1
|
Mitchell C, Al Mukaddim R, Liu Y, Graham M, Eickhoff JC, Weichmann AM, Tattersall MC, Korcarz CE, Stein JH, Varghese T, Eliceiri KW. Changes in carotid artery texture by ultrasound and elastin features in a murine model. Front Cardiovasc Med 2023; 10:1215449. [PMID: 37560112 PMCID: PMC10407807 DOI: 10.3389/fcvm.2023.1215449] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2023] [Accepted: 06/28/2023] [Indexed: 08/11/2023] Open
Abstract
OBJECTIVE In humans, arterial grayscale ultrasound texture features independently predict adverse cardiovascular disease (CVD) events and change with medical interventions. We performed this study to examine how grayscale ultrasound texture features and elastin fibers change in plaque-free segments of the arterial wall in a murine model prone to atherosclerosis. METHODS A total of 10 Apoetm1Unc/J mice (n = 5 male, n = 5 female) were imaged at 6, 16, and 24 weeks of age. Two mice were euthanized at 6 and 16 weeks and the remaining mice at 24 weeks. Texture features were extracted from the ultrasound images of the distal 1.0 mm of the common carotid artery wall, and elastin measures were extracted from histology images. Two-way analysis of variance was used to evaluate associations between week, sex, and grayscale texture features. Texture feature and elastin number comparisons between weeks were conducted using the sex-by-week two-way interaction contrasts. Sex-specific correlations between the number of elastin fibers and grayscale texture features were analyzed by conducting non-parametric Spearman's rank correlation analyses. RESULTS Arterial wall homogeneity changed significantly in male mice from 6 to 24 weeks, with a mean (SD) of 0.14 (0.03) units at 6 weeks and 0.18 (0.03) units at 24 weeks (p = 0.026). Spatial gray level dependence matrices-homogeneity (SGLD-HOM) also correlated with carotid artery plaque score (rs = 0.707, p = 0.033). Elastin fibers in the region of interest decreased from 6 to 24 weeks for both male and female mice, although only significantly in male mice. The mean (SD) number of elastin fibers for male mice was 5.32 (1.50) at 6 weeks and 3.59 (0.38) at 24 weeks (p = 0.023). For female mice, the mean (SD) number of elastin fibers was 3.98 (0.38) at 6 weeks and 3.46 (0.19) at 24 weeks (p = 0.051). CONCLUSION Grayscale ultrasound texture features that are associated with increased risk for CVD events in humans were used in a murine model, and the grayscale texture feature SGLD-HOM was shown to change in male mice from 6 weeks to 24 weeks. Structural alterations of the arterial wall (change in elastin fiber number) were observed during this time and may differ by sex.
Collapse
Affiliation(s)
- Carol Mitchell
- Department of Medicine, University of Wisconsin-Madison, Madison, WI, United States
- Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, United States
| | - Rashid Al Mukaddim
- Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, United States
| | - Yuming Liu
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, United States
| | - Melissa Graham
- Comparative Pathology Laboratory, Research Animal Resources and Compliance, University of Wisconsin-Madison, Madison, WI, United States
| | - Jens C. Eickhoff
- Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI, United States
| | - Ashley M. Weichmann
- Carbone Cancer Center, Small Animal Imaging and Radiotherapy Facility, University of Wisconsin-Madison, Madison, WI, United States
| | | | - Claudia E. Korcarz
- Department of Medicine, University of Wisconsin-Madison, Madison, WI, United States
| | - James H. Stein
- Department of Medicine, University of Wisconsin-Madison, Madison, WI, United States
| | - Tomy Varghese
- Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, United States
| | - Kevin W. Eliceiri
- Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, United States
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, United States
- Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI, United States
- Morgridge Institute for Research, Madison, WI, United States
| |
Collapse
|
2
|
Human Behavior Recognition Model Based on Feature and Classifier Selection. SENSORS 2021; 21:s21237791. [PMID: 34883795 PMCID: PMC8659462 DOI: 10.3390/s21237791] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/12/2021] [Revised: 11/07/2021] [Accepted: 11/19/2021] [Indexed: 02/04/2023]
Abstract
With the rapid development of the computer and sensor field, inertial sensor data have been widely used in human activity recognition. At present, most relevant studies divide human activities into basic actions and transitional actions, in which basic actions are classified by unified features, while transitional actions usually use context information to determine the category. For the existing single method that cannot well realize human activity recognition, this paper proposes a human activity classification and recognition model based on smartphone inertial sensor data. The model fully considers the feature differences of different properties of actions, uses a fixed sliding window to segment the human activity data of inertial sensors with different attributes and, finally, extracts the features and recognizes them on different classifiers. The experimental results show that dynamic and transitional actions could obtain the best recognition performance on support vector machines, while static actions could obtain better classification effects on ensemble classifiers; as for feature selection, the frequency-domain feature used in dynamic action had a high recognition rate, up to 99.35%. When time-domain features were used for static and transitional actions, higher recognition rates were obtained, 98.40% and 91.98%, respectively.
Collapse
|
4
|
Machine Learning Quantitation of Cardiovascular and Cerebrovascular Disease: A Systematic Review of Clinical Applications. Diagnostics (Basel) 2021; 11:diagnostics11030551. [PMID: 33808677 PMCID: PMC8003459 DOI: 10.3390/diagnostics11030551] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2021] [Revised: 03/12/2021] [Accepted: 03/16/2021] [Indexed: 01/10/2023] Open
Abstract
Research into machine learning (ML) for clinical vascular analysis, such as those useful for stroke and coronary artery disease, varies greatly between imaging modalities and vascular regions. Limited accessibility to large diverse patient imaging datasets, as well as a lack of transparency in specific methods, are obstacles to further development. This paper reviews the current status of quantitative vascular ML, identifying advantages and disadvantages common to all imaging modalities. Literature from the past 8 years was systematically collected from MEDLINE® and Scopus database searches in January 2021. Papers satisfying all search criteria, including a minimum of 50 patients, were further analysed and extracted of relevant data, for a total of 47 publications. Current ML image segmentation, disease risk prediction, and pathology quantitation methods have shown sensitivities and specificities over 70%, compared to expert manual analysis or invasive quantitation. Despite this, inconsistencies in methodology and the reporting of results have prevented inter-model comparison, impeding the identification of approaches with the greatest potential. The clinical potential of this technology has been well demonstrated in Computed Tomography of coronary artery disease, but remains practically limited in other modalities and body regions, particularly due to a lack of routine invasive reference measurements and patient datasets.
Collapse
|
5
|
Defeudis A, De Mattia C, Rizzetto F, Calderoni F, Mazzetti S, Torresin A, Vanzulli A, Regge D, Giannini V. Standardization of CT radiomics features for multi-center analysis: impact of software settings and parameters. Phys Med Biol 2020; 65:195012. [PMID: 32575082 DOI: 10.1088/1361-6560/ab9f61] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
The aim of this multicentric study is an inter-center benchmarking, to assess how different set tools applied to the same radiomics workflow affected the radiomics features (RFs) values. This topic is of key importance to start collaboration between different centers and to bring radiomic studies from benchmark to bedside. A per-lesion analysis was performed on 56 metastases (mts) selected from 14 patients. A single radiologist performed the segmentation of all mts, and RFs were extracted from the same segmentation of each mts, using two different software and file formats. Potential sources of discrepancies were evaluated. The intraclass correlation coefficient was used to describe how strongly the same radiomic measurements calculated in the two different centers resemble each other. Moreover, means of the relative changes of each RF were calculated, compared and gradually reduced. We showed that, after matching all formulas, discrepancies in RFs calculation between two centers ranged from 1% to 277%. Therefore, we evaluated other sources of variability using a stepwise approach, which led us to reduce the inter-center discrepancies to 0% for 22/25 RFs and below 2% for 3 RFs out of 25. In this study we demonstrated that different radiomic applications and masks formats might strongly impact the computation of some RFs. Therefore, when dealing with multi-center studies it is mandatory to adopt all strategies that can help in limiting the differences, thus keeping in mind the feasibility of these strategies in large cohort studies.
Collapse
Affiliation(s)
- Arianna Defeudis
- Department of Radiology, Candiolo Cancer Institute, FPO-IRCCS, Candiolo, Italy. Department of Surgical Sciences, University of Turin, Turin, Italy
| | | | | | | | | | | | | | | | | |
Collapse
|
6
|
Rosati S, Balestra G, Knaflitz M. Comparison of Different Sets of Features for Human Activity Recognition by Wearable Sensors. SENSORS 2018; 18:s18124189. [PMID: 30501111 PMCID: PMC6308535 DOI: 10.3390/s18124189] [Citation(s) in RCA: 45] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/29/2018] [Revised: 11/22/2018] [Accepted: 11/27/2018] [Indexed: 11/16/2022]
Abstract
Human Activity Recognition (HAR) refers to an emerging area of interest for medical, military, and security applications. However, the identification of the features to be used for activity classification and recognition is still an open point. The aim of this study was to compare two different feature sets for HAR. Particularly, we compared a set including time, frequency, and time-frequency domain features widely used in literature (FeatSet_A) with a set of time-domain features derived by considering the physical meaning of the acquired signals (FeatSet_B). The comparison of the two sets were based on the performances obtained using four machine learning classifiers. Sixty-one healthy subjects were asked to perform seven different daily activities wearing a MIMU-based device. Each signal was segmented using a 5-s window and for each window, 222 and 221 variables were extracted for the FeatSet_A and FeatSet_B respectively. Each set was reduced using a Genetic Algorithm (GA) simultaneously performing feature selection and classifier optimization. Our results showed that Support Vector Machine achieved the highest performances using both sets (97.1% and 96.7% for FeatSet_A and FeatSet_B respectively). However, FeatSet_B allows to better understand alterations of the biomechanical behavior in more complex situations, such as when applied to pathological subjects.
Collapse
Affiliation(s)
- Samanta Rosati
- Department of Electronics and Telecommunications, Politecnico di Torino, 10129 Torino, Italy.
| | - Gabriella Balestra
- Department of Electronics and Telecommunications, Politecnico di Torino, 10129 Torino, Italy.
| | - Marco Knaflitz
- Department of Electronics and Telecommunications, Politecnico di Torino, 10129 Torino, Italy.
| |
Collapse
|
7
|
Zaccaria GM, Rosati S, Castagneri C, Ferrero S, Ladetto M, Boccadoro M, Balestra G. Data quality improvement of a multicenter clinical trial dataset. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2017; 2017:1190-1193. [PMID: 29060088 DOI: 10.1109/embc.2017.8037043] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
Medical datasets are usually affected by several problems, such as missing values, inconsistencies, redundancies, that can influence the data mining process and the extraction of useful knowledge. For these reasons, a preprocessing phase should be performed for improving the overall quality of data and, consequently, of the information that may be discovered from them. In this study we applied five steps of data preprocessing to improve the quality of a large dataset derived from a multicenter clinical trial. Our dataset included 298 patients enrolled in a prospective, multicenter, clinical trial, characterized by 22 input variables and one class variable (MIPI value). In particular, data coming from different medical centers were firstly integrated to obtain a homogeneous dataset. The latter was normalized to scale all variables into smaller and similar intervals. Then, all missing values were estimated by means of an imputation step. The complete dataset was finally discretized and reduced to remove redundant variables and decrease the amount of data to be managed. The improvement of data quality after each step was evaluated by means of the patients' classification accuracy using the KNN classifier. Our results showed that the proposed pipeline produced an increment of more than 20% of the classification performances. Moreover, the highest growth of accuracy was obtained after missing value imputation, whereas the discretization and feature selection steps allowed for a significant reduction of variables to be managed, without any deterioration of the information contained in data.
Collapse
|