1
|
Baek J, Basavarajappa L, Margolis R, Arthur L, Li J, Hoyt K, Parker KJ. Multiparametric ultrasound imaging for early-stage steatosis: Comparison with magnetic resonance imaging-based proton density fat fraction. Med Phys 2024; 51:1313-1325. [PMID: 37503961 PMCID: PMC11238269 DOI: 10.1002/mp.16648] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2022] [Revised: 06/23/2023] [Accepted: 07/04/2023] [Indexed: 07/29/2023] Open
Abstract
BACKGROUND The prevalence of liver diseases, especially steatosis, requires a more convenient and noninvasive tool for liver diagnosis, which can be a surrogate for the gold standard biopsy. Magnetic resonance (MR) measurement offers potential, however ultrasound (US) has better accessibility than MR. PURPOSE This study aims to suggest a multiparametric US approach which demonstrates better quantification and imaging performance than MR imaging-based proton density fat fraction (MRI-PDFF) for hepatic steatosis assessment. METHODS We investigated early-stage steatosis to evaluate our approach. An in vivo (within the living) animal study was performed. Fat inclusions were accumulated in the animal livers by feeding a methionine and choline deficient (MCD) diet for 2 weeks. The animals (n = 19) underwent US and MR imaging, and then their livers were excised for histological staining. From the US, MR, and histology images, fat accumulation levels were measured and compared: multiple US parameters; MRI-PDFF; histology fat percentages. Seven individual US parameters were extracted using B-mode measurement, Burr distribution estimation, attenuation estimation, H-scan analysis, and shear wave elastography. Feature selection was performed, and the selected US features were combined, providing quantification of fat accumulation. The combined parameter was used for visualizing the localized probability of fat accumulation level in the liver; This procedure is known as disease-specific imaging (DSI). RESULTS The combined US parameter can sensitively assess fat accumulation levels, which is highly correlated with histology fat percentage (R = 0.93, p-value < 0.05) and outperforms the correlation between MRI-PDFF and histology (R = 0.89, p-value < 0.05). Although the seven individual US parameters showed lower correlation with histology compared to MRI-PDFF, the multiparametric analysis enabled US to outperform MR. Furthermore, this approach allowed DSI to detect and display gradual increases in fat accumulation. From the imaging output, we measured the color-highlighted area representing fatty tissues, and the fat fraction obtained from DSI and histology showed strong agreement (R = 0.93, p-value < 0.05). CONCLUSIONS We demonstrated that fat quantification utilizing a combination of multiple US parameters achieved higher performance than MRI-PDFF; therefore, our multiparametric analysis successfully combined selected features for hepatic steatosis characterization. We anticipate clinical use of our proposed multiparametric US analysis, which could be beneficial in assessing steatosis in humans.
Collapse
Affiliation(s)
- Jihye Baek
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, New York, USA
| | - Lokesh Basavarajappa
- Department of Bioengineering, University of Texas at Dallas, Richardson, Texas, USA
| | - Ryan Margolis
- Department of Bioengineering, University of Texas at Dallas, Richardson, Texas, USA
| | - Leroy Arthur
- Department of Bioengineering, University of Texas at Dallas, Richardson, Texas, USA
| | - Junjie Li
- Department of Bioengineering, University of Texas at Dallas, Richardson, Texas, USA
| | - Kenneth Hoyt
- Department of Bioengineering, University of Texas at Dallas, Richardson, Texas, USA
| | - Kevin J. Parker
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, New York, USA
| |
Collapse
|
2
|
Baek J, Qin SS, Prieto PA, Parker KJ. H-Scan Discrimination for Tumor Microenvironmental Heterogeneity in Melanoma. ULTRASOUND IN MEDICINE & BIOLOGY 2024; 50:268-276. [PMID: 37993356 PMCID: PMC10794040 DOI: 10.1016/j.ultrasmedbio.2023.10.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 10/24/2023] [Accepted: 10/28/2023] [Indexed: 11/24/2023]
Abstract
OBJECTIVE Melanoma is a form of malignant skin cancer that exhibits significant inter-tumoral differences in the tumor microenvironment (TME) secondary to genetic mutations. The heterogeneity may be subtle but can complicate the treatment of metastatic melanoma, contributing to a high mortality rate. Therefore, developing an accurate and non-invasive procedure to discriminate microenvironmental heterogeneity to facilitate therapy selection is an important goal. METHODS In vivo murine melanoma models that recapitulate human disease using synchronous implanted YUMM 1.7 (Yale University Mouse Melanoma) and YUMMER 1.7 (Yale University Mouse Melanoma Exposed to Radiation) murine melanoma lines were investigated. Mice were treated with antibodies to modulate the immune response and longitudinally scanned with ultrasound (US). US radiofrequency data were processed using the H-scan analysis, attenuation estimation and B-mode processing to extract five US features. The measures were used to compare different TMEs (YUMMER vs. YUMM) and responses to immunomodulatory therapies with CD8 depletion or programmed cell death protein 1 (PD-1) inhibition. RESULTS Multiparametric analysis produced a combined H-scan parameter, resolving significant differences (i) between untreated YUMMER and YUMM and (ii) between untreated, PD-1-treated and CD8-treated YUMMER. However, more importantly, the B-mode and attenuation measures failed to differentiate YUMMER and YUMM and to monitor treatment responses, indicating that H-scan is required to differentiate subtle differences within the TME. CONCLUSION We anticipate that the H-scan analysis could discriminate heterogeneous melanoma metastases and guide diagnosis and treatment selection, potentially reducing the need for invasive biopsies or immunologic procedures.
Collapse
Affiliation(s)
- Jihye Baek
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA
| | - Shuyang S Qin
- Department of Microbiology & Immunology, University of Rochester School of Medicine & Dentistry, Rochester, NY, USA
| | - Peter A Prieto
- Department of Surgery, University of Rochester Medical Center, Rochester, NY, USA
| | - Kevin J Parker
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA.
| |
Collapse
|
3
|
Timaná J, Chahuara H, Basavarajappa L, Basarab A, Hoyt K, Lavarello R. Simultaneous imaging of ultrasonic relative backscatter and attenuation coefficients for quantitative liver steatosis assessment. Sci Rep 2023; 13:8898. [PMID: 37264043 DOI: 10.1038/s41598-023-33964-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Accepted: 04/21/2023] [Indexed: 06/03/2023] Open
Abstract
Prevalence of liver disease is continuously increasing and nonalcoholic fatty liver disease (NAFLD) is the most common etiology. We present an approach to detect the progression of liver steatosis based on quantitative ultrasound (QUS) imaging. This study was performed on a group of 55 rats that were subjected to a control or methionine and choline deficient (MCD) diet known to induce NAFLD. Ultrasound (US) measurements were performed at 2 and 6 weeks. Thereafter, animals were humanely euthanized and livers excised for histological analysis. Relative backscatter and attenuation coefficients were simultaneously estimated from the US data and envelope signal-to-noise ratio was calculated to train a regression model for: (1) fat fraction percentage estimation and (2) performing classification according to Brunt's criteria in grades (0 <5%; 1, 5-33%; 2, >33-66%; 3, >66%) of liver steatosis. The trained regression model achieved an [Formula: see text] of 0.97 (p-value < 0.01) and a RMSE of 3.64. Moreover, the classification task reached an accuracy of 94.55%. Our results suggest that in vivo QUS is a promising noninvasive imaging modality for the early assessment of NAFLD.
Collapse
Affiliation(s)
- José Timaná
- Laboratorio de Imágenes Médicas, Pontificia Universidad Católica del Perú, Lima, Peru
| | - Hector Chahuara
- Laboratorio de Imágenes Médicas, Pontificia Universidad Católica del Perú, Lima, Peru
| | - Lokesh Basavarajappa
- Department of Bioengineering, University of Texas at Dallas, Richardson, TX, USA
| | - Adrian Basarab
- INSA-Lyon, UCBL, CNRS, Inserm, CREATIS UMR 5220 U1294, Université de Lyon, Villeurbanne, France
| | - Kenneth Hoyt
- Department of Bioengineering, University of Texas at Dallas, Richardson, TX, USA
| | - Roberto Lavarello
- Laboratorio de Imágenes Médicas, Pontificia Universidad Católica del Perú, Lima, Peru.
| |
Collapse
|
4
|
Singla R, Hu R, Ringstrom C, Lessoway V, Reid J, Nguan C, Rohling R. The Kidneys Are Not All Normal: Transplanted Kidneys and Their Speckle Distributions. ULTRASOUND IN MEDICINE & BIOLOGY 2023; 49:1268-1274. [PMID: 36842904 DOI: 10.1016/j.ultrasmedbio.2023.01.013] [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: 09/13/2022] [Revised: 12/21/2022] [Accepted: 01/19/2023] [Indexed: 05/11/2023]
Abstract
OBJECTIVE Modelling ultrasound speckle to characterise tissue properties has generated considerable interest. As speckle is dependent on the underlying tissue architecture, modelling it may aid in tasks such as segmentation or disease detection. For the transplanted kidney, where ultrasound is used to investigate dysfunction, it is unknown which statistical distribution best characterises such speckle. This applies to the regions of the transplanted kidney: the cortex, the medulla and the central echogenic complex. Furthermore, it is unclear how these distributions vary by patient variables such as age, sex, body mass index, primary disease or donor type. These traits may influence speckle modelling given their influence on kidney anatomy. We investigate these two aims. METHODS B-mode images from n = 821 kidney transplant recipients (one image per recipient) were automatically segmented into the cortex, medulla and central echogenic complex using a neural network. Seven distinct probability distributions were fitted to each region's histogram, and statistical analysis was performed. DISCUSSION The Rayleigh and Nakagami distributions had model parameters that differed significantly between the three regions (p ≤ 0.05). Although both had excellent goodness of fit, the Nakagami had higher Kullbeck-Leibler divergence. Recipient age correlated weakly with scale in the cortex (Ω: ρ = 0.11, p = 0.004), while body mass index correlated weakly with shape in the medulla (m: ρ = 0.08, p = 0.04). Neither sex, primary disease nor donor type exhibited any correlation. CONCLUSION We propose the Nakagami distribution be used to characterize transplanted kidneys regionally independent of disease etiology and most patient characteristics.
Collapse
Affiliation(s)
- Rohit Singla
- School of Biomedical Engineering, University of British Columbia, Vancouver, British Columbia, Canada.
| | - Ricky Hu
- Faculty of Medicine, Queen's University, Kingston, Ontario, Canada
| | - Cailin Ringstrom
- Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada
| | - Victoria Lessoway
- Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada
| | - Janice Reid
- Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada
| | - Christopher Nguan
- Urologic Sciences, University of British Columbia, Vancouver, British Columbia, Canada
| | - Robert Rohling
- Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada; Mechanical Engineering, University of British Columbia, Vancouver, British Columbia, Canada
| |
Collapse
|
5
|
Khairalseed M, Hoyt K. High-Resolution Ultrasound Characterization of Local Scattering in Cancer Tissue. ULTRASOUND IN MEDICINE & BIOLOGY 2023; 49:951-960. [PMID: 36681609 PMCID: PMC9974749 DOI: 10.1016/j.ultrasmedbio.2022.11.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/22/2022] [Revised: 11/21/2022] [Accepted: 11/23/2022] [Indexed: 06/17/2023]
Abstract
Ultrasound (US) has afforded an approach to tissue characterization for more than a decade. The challenge is to reveal hidden patterns in the US data that describe tissue function and pathology that cannot be seen in conventional US images. Our group has developed a high-resolution analysis technique for tissue characterization termed H-scan US, an imaging method used to interpret the relative size of acoustic scatterers. In the present study, the objective was to compare local H-scan US image intensity with registered histologic measurements made directly at the cellular level. Human breast cancer cells (MDA-MB 231, American Type Culture Collection, Manassas, VA, USA) were orthotopically implanted into female mice (N = 5). Tumors were allowed to grow for approximately 4 wk before the study started. In vivo imaging of tumor tissue was performed using a US system (Vantage 256, Verasonics Inc., Kirkland, WA, USA) equipped with a broadband capacitive micromachined ultrasonic linear array transducer (Kolo Medical, San Jose, CA, USA). A 15-MHz center frequency was used for plane wave imaging with five angles for spatial compounding. H-scan US image reconstruction involved use of parallel convolution filters to measure the relative strength of backscattered US signals. Color codes were applied to filter outputs to form the final H-scan US image display. For histologic processing, US imaging cross-sections were carefully marked on the tumor surface, and tumors were excised and sliced along the same plane. By use of optical microscopy, whole tumor tissue sections were scanned and digitized after nuclear staining. US images were interpolated to have the same number of pixels as the histology images and then spatially aligned. Each nucleus from the histologic sections was automatically segmented using custom MATLAB software (The MathWorks Inc., Natick, MA, USA). Nuclear size and spacing from the histology images were then compared with local H-scan US image features. Overall, local H-scan US image intensity exhibited a significant correlation with both cancer cell nuclear size (R2 > 0.27, p < 0.001) and the inverse relationship with nuclear spacing (R2 > 0.17, p < 0.001).
Collapse
Affiliation(s)
- Mawia Khairalseed
- Department of Bioengineering, University of Texas at Dallas, Richardson, Texas, USA
| | - Kenneth Hoyt
- Department of Bioengineering, University of Texas at Dallas, Richardson, Texas, USA.
| |
Collapse
|
6
|
Tai H, Basavarajappa L, Hoyt K. 3-D H-scan ultrasound imaging of relative scatterer size using a matrix array transducer and sparse random aperture compounding. Comput Biol Med 2022; 151:106316. [PMID: 36442278 PMCID: PMC9749370 DOI: 10.1016/j.compbiomed.2022.106316] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2022] [Revised: 11/05/2022] [Accepted: 11/13/2022] [Indexed: 11/18/2022]
Abstract
H-scan ultrasound (US) is a high-resolution imaging technique for soft tissue characterization. By acquiring data in volume space, H-scan US can provide insight into subtle tissue changes or heterogenous patterns that might be missed using traditional cross-sectional US imaging approaches. In this study, we introduce a 3-dimensional (3-D) H-scan US imaging technology for voxel-level tissue characterization in simulation and experimentation. Using a matrix array transducer, H-scan US imaging was developed to evaluate the relative size of US scattering aggregates in volume space. Experimental data was acquired using a programmable US system (Vantage 256, Verasonics Inc, Kirkland, WA) equipped with a 1024-element (32 × 32) matrix array transducer (Vermon Inc, Tours, France). Imaging was performed using the full array in transmission. Radiofrequency (RF) data sequences were collected using a sparse random aperture compounding technique with 6 different data compounding approaches. Plane wave imaging at five angles was performed at a center frequency of 8 MHz. Scan conversion and attenuation correction were applied. To generate the 3-D H-scan US images, a convolution filter bank (N = 256) was then used to process the RF data sequences and measure the spectral content of the backscattered US signals before volume reconstruction. Preliminary experimental studies were conducted using homogeneous phantom materials embedded with spherical US scatterers of varying diameter, i.e., 27 to 45, 63 to 75, or 106-126 μm. Both simulated and experimental results revealed that 3-D H-scan US images have a low spatial variance when tested with homogeneous phantom materials. Furthermore, H-scan US is considerably more sensitive than traditional B-mode US imaging for differentiating US scatterers of varying size (p = 0.001 and p = 0.93, respectively). Overall, this study demonstrates the feasibility of 3-D H-scan US imaging using a matrix array transducer for tissue characterization in volume space.
Collapse
Affiliation(s)
- Haowei Tai
- Department of Bioengineering, University of Texas at Dallas, Richardson, TX, USA
| | - Lokesh Basavarajappa
- Department of Bioengineering, University of Texas at Dallas, Richardson, TX, USA
| | - Kenneth Hoyt
- Department of Bioengineering, University of Texas at Dallas, Richardson, TX, USA.
| |
Collapse
|
7
|
Baek J, O’Connell AM, Parker KJ. Improving breast cancer diagnosis by incorporating raw ultrasound parameters into machine learning. MACHINE LEARNING: SCIENCE AND TECHNOLOGY 2022; 3:045013. [PMID: 36698865 PMCID: PMC9855672 DOI: 10.1088/2632-2153/ac9bcc] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2022] [Revised: 10/15/2022] [Accepted: 10/19/2022] [Indexed: 01/28/2023] Open
Abstract
The improved diagnostic accuracy of ultrasound breast examinations remains an important goal. In this study, we propose a biophysical feature-based machine learning method for breast cancer detection to improve the performance beyond a benchmark deep learning algorithm and to furthermore provide a color overlay visual map of the probability of malignancy within a lesion. This overall framework is termed disease-specific imaging. Previously, 150 breast lesions were segmented and classified utilizing a modified fully convolutional network and a modified GoogLeNet, respectively. In this study multiparametric analysis was performed within the contoured lesions. Features were extracted from ultrasound radiofrequency, envelope, and log-compressed data based on biophysical and morphological models. The support vector machine with a Gaussian kernel constructed a nonlinear hyperplane, and we calculated the distance between the hyperplane and each feature's data point in multiparametric space. The distance can quantitatively assess a lesion and suggest the probability of malignancy that is color-coded and overlaid onto B-mode images. Training and evaluation were performed on in vivo patient data. The overall accuracy for the most common types and sizes of breast lesions in our study exceeded 98.0% for classification and 0.98 for an area under the receiver operating characteristic curve, which is more precise than the performance of radiologists and a deep learning system. Further, the correlation between the probability and Breast Imaging Reporting and Data System enables a quantitative guideline to predict breast cancer. Therefore, we anticipate that the proposed framework can help radiologists achieve more accurate and convenient breast cancer classification and detection.
Collapse
Affiliation(s)
- Jihye Baek
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, United States of America
| | - Avice M O’Connell
- Department of Imaging Sciences, University of Rochester Medical Center, Rochester, NY, United States of America
| | - Kevin J Parker
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, United States of America,Author to whom any correspondence should be addressed
| |
Collapse
|
8
|
Basavarajappa L, Hoyt K. Photoacoustic graphic equalization and application in characterization of red blood cell aggregates. PHOTOACOUSTICS 2022; 26:100365. [PMID: 35592591 PMCID: PMC9111976 DOI: 10.1016/j.pacs.2022.100365] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/14/2022] [Revised: 04/15/2022] [Accepted: 05/06/2022] [Indexed: 06/15/2023]
Abstract
A photoacoustic (PA) graphic equalization (PAGE) algorithm was developed to characterize the relative size of optical absorbing aggregates. This technique divides the PA signal into frequency bands related to different-sized optical absorbers. Simulations of a material containing optical absorbing microparticles of varying size were used to assess PAGE performance. Experiments were performed on phantom materials containing microspheres of varying size and concentration. Additional experiments were performed using tubes with fresh clotting blood. PA data was obtained using a Vevo LAZR-X system (FUJIFILM VisualSonics Inc). PAGE imaging of phantoms with varying-sized optical absorbers found a 1.5-fold difference in mean image intensity (p < 0.001). Conversely, PA images from these same materials exhibited no intensity changes (p = 0.68). PAGE imaging results from clotting blood exhibited differences for clot sizes in the range 0.30-0.64 mm (p < 0.001). In summary, PAGE imaging can distinguish optical absorbing aggregates of varying size.
Collapse
|
9
|
Ormachea J, Parker KJ. A Preliminary Study of Liver Fat Quantification Using Reported Ultrasound Speed of Sound and Attenuation Parameters. ULTRASOUND IN MEDICINE & BIOLOGY 2022; 48:675-684. [PMID: 35039191 DOI: 10.1016/j.ultrasmedbio.2021.12.009] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/02/2021] [Revised: 12/07/2021] [Accepted: 12/08/2021] [Indexed: 06/14/2023]
Abstract
The quantification of liver fat as a diagnostic assessment of steatosis remains an important priority for non-invasive imaging systems. We derive a framework in which the unknown fat volume percentage can be estimated from a pair of ultrasound measurements. The precise estimation of ultrasound speed of sound and attenuation within the liver is found to be sufficient for estimating fat volume assuming a classic model of the properties of a composite elastic material. In this model, steatosis is represented as a random dispersion of spherical fat vacuoles with acoustic properties similar to those of edible oils. Using values of speed of sound and attenuation from the literature in which normal and steatotic livers were studied near 3.5 MHz, we describe agreement of the new estimation method with independent measures of fat. This framework holds the potential for translation to clinical scanners with which the two ultrasound measurements can be made and used for improved quantitative assessment of steatosis.
Collapse
Affiliation(s)
- Juvenal Ormachea
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, New York, USA
| | - Kevin J Parker
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, New York, USA.
| |
Collapse
|
10
|
Baek J, Basavarajappa L, Hoyt K, Parker KJ. Disease-Specific Imaging Utilizing Support Vector Machine Classification of H-Scan Parameters: Assessment of Steatosis in a Rat Model. IEEE TRANSACTIONS ON ULTRASONICS, FERROELECTRICS, AND FREQUENCY CONTROL 2022; 69:720-731. [PMID: 34936555 PMCID: PMC8908945 DOI: 10.1109/tuffc.2021.3137644] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/03/2023]
Abstract
In medical imaging, quantitative measurements have shown promise in identifying diseases by classifying normal versus pathological parameters from tissues. The support vector machine (SVM) has shown promise as a supervised classification algorithm and has been widely used. However, the classification results typically identify a category of abnormal tissues but do not necessarily differentiate progressive stages of a disease. Moreover, the classification result is typically provided independently as a supplement to medical images, which contributes to an overload of information sources in the clinic. Hence, we propose a new imaging method utilizing the SVM to integrate classification results into medical images. This framework is called disease-specific imaging (DSI) that produces a color overlaid highlight on B-mode ultrasound images indicating the type, location, and severity of pathology from different conditions. In this article, the SVM training was performed to construct hyperplanes that can differentiate normal, fibrosis, steatosis, and pancreatic ductal adenocarcinoma (PDAC) metastases in livers based on ultrasound echoes. Also, cluster centroids for specific diseases define unique disease axes, and the inner product between measured features and any disease axis selected by the SVM quantifies the disease progression. The features were measured from 2794 ultrasound frames using the H-scan analysis, attenuation estimation, and B-mode image analysis. The performance of our proposed DSI method was evaluated for a preclinical model of steatosis ( n = 400 frames). The contribution of each feature was assessed, and the results were compared with ground truth from histology. Moreover, the images generated by our DSI were compared with earlier imaging methods of B-mode, H-scan, and histology. The comparisons demonstrate that DSI images yield higher sensitivity to monitor progressive steatosis than B-mode and H-scan and provide a comparable performance with the histology. For the parameter comparison, DSI and H-scan resulted in similar correlation with histology ( rs = 0.83 ) but higher than attenuation ( rs = 0.73 ) and B-mode ( rs = 0.47 ). Therefore, we conclude that DSI utilizing the SVM applied to steatosis can visually represent the classification results with color highlighting, which can simplify the interpretation of classification compared to the traditional SVM result. We expect that the proposed DSI can be used for any medical imaging modality that can estimate multiple quantitative parameters at high resolution.
Collapse
|
11
|
Baek J, Parker KJ. H-scan trajectories indicate the progression of specific diseases. Med Phys 2021; 48:5047-5058. [PMID: 34287952 DOI: 10.1002/mp.15108] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2021] [Revised: 07/09/2021] [Accepted: 07/12/2021] [Indexed: 01/18/2023] Open
Abstract
PURPOSE The ability of ultrasound to assess pathology is increasing with the development of quantitative parameters. Among these are a set of parameters derived from the recent H-scan analysis of subresolvable scattering. The emergence of these quantitative measures of tissue/ultrasound interactions now enables a study of the unique trajectories of multiparametric features in multidimensional space, representing the progression of specific diseases over time. We develop the mathematical and visual tools that are effective for classifying, quantifying, and visualizing the steady progression of several diseases from independent studies, all within a uniform framework. METHODS After applying the H-scan analysis of ultrasound echoes, we trained a support vector machine (SVM) to classify the unique trajectories of progressive liver disease from fibrosis, steatosis, and pancreatic ductal adenocarcinoma (PDAC) metastasis. Our approaches include the development of trajectory maps and disease-specific color imaging stains. RESULTS The multidimensional SVM image classification reached 100% accuracy across the three different studies. CONCLUSION H-scan trajectories can be useful to track the progression of multiple classes of diseases, improving diagnosis, staging, and assessing the response to therapy.
Collapse
Affiliation(s)
- Jihye Baek
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, New York, USA
| | - Kevin J Parker
- Department of Electrical and Computer Engineering, University of Rochester, Rochester, New York, USA
| |
Collapse
|