Artem Mikheev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Artem Mikheev has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Henry Rusinek
Department of Radiology and Psychiatry, NYU Grossman School of Medicine, 660 First Ave, New York, NY 10016, USA; Department of Psychiatry, NYU Grossman School of Medicine, 145 East 32nd Street, New York, NY 10016, USA
3 shared publications - Akshat C. Pujara
Department of Radiology, New York University School of Medicine, New York, New York, USA
1 shared publication - Alexander S. Leidner
Northwestern University Feinberg School of Medicine, Chicago, IL
1 shared publication - Amy N. Melsaether
NYU School of Medicine
1 shared publication - Anand Srivastava
Division of Nephrology, University of Illinois Chicago, Chicago, Illinois
1 shared publication - Anne Bertrand
MRC Oulu, Oulu University Hospital, Oulu, Finland
1 shared publication
Latest Publications
- Open Access
- 1 April 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (7) , 1972
Radiomics-Based Image Phenotyping of Kidney Apparent Diffusion Coefficient Maps: Preliminary Feasibility & Efficacy
Given the central role of interstitial fibrosis in disease progression in chronic kidney disease (CKD), a role for diffusion-weighted MRI has been pursued. We evaluated the feasibility and preliminary efficacy of using radiomic features to phenotype apparent diffusion coefficient (ADC) maps and hence to the clinical classification(s) of the participants. The study involved 40 individuals (10 healthy and 30 with CKD (eGFR < 60 mL/min/1.73 m2)). Machine learning methods, such as hierarchical clustering and logistic regression, were used. Clustering resulted in the identification of two clusters, one including all individuals with CKD (n = 17), while the second one included all the healthy volunteers (n = 10) and the remaining individuals with CKD (n = 13), resulting in 100% specificity. Logistic regression identified five radiomic features to classify participants as with CKD vs. healthy volunteers, with a sensitivity and specificity of 93% and 70%, respectively, and an AUC of 0.95. Similarly, four radiomic features were able to classify participants as rapid vs. non-rapid CKD progressors among the 30 individuals with CKD, with a sensitivity and specificity of 71% and 43%, respectively, and an AUC of 0.75. These promising preliminary data should support future studies with larger numbers of participants with varied disease severity and etiologies to improve performance.
- 1 April 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (7) , 1972
Open AccessRadiomics-Based Image Phenotyping of Kidney Apparent Diffusion Coefficient Maps: Preliminary Feasibility & Efficacy
Given the central role of interstitial fibrosis in disease progression in chronic kidney disease (CKD), a role for diffusion-weighted MRI has been pursued. We evaluated the feasibility and preliminary efficacy of using radiomic features to phenotype apparent diffusion coefficient (ADC) maps and hence to the clinical classification(s) of the participants. The study involved 40 individuals (10 healthy and 30 with CKD (eGFR < 60 mL/min/1.73 m2)). Machine learning methods, such as hierarchical clustering and logistic regression, were used. Clustering resulted in the identification of two clusters, one including all individuals with CKD (n = 17), while the second one included all the healthy volunteers (n = 10) and the remaining individuals with CKD (n = 13), resulting in 100% specificity. Logistic regression identified five radiomic features to classify participants as with CKD vs. healthy volunteers, with a sensitivity and specificity of 93% and 70%, respectively, and an AUC of 0.95. Similarly, four radiomic features were able to classify participants as rapid vs. non-rapid CKD progressors among the 30 individuals with CKD, with a sensitivity and specificity of 71% and 43%, respectively, and an AUC of 0.75. These promising preliminary data should support future studies with larger numbers of participants with varied disease severity and etiologies to improve performance.
- 1 March 2017
- Published by Elsevier in Clinical Imaging
- Vol. 42, 119-125
Clinical applicability and relevance of fibroglandular tissue segmentation on routine T1 weighted breast MRI
- 1 March 2017
- Published by Elsevier in Clinical Imaging
- Vol. 42, 119-125
Clinical applicability and relevance of fibroglandular tissue segmentation on routine T1 weighted breast MRI
- 29 March 2016
- Published by SPIE-Intl Soc Optical Eng
- Vol. 9788, 97881P
Optimal target VOI size for accurate 4D coregistration of DCE-MRI
Dynamic contrast enhanced (DCE) MRI has emerged as a reliable and diagnostically useful functional imaging technique. DCE protocol typically lasts 3-15 minutes and results in a time series of N volumes. For automated analysis, it is important that volumes acquired at different times be spatially coregistered. We have recently introduced a novel 4D, or volume time series, coregistration tool based on a user-specified target volume of interest (VOI). However, the relationship between coregistration accuracy and target VOI size has not been investigated. In this study, coregistration accuracy was quantitatively measured using various sized target VOIs. Coregistration of 10 DCE-MRI mouse head image sets were performed with various sized VOIs targeting the mouse brain. Accuracy was quantified by measures based on the union and standard deviation of the coregistered volume time series. Coregistration accuracy was determined to improve rapidly as the size of the VOI increased and approached the approximate volume of the target (mouse brain). Further inflation of the VOI beyond the volume of the target (mouse brain) only marginally improved coregistration accuracy. The CPU time needed to accomplish coregistration is a linear function of N that varied gradually with VOI size. From the results of this study, we recommend the optimal size of the VOI to be slightly overinclusive, approximately by 5 voxels, of the target for computationally efficient and accurate coregistration.
- 29 March 2016
- Published by SPIE-Intl Soc Optical Eng
- Vol. 9788, 97881P
Optimal target VOI size for accurate 4D coregistration of DCE-MRI
Dynamic contrast enhanced (DCE) MRI has emerged as a reliable and diagnostically useful functional imaging technique. DCE protocol typically lasts 3-15 minutes and results in a time series of N volumes. For automated analysis, it is important that volumes acquired at different times be spatially coregistered. We have recently introduced a novel 4D, or volume time series, coregistration tool based on a user-specified target volume of interest (VOI). However, the relationship between coregistration accuracy and target VOI size has not been investigated. In this study, coregistration accuracy was quantitatively measured using various sized target VOIs. Coregistration of 10 DCE-MRI mouse head image sets were performed with various sized VOIs targeting the mouse brain. Accuracy was quantified by measures based on the union and standard deviation of the coregistered volume time series. Coregistration accuracy was determined to improve rapidly as the size of the VOI increased and approached the approximate volume of the target (mouse brain). Further inflation of the VOI beyond the volume of the target (mouse brain) only marginally improved coregistration accuracy. The CPU time needed to accomplish coregistration is a linear function of N that varied gradually with VOI size. From the results of this study, we recommend the optimal size of the VOI to be slightly overinclusive, approximately by 5 voxels, of the target for computationally efficient and accurate coregistration.