Juan C. Restrepo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Juan C. Restrepo has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Ender A. Finol
Department of Mechanical, Aerospace, and Industrial Engineering, The University of Texas at San Antonio, San Antonio, TX 78249, USA
4 shared publications - Satish C. Muluk
Department of Thoracic and Cardiovascular Surgery, Allegheny Health Network, Allegheny General Hospital, Pittsburgh, PA 15212, USA
3 shared publications Mark K. Eskandari
Feinberg School of Medicine, Northwestern University, Chicago, IL, 60611, USA
2 shared publications- Mark K. Eskandari
Feinberg School of Medicine, Northwestern University, Chicago, IL 60611, USA
2 shared publications - Seungik Baek
Department of Mechanical Engineering Michigan State University East Lansing Michigan USA
2 shared publications - Vikram S. Kashyap
Cardiovascular Health, Corewell Health, Grand Rapids, MI 49503, USA
2 shared publications
Latest Publications
- Open Access
- 6 May 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (9) , 1409
Forecasting Patient-Specific Abdominal Aortic Aneurysm Geometry with Mixed-Effects Models
Background/Objectives: Abdominal aortic aneurysm (AAA) surveillance is based largely on monitoring the maximum diameter, a single scalar metric that obscures regional remodeling and offers limited information on the location and time dependency of the growth rate. The present work addresses this limitation with a geometry-based patient-specific framework that learns local, linear evolution from longitudinal clinical imaging, yielding 3D forecasts of AAA geometry at arbitrary future times. Methods: Lumen and outer wall surfaces are represented on a centerline-anchored cylindrical grid, with subsequent implementation of individualized linear mixed-effects models. The model is explicitly interpretable as the fixed effects predict global trends and the random effects represent regional heterogeneity. In a multicenter cohort of 79 patients, we evaluated forecasts using spatial similarity (with the 95th percentile of the Hausdorff distance—HD95) and clinically relevant global geometric scalars such as maximum diameter and volume. Results: When forecasting a future AAA geometry, the model achieved sub-millimetric HD95 spatial errors and less than 6% error for the aforementioned global scalars. The model was deployed in an interactive application named the Aneurysm Forecasting Studio, which allows a user to visualize the AAA in an explorable forecast space. Conclusions: During typical clinical surveillance intervals, AAA geometric remodeling is reasonably approximated as locally linear in time, enabling transparent, fast forecasts that support surveillance optimization, threshold timing, and digital twin-based interventional planning.
- 6 May 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (9) , 1409
Open AccessForecasting Patient-Specific Abdominal Aortic Aneurysm Geometry with Mixed-Effects Models
Background/Objectives: Abdominal aortic aneurysm (AAA) surveillance is based largely on monitoring the maximum diameter, a single scalar metric that obscures regional remodeling and offers limited information on the location and time dependency of the growth rate. The present work addresses this limitation with a geometry-based patient-specific framework that learns local, linear evolution from longitudinal clinical imaging, yielding 3D forecasts of AAA geometry at arbitrary future times. Methods: Lumen and outer wall surfaces are represented on a centerline-anchored cylindrical grid, with subsequent implementation of individualized linear mixed-effects models. The model is explicitly interpretable as the fixed effects predict global trends and the random effects represent regional heterogeneity. In a multicenter cohort of 79 patients, we evaluated forecasts using spatial similarity (with the 95th percentile of the Hausdorff distance—HD95) and clinically relevant global geometric scalars such as maximum diameter and volume. Results: When forecasting a future AAA geometry, the model achieved sub-millimetric HD95 spatial errors and less than 6% error for the aforementioned global scalars. The model was deployed in an interactive application named the Aneurysm Forecasting Studio, which allows a user to visualize the AAA in an explorable forecast space. Conclusions: During typical clinical surveillance intervals, AAA geometric remodeling is reasonably approximated as locally linear in time, enabling transparent, fast forecasts that support surveillance optimization, threshold timing, and digital twin-based interventional planning.
- Open Access
- 9 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Geometry quantification for growth assessment of abdominal aortic aneurysms under surveillance
Abdominal Aortic Aneurysms (AAAs) are localized expansions of the abdominal aorta with complex growth patterns, which offer challenges in accurately characterizing aneurysm growth and morphological evolution using traditional maximum diameter [Formula: see text] assessments. Alternative geometric indices and advanced modeling techniques have emerged to address the limitations inherent to diameter-based metrics. The objective of the present work is to elucidate AAA growth dynamics by comparing linear and exponential growth models and examining their correlations with changes in a geometry-driven rupture proxy index (GDRPI), emphasizing additional geometric indices beyond [Formula: see text]. In a cohort of 40 patients, exponential models exhibited strong correlations with multiple geometric indices, with aneurysm volume (V) and thrombus-related indices demonstrating high predictive relevance. Thrombus-related indices strongly correlated with the maximum value of GDRPI, highlighting their potential utility as supplementary surveillance markers. Growth trajectories showed substantial inter-patient variability; aneurysms with mean volumes exceeding 75 [Formula: see text] predominantly followed linear growth, while smaller aneurysms with mean volumes of 50 [Formula: see text] displayed ambiguous growth patterns. Mixed effects techniques significantly improved growth prediction accuracy (mean [Formula: see text] for linear growth models and [Formula: see text] for exponential growth models). Although linear models slightly outperformed exponential models, both effectively described patient-specific AAA progression when used with mixed effects techniques. Integrating thrombus-related indices and mixed effects growth modeling offers a promising pathway for enhanced geometric characterization of AAAs under surveillance, potentially improving longitudinal growth assessment and individual monitoring strategies.
- 9 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessGeometry quantification for growth assessment of abdominal aortic aneurysms under surveillance
Abdominal Aortic Aneurysms (AAAs) are localized expansions of the abdominal aorta with complex growth patterns, which offer challenges in accurately characterizing aneurysm growth and morphological evolution using traditional maximum diameter [Formula: see text] assessments. Alternative geometric indices and advanced modeling techniques have emerged to address the limitations inherent to diameter-based metrics. The objective of the present work is to elucidate AAA growth dynamics by comparing linear and exponential growth models and examining their correlations with changes in a geometry-driven rupture proxy index (GDRPI), emphasizing additional geometric indices beyond [Formula: see text]. In a cohort of 40 patients, exponential models exhibited strong correlations with multiple geometric indices, with aneurysm volume (V) and thrombus-related indices demonstrating high predictive relevance. Thrombus-related indices strongly correlated with the maximum value of GDRPI, highlighting their potential utility as supplementary surveillance markers. Growth trajectories showed substantial inter-patient variability; aneurysms with mean volumes exceeding 75 [Formula: see text] predominantly followed linear growth, while smaller aneurysms with mean volumes of 50 [Formula: see text] displayed ambiguous growth patterns. Mixed effects techniques significantly improved growth prediction accuracy (mean [Formula: see text] for linear growth models and [Formula: see text] for exponential growth models). Although linear models slightly outperformed exponential models, both effectively described patient-specific AAA progression when used with mixed effects techniques. Integrating thrombus-related indices and mixed effects growth modeling offers a promising pathway for enhanced geometric characterization of AAAs under surveillance, potentially improving longitudinal growth assessment and individual monitoring strategies.
- Open Access
- 7 February 2026
- Published by MDPI AG in Bioengineering
- Vol. 13 (2) , 191
An Integrated Framework for Automated Image Segmentation and Personalized Wall Stress Estimation of Abdominal Aortic Aneurysms
Abdominal Aortic Aneurysm (AAA) remains a significant public health challenge, with an 82.1% increase in related fatalities from 1990 to 2019. In the United States alone, AAA complications resulted in an estimated 13,640 deaths between 2018 and 2021. In clinical practice, computed tomography angiography (CTA) is the primary imaging modality for monitoring and pre-surgical planning of AAA patients. CTA provides high-resolution vascular imaging, enabling detailed assessments of aneurysm morphology and informing critical clinical decisions. However, manual segmentation of CTA images is labor-intensive and time consuming, underscoring the need for automated segmentation algorithms, particularly when feature extraction from clinical images can inform treatment decisions. We propose a framework to automatically segment the outer wall of the abdominal aorta from CTA images and estimate AAA wall stress. Our approach employs a patch-based dilated modified U-Net model to accurately delineate the outer wall boundary of AAAs and Nonlinear Elastic Membrane Analysis (NEMA) to estimate their wall stress. We further integrate Non-Uniform Rational B-Splines (NURBS) to refine the segmentation. During prediction, our deep learning architecture requires milliseconds per frame to generate the final segmented output. The latter is used to provide critical insight into the biomechanical state of stress of an AAA. This modeling strategy merges advanced deep learning architecture, the precision of NURBS, and the advantages of NEMA to deliver a robust and efficient method for computational analysis of AAAs.- 7 February 2026
- Published by MDPI AG in Bioengineering
- Vol. 13 (2) , 191
Open AccessAn Integrated Framework for Automated Image Segmentation and Personalized Wall Stress Estimation of Abdominal Aortic Aneurysms
Abdominal Aortic Aneurysm (AAA) remains a significant public health challenge, with an 82.1% increase in related fatalities from 1990 to 2019. In the United States alone, AAA complications resulted in an estimated 13,640 deaths between 2018 and 2021. In clinical practice, computed tomography angiography (CTA) is the primary imaging modality for monitoring and pre-surgical planning of AAA patients. CTA provides high-resolution vascular imaging, enabling detailed assessments of aneurysm morphology and informing critical clinical decisions. However, manual segmentation of CTA images is labor-intensive and time consuming, underscoring the need for automated segmentation algorithms, particularly when feature extraction from clinical images can inform treatment decisions. We propose a framework to automatically segment the outer wall of the abdominal aorta from CTA images and estimate AAA wall stress. Our approach employs a patch-based dilated modified U-Net model to accurately delineate the outer wall boundary of AAAs and Nonlinear Elastic Membrane Analysis (NEMA) to estimate their wall stress. We further integrate Non-Uniform Rational B-Splines (NURBS) to refine the segmentation. During prediction, our deep learning architecture requires milliseconds per frame to generate the final segmented output. The latter is used to provide critical insight into the biomechanical state of stress of an AAA. This modeling strategy merges advanced deep learning architecture, the precision of NURBS, and the advantages of NEMA to deliver a robust and efficient method for computational analysis of AAAs. - Open Access
- 23 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 24544-24554
Automatic Segmentation of Abdominal Aortic Aneurysm From Computed Tomography Angiography Using a Patch-Based Dilated UNet Model
Abdominal Aortic Aneurysm (AAA) is still a socially relevant public health challenge, evidenced by an 82.1% increase in associated fatalities from 1990 to 2019 (with 172,427 deaths in 2019 alone). In a clinical setting, computed tomography angiography (CTA) is the imaging modality of choice for monitoring and/or presurgical planning of AAA patients. However, manual segmentation of CTA images is labor intensive and time consuming. Hence, there is a growing need for automated segmentation algorithms, particularly when these influence treatment planning. The deep-learning pipeline proposed in this work is designed to automatically segment AAA CTA images. The framework adapted a fully developed patch-based dilated modified U-Net model, which shows remarkable efficiency in accurately delineating AAA regions within the CTA scans. During the prediction phase, the deep learning architecture demonstrates exceptional speed, requiring $17~\pm ~0.02$ milliseconds per frame to generate the final segmented output. Building upon this work, we included the application of Non-Uniform Rational B-Splines (NURBS) to enhance the segmentation process. This advancement is essential in addressing the critical need for clinical accuracy in medical image segmentation. NURBS enables the creation of continuous curves that seamlessly conform to the intricate contours of anatomical structures, offering a significant improvement in segmentation accuracy. Through the integration of advanced deep learning architectures and the precision of NURBS for segmentation refinement, coupled with the fast processing time and accurate segmentation, the the proposed model represents a promising clinical tool that can be used in the clinical management of AAAs.
- 23 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 24544-24554
Open AccessAutomatic Segmentation of Abdominal Aortic Aneurysm From Computed Tomography Angiography Using a Patch-Based Dilated UNet Model
Abdominal Aortic Aneurysm (AAA) is still a socially relevant public health challenge, evidenced by an 82.1% increase in associated fatalities from 1990 to 2019 (with 172,427 deaths in 2019 alone). In a clinical setting, computed tomography angiography (CTA) is the imaging modality of choice for monitoring and/or presurgical planning of AAA patients. However, manual segmentation of CTA images is labor intensive and time consuming. Hence, there is a growing need for automated segmentation algorithms, particularly when these influence treatment planning. The deep-learning pipeline proposed in this work is designed to automatically segment AAA CTA images. The framework adapted a fully developed patch-based dilated modified U-Net model, which shows remarkable efficiency in accurately delineating AAA regions within the CTA scans. During the prediction phase, the deep learning architecture demonstrates exceptional speed, requiring $17~\pm ~0.02$ milliseconds per frame to generate the final segmented output. Building upon this work, we included the application of Non-Uniform Rational B-Splines (NURBS) to enhance the segmentation process. This advancement is essential in addressing the critical need for clinical accuracy in medical image segmentation. NURBS enables the creation of continuous curves that seamlessly conform to the intricate contours of anatomical structures, offering a significant improvement in segmentation accuracy. Through the integration of advanced deep learning architectures and the precision of NURBS for segmentation refinement, coupled with the fast processing time and accurate segmentation, the the proposed model represents a promising clinical tool that can be used in the clinical management of AAAs.