studies have attempted to use MLE for parameter estimation of HK distribution. However, some of the statements in these studies are not fully justified and they may hinder the application of parameter estimation of HK distribution based on MLE. In this study, we propose a new parameter estimator for the HK distribution based on the MLE (i.e., MLE1), which overcomes the disadvantages of conventional MLE of HK distribution. The MLE1 was compared with other estimators, such as XU estimator (an estimation method based on the first moment of the intensity and tow log-moments) and ANN estimator (an estimation method based on artificial neural networks). We showed that the estimations of parameters α and k are the best overall (in terms of the relative bias, normalized standard deviation, and relative root mean squared errors) using the proposed MLE1 compared with the others based on the simulated data when the sample size was N = 1000. Moreover, we assessed the usefulness of the proposed MLE1 when the number of scatterers per resolution cell was high (i.e., α up to 80) and when the sample size was small (i.e., N = 100), and we found a satisfactory result. Tests on simulated ultrasound images based on Field II were performed and the results confirmed that the proposed MLE1 is feasible and reliable for the parameter estimation from the ultrasonic envelope signal. Therefore, the proposed MLE1 can accurately estimate the HK parameters with lower uncertainty, which presents a potential practical value for further ultrasonic applications.
Collapse
Affiliation(s)
- Yang Liu
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Yufeng Zhang
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Bingbing He
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Zhiyao Li
- The Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, China
| | - Xun Lang
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Hong Liang
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| | - Jianhua Chen
- Department of Electronic Engineering, Information School, Yunnan University, Kunming, Yunnan, China
| |
Collapse
|
4
|
Park J, Lee JM, Lee G, Jeon SK, Joo I. Quantitative Evaluation of Hepatic Steatosis Using Advanced Imaging Techniques: Focusing on New Quantitative Ultrasound Techniques. Korean J Radiol 2022; 23:13-29. [PMID: 34983091 PMCID: PMC8743150 DOI: 10.3348/kjr.2021.0112] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Revised: 07/26/2021] [Accepted: 08/31/2021] [Indexed: 12/12/2022] Open
Abstract
Nonalcoholic fatty liver disease, characterized by excessive accumulation of fat in the liver, is the most common chronic liver disease worldwide. The current standard for the detection of hepatic steatosis is liver biopsy; however, it is limited by invasiveness and sampling errors. Accordingly, MR spectroscopy and proton density fat fraction obtained with MRI have been accepted as non-invasive modalities for quantifying hepatic steatosis. Recently, various quantitative ultrasonography techniques have been developed and validated for the quantification of hepatic steatosis. These techniques measure various acoustic parameters, including attenuation coefficient, backscatter coefficient and speckle statistics, speed of sound, and shear wave elastography metrics. In this article, we introduce several representative quantitative ultrasonography techniques and their diagnostic value for the detection of hepatic steatosis.
Collapse
Affiliation(s)
- Junghoan Park
- Department of Radiology, Seoul National University Hospital, Seoul, Korea
| | - Jeong Min Lee
- Department of Radiology, Seoul National University Hospital, Seoul, Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
- Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Korea.
| | - Gunwoo Lee
- Ultrasound R&D 2 Group, Health & Medical Equipment Business, Samsung Electronics Co., Ltd., Seoul, Korea
| | - Sun Kyung Jeon
- Department of Radiology, Seoul National University Hospital, Seoul, Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| | - Ijin Joo
- Department of Radiology, Seoul National University Hospital, Seoul, Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| |
Collapse
|
5
|
Qayyum A, Qadir J, Bilal M, Al-Fuqaha A. Secure and Robust Machine Learning for Healthcare: A Survey. IEEE Rev Biomed Eng 2021; 14:156-180. [PMID: 32746371 DOI: 10.1109/rbme.2020.3013489] [Citation(s) in RCA: 81] [Impact Index Per Article: 27.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
Recent years have witnessed widespread adoption of machine learning (ML)/deep learning (DL) techniques due to their superior performance for a variety of healthcare applications ranging from the prediction of cardiac arrest from one-dimensional heart signals to computer-aided diagnosis (CADx) using multi-dimensional medical images. Notwithstanding the impressive performance of ML/DL, there are still lingering doubts regarding the robustness of ML/DL in healthcare settings (which is traditionally considered quite challenging due to the myriad security and privacy issues involved), especially in light of recent results that have shown that ML/DL are vulnerable to adversarial attacks. In this paper, we present an overview of various application areas in healthcare that leverage such techniques from security and privacy point of view and present associated challenges. In addition, we present potential methods to ensure secure and privacy-preserving ML for healthcare applications. Finally, we provide insight into the current research challenges and promising directions for future research.
Collapse
|
6
|
Kim KB, Kim GH, Song DH, Park HJ, Kim CW. Automatic segmentation of liver/kidney area with double-layered fuzzy C-means and the utility of hepatorenal index for fatty liver severity classification. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2020. [DOI: 10.3233/jifs-191850] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Affiliation(s)
- Kwang Baek Kim
- Division of Computer Software Engineering, Silla University, Busan, Korea
| | - Gwang Ha Kim
- Department of Internal Medicine, School of Medicine and Biomedical Research Institute, Pusan National University, Pusan National University Hospital, Busan, Korea
| | - Doo Heon Song
- Department of Computer Games, Yong-in SongDam College, Yongin, Korea
| | - Hyun Jun Park
- Division of Software Convergence, Cheongju University, Cheongju, Korea
| | - Chang Won Kim
- Department of Radiology, School of Medicine and Biomedical Research Institute, Pusan National University, Pusan National University Hospital, Busan, Korea
| |
Collapse
|
7
|
Zhou Z, Zhang Q, Wu W, Lin YH, Tai DI, Tseng JH, Lin YR, Wu S, Tsui PH. Hepatic steatosis assessment using ultrasound homodyned-K parametric imaging: the effects of estimators. Quant Imaging Med Surg 2019; 9:1932-1947. [PMID: 31929966 PMCID: PMC6942974 DOI: 10.21037/qims.2019.08.03] [Citation(s) in RCA: 20] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Abstract
BACKGROUND The homodyned-K (HK) distribution is an important statistical model for describing ultrasound backscatter envelope statistics. HK parametric imaging has shown potential for characterizing hepatic steatosis. However, the feasibility of HK parametric imaging in assessing human hepatic steatosis in vivo remains unclear. METHODS In this paper, ultrasound HK μ parametric imaging was proposed for assessing human hepatic steatosis in vivo. Two recent estimators for the HK model, RSK (the level-curve method that uses the signal-to-noise ratio (SNR), skewness, and kurtosis based on the fractional moments of the envelope) and XU (the estimation method based on the first moment of the intensity and two log-moments, namely X- and U-statistics), were investigated. Liver donors (n=72) and patients (n=204) were recruited to evaluate hepatic fat fractions (HFFs) using magnetic resonance spectroscopy and to evaluate the stages of fatty liver disease (normal, mild, moderate, and severe) using liver biopsy with histopathology. Livers were scanned using a 3-MHz ultrasound to construct μ RSK and μ XU images to correlate with HFF analyses and fatty liver stages. The μ RSK and μ XU parametric images were constructed using the sliding window technique with the window side length (WSL) =1-9 pulse lengths (PLs). The diagnostic values of the μ RSK and μ XU parametric imaging methods were evaluated using receiver operating characteristic (ROC) curves. RESULTS For the 72 participants in Group A, the μ RSK parametric imaging with WSL =2-9 PLs exhibited similar correlation with log10(HFF), and the μ RSK parametric imaging with WSL = 3 PLs had the highest correlation with log10(HFF) (r=0.592); the μ XU parametric imaging with WSL =1-9 PLs exhibited similar correlation with log10(HFF), and the μ XU parametric imaging with WSL =1 PL had the highest correlation with log10(HFF) (r=0.628). For the 204 patients in Group B, the areas under the ROC (AUROCs) obtained using μ RSK for fatty stages ≥ mild (AUROC1), ≥ moderate (AUROC2), and ≥ severe (AUROC3) were (AUROC1, AUROC2, AUROC3) = (0.56, 0.57, 0.53), (0.68, 0.72, 0.75), (0.73, 0.78, 0.80), (0.74, 0.77, 0.79), (0.74, 0.78, 0.79), (0.75, 0.80, 0.82), (0.74, 0.77, 0.83), (0.74, 0.78, 0.84) and (0.73, 0.76, 0.83) for WSL =1, 2, 3, 4, 5, 6, 7, 8 and 9 PLs, respectively. The AUROCs obtained using μ XU for fatty stages ≥ mild, ≥ moderate, and ≥ severe were (AUROC1, AUROC2, AUROC3) = (0.75, 0.83, 0.81), (0.74, 0.80, 0.80), (0.76, 0.82, 0.82), (0.74, 0.80, 0.84), (0.76, 0.80, 0.83), (0.75, 0.80, 0.84), (0.75, 0.79, 0.85), (0.75, 0.80, 0.85) and (0.73, 0.77, 0.83) for WSL = 1, 2, 3, 4, 5, 6, 7, 8 and 9 PLs, respectively. CONCLUSIONS Both the μ RSK and μ XU parametric images are feasible for evaluating human hepatic steatosis. The WSL exhibits little impact on the diagnosing performance of the μ RSK and μ XU parametric imaging. The μ XU parametric imaging provided improved performance compared to the μ RSK parametric imaging in characterizing human hepatic steatosis in vivo.
Collapse
Affiliation(s)
- Zhuhuang Zhou
- College of Life Science and Bioengineering, Beijing University of Technology, Beijing 100124, China
| | - Qiyu Zhang
- College of Life Science and Bioengineering, Beijing University of Technology, Beijing 100124, China
| | - Weiwei Wu
- College of Biomedical Engineering, Capital Medical University, Beijing 100069, China
| | - Ying-Hsiu Lin
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
| | - Dar-In Tai
- Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital at Linkou, Chang Gung University, Taoyuan 33302, Taiwan
| | - Jeng-Hwei Tseng
- Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan 33302, Taiwan
| | - Yi-Ru Lin
- Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei 10607, Taiwan
| | - Shuicai Wu
- College of Life Science and Bioengineering, Beijing University of Technology, Beijing 100124, China
| | - Po-Hsiang Tsui
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
- Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan 33302, Taiwan
- Medical Imaging Research Center, Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan 33302, Taiwan
| |
Collapse
|
8
|
Marsh JN, Korenblat KM, Liu TC, McCarthy JE, Wickline SA. Resolution of Murine Toxic Hepatic Injury Quantified With Ultrasound Entropy Metrics. ULTRASOUND IN MEDICINE & BIOLOGY 2019; 45:2777-2786. [PMID: 31320149 PMCID: PMC6718339 DOI: 10.1016/j.ultrasmedbio.2019.06.412] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/27/2018] [Revised: 06/19/2019] [Accepted: 06/21/2019] [Indexed: 06/10/2023]
Abstract
Image-based classification of liver disease generally lacks specificity for distinguishing between acute, resolvable injury and chronic irreversible injury. We propose that ultrasound radiofrequency data acquired in vivo from livers subjected to toxic drug injury can be analyzed with information theoretic detectors to derive entropy metrics, which classify a statistical distribution of pathologic scatterers that dissipate over time as livers heal. Here we exposed 38 C57BL/6 mice to carbon tetrachloride to cause liver damage, and imaged livers in vivo 1, 4, 8, 12 and 18 d after exposure with a broadband 15-MHz probe. Selected entropy metrics manifested monotonic recovery to normal values over time as livers healed, and were correlated directly with progressive restoration of liver architecture by histologic assessment (r2 ≥ 0.95, p < 0.004). Thus, recovery of normal liver microarchitecture after toxic exposure can be delineated sensitively with entropy metrics.
Collapse
Affiliation(s)
- Jon N Marsh
- Department of Immunology & Pathology, Washington University School of Medicine, St. Louis, Missouri, USA
| | - Kevin M Korenblat
- Department of Internal Medicine-Gastroenterology, Washington University School of Medicine, St. Louis, Missouri, USA
| | - Ta-Chiang Liu
- Department of Anatomic & Molecular Pathology, Washington University School of Medicine, St. Louis, Missouri, USA
| | - John E McCarthy
- Department of Mathematics and Statistics, Washington University, St. Louis, Missouri, USA
| | - Samuel A Wickline
- University of South Florida Health Heart Institute, Morsani School of Medicine, Tampa, Florida, USA.
| |
Collapse
|
9
|
Lin YH, Wan YL, Tai DI, Tseng JH, Wang CY, Tsai YW, Lin YR, Chang TY, Tsui PH. Considerations of Ultrasound Scanning Approaches in Non-alcoholic Fatty Liver Disease Assessment through Acoustic Structure Quantification. ULTRASOUND IN MEDICINE & BIOLOGY 2019; 45:1955-1969. [PMID: 31130411 DOI: 10.1016/j.ultrasmedbio.2019.04.018] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/06/2018] [Revised: 04/10/2019] [Accepted: 04/12/2019] [Indexed: 02/07/2023]
Abstract
Non-alcoholic fatty liver disease (NAFLD) is a risk factor for hepatic fibrosis and cirrhosis. Acoustic structure quantification (ASQ), based on statistical analysis of ultrasound echoes, is an emerging technique for hepatic steatosis diagnosis. A standardized measurement protocol for ASQ analysis was suggested previously; however, an optimal ultrasound scanning approach has not been concluded thus far. In this study, the suitability of scanning approaches for the ASQ-based evaluation of hepatic steatosis was investigated. Hepatic fat fractions (HFFs; liver segments VIII, III and VI) of 70 living liver donors were assessed with magnetic resonance spectroscopy. A clinical ultrasound machine equipped with a 3-MHz convex transducer was used to scan each participant using the intercostal, epigastric and subcostal planes to acquire raw data for estimating two ASQ parameters (Cm2 and focal disturbance [FD] ratio) of segments VIII, III and VI, respectively. The parameters were plotted as functions of the HFF for calculating the values of the correlation coefficient (r) and probability value (p). The diagnostic performance of the parameters in discriminating between the normal and steatotic (≥5 and ≥10%) groups was also compared using receiver operating characteristic (ROC) curves. The Cm2 and FD ratio values measured using the epigastric and subcostal planes did not correlate with the severity of hepatic steatosis. However, intercostal imaging exhibited a higher correlation between the ASQ parameters and HFF (r = -0.64, p < 0.001). The diagnostic performance of Cm2 and FD ratio in detecting hepatic steatosis using intercostal imaging was also satisfactory (areas under ROC curves >0.8). Intercostal imaging is an appropriate scanning approach for ASQ analysis of the liver.
Collapse
Affiliation(s)
- Ying-Hsiu Lin
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | - Yung-Liang Wan
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan; Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
| | - Dar-In Tai
- Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital at Linkou, Chang Gung University, Taoyuan, Taiwan
| | - Jeng-Hwei Tseng
- Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
| | - Chiao-Yin Wang
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Graduate Institute of Clinical Medical Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | - Yu-Wei Tsai
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | - Yi-Ru Lin
- Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan
| | - Tu-Yung Chang
- Department of Public Health, College of Public Health, China Medical University, Taichung, Taiwan
| | - Po-Hsiang Tsui
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan; Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan.
| |
Collapse
|
10
|
Hepatic Steatosis Assessment Using Quantitative Ultrasound Parametric Imaging Based on Backscatter Envelope Statistics. APPLIED SCIENCES-BASEL 2019. [DOI: 10.3390/app9040661] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
Abstract
Hepatic steatosis is a key manifestation of non-alcoholic fatty liver disease (NAFLD). Early detection of hepatic steatosis is of critical importance. Currently, liver biopsy is the clinical golden standard for hepatic steatosis assessment. However, liver biopsy is invasive and associated with sampling errors. Ultrasound has been recommended as a first-line diagnostic test for the management of NAFLD. However, B-mode ultrasound is qualitative and can be affected by factors including image post-processing parameters. Quantitative ultrasound (QUS) aims to extract quantified acoustic parameters from the ultrasound backscattered signals for ultrasound tissue characterization and can be a complement to conventional B-mode ultrasound. QUS envelope statistics techniques, both statistical model-based and non-model-based, have shown potential for hepatic steatosis characterization. However, a state-of-the-art review of hepatic steatosis assessment using envelope statistics techniques is still lacking. In this paper, envelope statistics-based QUS parametric imaging techniques for characterizing hepatic steatosis are reviewed and discussed. The reviewed ultrasound envelope statistics parametric imaging techniques include acoustic structure quantification imaging, ultrasound Nakagami imaging, homodyned-K imaging, kurtosis imaging, and entropy imaging. Future developments are suggested.
Collapse
|
11
|
Anwar SM, Majid M, Qayyum A, Awais M, Alnowami M, Khan MK. Medical Image Analysis using Convolutional Neural Networks: A Review. J Med Syst 2018; 42:226. [DOI: 10.1007/s10916-018-1088-1] [Citation(s) in RCA: 247] [Impact Index Per Article: 41.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2018] [Accepted: 09/25/2018] [Indexed: 01/03/2023]
|
12
|
Fang J, Zhou Z, Chang NF, Wan YL, Tsui PH. Ultrasound parametric imaging of hepatic steatosis using the homodyned-K distribution: An animal study. ULTRASONICS 2018; 87:91-102. [PMID: 29476945 DOI: 10.1016/j.ultras.2018.02.015] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/27/2017] [Revised: 01/12/2018] [Accepted: 02/14/2018] [Indexed: 06/08/2023]
Abstract
Hepatic steatosis is an abnormal state where excess lipid mass is accumulated in hepatocyte vesicles. Backscattered ultrasound signals received from the liver contain useful information regarding the degree of steatosis in the liver. The homodyned-K (HK) distribution has been demonstrated as a general model for ultrasound backscattering. The estimator based on the first three integer moments (denoted as "FTM") of the intensity has potential for practical applications because of its simplicity and low computational complexity. This study explored the diagnostic performance of HK parametric imaging based on the FTM method in the assessment of hepatic steatosis. Phantom experiments were initially conducted using the sliding window technique to determine an appropriate window size length (WSL) for HK parametric imaging. Subsequently, hepatic steatosis was induced in male Wistar rats fed a methionine- and choline-deficient (MCD) diet for 0 (i.e., normal control), 1, 2, 4, 6, and 8 weeks (n = 36; six rats in each group). After completing the scheduled MCD diet, ultrasound B-mode and HK imaging of the rat livers were performed in vivo and histopathological examinations were conducted to score the degree of hepatic steatosis. HK parameters μ (related to scatterer number density) and k (related to scatterer periodicity) were expressed as functions of the steatosis stage in terms of the median and interquartile range (IQR). Receiver operating characteristic (ROC) curve analysis was conducted to assess the diagnostic performance levels of the μ and k parameters. The results showed that an appropriate WSL for HK parametric imaging is seven times the pulse length of the transducer. The median value of the μ parameter increased monotonically from 0.194 (IQR: 0.18-0.23) to 0.893 (IQR: 0.64-1.04) as the steatosis stage increased. Concurrently, the median value of the k parameter increased from 0.279 (IQR: 0.26-0.31) to 0.5 (IQR: 0.41-0.54) in the early stages (normal to mild) and decreased to 0.39 (IQR: 0.29-0.45) in the advanced stages (moderate to severe). The areas under the ROC curves obtained using (μ, k) were (0.947, 0.804), (0.914, 0.575), and (0.813, 0.604) for the steatosis stages of ≥mild, ≥moderate, and ≥severe, respectively. The current findings suggest that ultrasound HK parametric imaging based on FTM estimation has great potential for future clinical diagnoses of hepatic steatosis.
Collapse
Affiliation(s)
- Jui Fang
- Ph. D. Program in Biomedical Engineering, College of Engineering, Chang Gung University, Taoyuan, Taiwan
| | - Zhuhuang Zhou
- College of Life Science and Bioengineering, Beijing University of Technology, Beijing, China; Faculty of Information Technology, Beijing University of Technology, Beijing, China
| | - Ning-Fang Chang
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | - Yung-Liang Wan
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Medical Imaging Research Center, Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan; Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan.
| | - Po-Hsiang Tsui
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Medical Imaging Research Center, Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan; Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan.
| |
Collapse
|
13
|
Extreme Learning Machine Framework for Risk Stratification of Fatty Liver Disease Using Ultrasound Tissue Characterization. J Med Syst 2017; 41:152. [DOI: 10.1007/s10916-017-0797-1] [Citation(s) in RCA: 70] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2017] [Accepted: 08/08/2017] [Indexed: 12/17/2022]
|
14
|
Effects of Fatty Infiltration of the Liver on the Shannon Entropy of Ultrasound Backscattered Signals. ENTROPY 2016. [DOI: 10.3390/e18090341] [Citation(s) in RCA: 27] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
|
15
|
Manzoor U, Nefti S, Ferdinando M. Investigating the Effectiveness of Wavelet Approximations in Resizing Images for Ultrasound Image Classification. J Med Syst 2016; 40:221. [PMID: 27586590 DOI: 10.1007/s10916-016-0573-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2016] [Accepted: 08/11/2016] [Indexed: 11/26/2022]
Abstract
Images are difficult to classify and annotate but the availability of digital image databases creates a constant demand for tools that automatically analyze image content and describe it with either a category or a set of variables. Ultrasound Imaging is very popular and is widely used to see the internal organ(s) condition of the patient. The main target of this research is to develop a robust image processing techniques for a better and more accurate medical image retrieval and categorization. This paper looks at an alternative to feature extraction for image classification such as image resizing technique. A new mean for image resizing using wavelet transform is proposed. Results, using real medical images, have shown the effectiveness of the proposed technique for classification task comparing to bi-cubic interpolation and feature extraction.
Collapse
Affiliation(s)
- Umar Manzoor
- King Abdulaziz University, Jeddah, Saudi Arabia.
| | - Samia Nefti
- School of Computing, Science and Engineering, The University of Salford, Greater Manchester, Salford, UK
| | - Milella Ferdinando
- School of Computing, Science and Engineering, The University of Salford, Greater Manchester, Salford, UK
| |
Collapse
|