Jeremy Rubin
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
Jeremy Rubin has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Jarcy Zee
Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, USA
6 shared publications Andrew R. Janowczyk
Department of Biomedical Engineering Emory University Atlanta Georgia USA
3 shared publications- Brett Cucchiara
Division of Vascular Neurology, Department of Neurology Hospital of the University of Pennsylvania Philadelphia PA USA
3 shared publications - Jae Won Song
University of Pennsylvania
3 shared publications - Quy Cao
Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania
3 shared publications Fan Fan
Department of Biomedical Engineering Emory University Atlanta Georgia USA
2 shared publications
Latest Publications
- Open Access
- 30 July 2026
- Published by Springer Nature in Health Services and Outcomes Research Methodology
- p. 1-22
Outcome prediction using image features with conformal quantile regression: application to kidney function
Accurate prediction of clinical outcomes and a reliable assessment of the uncertainty around those predictions are critical for informed decision-making in medicine. Yet, as black-box machine learning algorithms are increasingly deployed for complex biomedical prediction tasks, their lack of robust uncertainty quantification, especially in small samples, rare diseases, and underrepresented groups, has led to overconfident predictions and adverse outcomes. Conformal quantile regression (CQR) offers a distribution-free, model-agnostic framework that generates finite-sample valid prediction intervals, ensuring reliable coverage guarantees regardless of the underlying ML algorithm. While CQR has been applied in various prediction tasks, it has not been explored in the context of predicting estimated glomerular filtration rate (eGFR) using high-dimensional image-derived regressors, such as features extracted from kidney biopsy images. In this study, we investigate the utility of CQR for predicting eGFR, a key biomarker of kidney function, by integrating demographic, clinical, and image data. Through simulation studies, we demonstrate that CQR maintains reliable coverage even when predictions are constructed from generated regressors subject to additive measurement error, although larger sample sizes are necessary when regressors are functionally misspecified. Finally, we apply CQR to real-world glomerular disease kidney biopsy image features and show that it produces well-calibrated prediction intervals for future eGFR measurements, addressing a critical gap in quantifying predictive uncertainty in complex biomedical models.
- 30 July 2026
- Published by Springer Nature in Health Services and Outcomes Research Methodology
- p. 1-22
Open AccessOutcome prediction using image features with conformal quantile regression: application to kidney function
Accurate prediction of clinical outcomes and a reliable assessment of the uncertainty around those predictions are critical for informed decision-making in medicine. Yet, as black-box machine learning algorithms are increasingly deployed for complex biomedical prediction tasks, their lack of robust uncertainty quantification, especially in small samples, rare diseases, and underrepresented groups, has led to overconfident predictions and adverse outcomes. Conformal quantile regression (CQR) offers a distribution-free, model-agnostic framework that generates finite-sample valid prediction intervals, ensuring reliable coverage guarantees regardless of the underlying ML algorithm. While CQR has been applied in various prediction tasks, it has not been explored in the context of predicting estimated glomerular filtration rate (eGFR) using high-dimensional image-derived regressors, such as features extracted from kidney biopsy images. In this study, we investigate the utility of CQR for predicting eGFR, a key biomarker of kidney function, by integrating demographic, clinical, and image data. Through simulation studies, we demonstrate that CQR maintains reliable coverage even when predictions are constructed from generated regressors subject to additive measurement error, although larger sample sizes are necessary when regressors are functionally misspecified. Finally, we apply CQR to real-world glomerular disease kidney biopsy image features and show that it produces well-calibrated prediction intervals for future eGFR measurements, addressing a critical gap in quantifying predictive uncertainty in complex biomedical models.
- Open Access
- 23 April 2026
- Published by Wiley in Statistical Analysis and Data Mining: An ASA Data Science Journal
- Vol. 19 (2)
Analysis of Correlated Image Features Using Scalar‐On‐Matrix Regression
Image features from digital kidney biopsies may serve as novel biomarkers of kidney function in glomerular disease. Every subject's biopsy contains a different number of histologic objects, and for every object, a common set of image features is measured across all subjects. These data can be represented by a matrix for each subject with the row dimension representing the objects and the column dimension representing the image features which are computed per object. However, no existing regression method can select informative features of outcomes when feature matrices are unbalanced across subjects and features are correlated. Therefore, we developed the Random CLUstering Structured lasSO (Random CLUSSO), a bootstrap‐based and L1‐penalized scalar‐on‐matrix approach. We demonstrated through simulations that Random CLUSSO has lower bias and a higher true positive rate for identifying informative image features relative to existing approaches when features are correlated. Finally, we applied Random CLUSSO to predict kidney function using image features from kidney biopsies of subjects with glomerular disease from the Nephrotic Syndrome Study Network (NEPTUNE) and Cure Glomerulonephropathy (CureGN) studies.
- 23 April 2026
- Published by Wiley in Statistical Analysis and Data Mining: An ASA Data Science Journal
- Vol. 19 (2)
Open AccessAnalysis of Correlated Image Features Using Scalar‐On‐Matrix Regression
Image features from digital kidney biopsies may serve as novel biomarkers of kidney function in glomerular disease. Every subject's biopsy contains a different number of histologic objects, and for every object, a common set of image features is measured across all subjects. These data can be represented by a matrix for each subject with the row dimension representing the objects and the column dimension representing the image features which are computed per object. However, no existing regression method can select informative features of outcomes when feature matrices are unbalanced across subjects and features are correlated. Therefore, we developed the Random CLUstering Structured lasSO (Random CLUSSO), a bootstrap‐based and L1‐penalized scalar‐on‐matrix approach. We demonstrated through simulations that Random CLUSSO has lower bias and a higher true positive rate for identifying informative image features relative to existing approaches when features are correlated. Finally, we applied Random CLUSSO to predict kidney function using image features from kidney biopsies of subjects with glomerular disease from the Nephrotic Syndrome Study Network (NEPTUNE) and Cure Glomerulonephropathy (CureGN) studies.
- Open Access
- 7 October 2025
- Published by Oxford University Press (OUP) in Journal Of Nephrology
- Vol. 38 (9) , 2949-2960
Determinants of left ventricular mass in children with autosomal recessive polycystic kidney disease
Background: Hypertension and left ventricular (LV) hypertrophy (LVH) are common in autosomal recessive polycystic kidney disease (ARPKD). We examined clinical determinants of LV mass in children with ARPKD. Methods: Retrospective study of patients with ARPKD with available echocardiogram data. Casual blood pressure (BP) percentiles, 24-h ambulatory BP monitor (ABPM) parameters, antihypertensive medications, and estimated glomerular filtration rate (eGFR) within 6 months of echocardiogram were collected. Outcomes included LV mass Z-score, LV mass index [LVMI in g/m 2.7 and g/(m 2.16 + 0.09)], and LVH. Results: Thirty patients with ARPKD (median age 7.2 years [IQR 3.4, 12.8]) had echocardiograms, 28 had casual BPs, 11 had ABPMs, and 93% were on antihypertensives. LVH occurred in 23% based on LVMI in g/m 2.7 > 95th percentile, and in 50% based on LVMI > 45 g/(m 2.16 + 0.09). Younger age correlated with higher number of antihypertensives ( ρ = − 0.46, P = 0.014) and higher casual systolic and diastolic BP percentiles ( r = − 0.74, P < 0.001; r = − 0.81, P < 0.001). After adjusting for age, sex, and eGFR, LV mass was not significantly associated with casual BP or ABPM, except for a negative association between LV mass Z-score and casual diastolic BP percentile (β coefficient − 0.31, P = 0.04). After adjusting for age, sex, and casual BP, both LVMI [in g/m 2.7 and g/(m 2.16 + 0.09)] and LV mass Z-score were significantly negatively associated with eGFR (β –1.08, P = 0.003; β –0.79, P = 0.007; and β -0.07, P = 0.01, respectively). Conclusions: Young children with ARPKD have a higher burden of hypertension. LV mass was unexpectedly not significantly associated with BP but was negatively associated with eGFR. Graphical
- 7 October 2025
- Published by Oxford University Press (OUP) in Journal Of Nephrology
- Vol. 38 (9) , 2949-2960
Open AccessDeterminants of left ventricular mass in children with autosomal recessive polycystic kidney disease
Background: Hypertension and left ventricular (LV) hypertrophy (LVH) are common in autosomal recessive polycystic kidney disease (ARPKD). We examined clinical determinants of LV mass in children with ARPKD. Methods: Retrospective study of patients with ARPKD with available echocardiogram data. Casual blood pressure (BP) percentiles, 24-h ambulatory BP monitor (ABPM) parameters, antihypertensive medications, and estimated glomerular filtration rate (eGFR) within 6 months of echocardiogram were collected. Outcomes included LV mass Z-score, LV mass index [LVMI in g/m 2.7 and g/(m 2.16 + 0.09)], and LVH. Results: Thirty patients with ARPKD (median age 7.2 years [IQR 3.4, 12.8]) had echocardiograms, 28 had casual BPs, 11 had ABPMs, and 93% were on antihypertensives. LVH occurred in 23% based on LVMI in g/m 2.7 > 95th percentile, and in 50% based on LVMI > 45 g/(m 2.16 + 0.09). Younger age correlated with higher number of antihypertensives ( ρ = − 0.46, P = 0.014) and higher casual systolic and diastolic BP percentiles ( r = − 0.74, P < 0.001; r = − 0.81, P < 0.001). After adjusting for age, sex, and eGFR, LV mass was not significantly associated with casual BP or ABPM, except for a negative association between LV mass Z-score and casual diastolic BP percentile (β coefficient − 0.31, P = 0.04). After adjusting for age, sex, and casual BP, both LVMI [in g/m 2.7 and g/(m 2.16 + 0.09)] and LV mass Z-score were significantly negatively associated with eGFR (β –1.08, P = 0.003; β –0.79, P = 0.007; and β -0.07, P = 0.01, respectively). Conclusions: Young children with ARPKD have a higher burden of hypertension. LV mass was unexpectedly not significantly associated with BP but was negatively associated with eGFR. Graphical
- Open Access
Carotid Plaque Calcification Attenuation Characteristics are Associated with Intraplaque Hemorrhage Volumes: A 3D Segmentation-Based Analysis
Background and Purpose: Despite the high prevalence of plaque calcifications in carotid atherosclerosis, the association between morphologic and attenuation features of calcifications and intraplaque hemorrhage (IPH) remains unclear. Methods: Carotid bifurcation calcific plaques were identified on neck CTAs from patients with unilateral anterior circulation ischemic stroke consistent with embolic stroke of undetermined source. Plaque calcifications were manually segmented using 3D Slicer to measure volume, surface area, shape, and attenuation (Hounsfield Units (HU)) characteristics. IPH volume (IPHvol) was quantified using a semi-automated software. A linear mixed regression model evaluated associations between calcification features and IPHvol, adjusting for sex, age, and cardiovascular risk factors. An interaction term between calcification volume and attenuation was included after dichotomizing attenuation (>924HU) and volume (>30mm 3 ) as high versus low based on median values. Results: From 70 patients (median age 68 years, 50% female), 116 calcific plaques containing 269 plaque calcifications were analyzed. Adjusting for age, cardiovascular risk factors and plaque calcification features, being female showed lower IPHvols compared to males (mean ratio 0.34, p=0.002). A significant interaction between calcification volume and attenuation emerged (p=0.042). Among plaques with low volumes (3 ) of plaque calcifications, plaques with low-attenuation (924HU), plaques with high volumes of these calcifications showed 4.40 times higher IPHvols compared to low-volumes of high-attenuation calcifications (p=0.011). Conclusions: Plaque calcification attenuation characteristics are associated with IPHvols. Beyond presence or volumes of plaque calcifications, calcification attenuation characteristics should be considered when evaluating unstable plaque components.
Open AccessCarotid Plaque Calcification Attenuation Characteristics are Associated with Intraplaque Hemorrhage Volumes: A 3D Segmentation-Based Analysis
Background and Purpose: Despite the high prevalence of plaque calcifications in carotid atherosclerosis, the association between morphologic and attenuation features of calcifications and intraplaque hemorrhage (IPH) remains unclear. Methods: Carotid bifurcation calcific plaques were identified on neck CTAs from patients with unilateral anterior circulation ischemic stroke consistent with embolic stroke of undetermined source. Plaque calcifications were manually segmented using 3D Slicer to measure volume, surface area, shape, and attenuation (Hounsfield Units (HU)) characteristics. IPH volume (IPHvol) was quantified using a semi-automated software. A linear mixed regression model evaluated associations between calcification features and IPHvol, adjusting for sex, age, and cardiovascular risk factors. An interaction term between calcification volume and attenuation was included after dichotomizing attenuation (>924HU) and volume (>30mm 3 ) as high versus low based on median values. Results: From 70 patients (median age 68 years, 50% female), 116 calcific plaques containing 269 plaque calcifications were analyzed. Adjusting for age, cardiovascular risk factors and plaque calcification features, being female showed lower IPHvols compared to males (mean ratio 0.34, p=0.002). A significant interaction between calcification volume and attenuation emerged (p=0.042). Among plaques with low volumes (3 ) of plaque calcifications, plaques with low-attenuation (924HU), plaques with high volumes of these calcifications showed 4.40 times higher IPHvols compared to low-volumes of high-attenuation calcifications (p=0.011). Conclusions: Plaque calcification attenuation characteristics are associated with IPHvols. Beyond presence or volumes of plaque calcifications, calcification attenuation characteristics should be considered when evaluating unstable plaque components.
- Open Access
- 5 March 2025
- Published by Springer Nature in Statistics in Biosciences
- Vol. 18 (1) , 192-213
Novel Scalar-on-matrix Regression for Unbalanced Feature Matrices
Image features that characterize tubules from digitized kidney biopsies may offer insight into disease prognosis as novel biomarkers. For each subject, we can construct a matrix whose entries are a common set of image features (e.g., area, orientation, eccentricity) that are measured for each tubule from that subject’s biopsy. Previous scalar-on-matrix regression approaches which can predict scalar outcomes using image feature matrices cannot handle varying numbers of tubules across subjects. We propose the CLUstering Structured laSSO (CLUSSO), a novel scalar-on-matrix regression technique that allows for unbalanced numbers of tubules, to predict scalar outcomes from the image feature matrices. Through classifying tubules into one of two different clusters, CLUSSO averages and weights tubular feature values within-subject and within-cluster to create balanced feature matrices that can then be used with structured lasso regression. We develop the theoretical large tubule sample properties for the error bounds of the feature coefficient estimates. Simulation study results indicate that CLUSSO often achieves a lower false positive rate and higher true positive rate for identifying the image features which truly affect outcomes relative to a naive method that averages feature values across all tubules. Additionally, we find that CLUSSO has lower bias and can predict outcomes with a competitive accuracy to the naïve approach. Finally, we applied CLUSSO to tubular image features from kidney biopsies of glomerular disease subjects from the Nephrotic Syndrome Study Network (NEPTUNE) to predict kidney function and used subjects from the Cure Glomerulonephropathy (CureGN) study as an external validation set.
- 5 March 2025
- Published by Springer Nature in Statistics in Biosciences
- Vol. 18 (1) , 192-213
Open AccessNovel Scalar-on-matrix Regression for Unbalanced Feature Matrices
Image features that characterize tubules from digitized kidney biopsies may offer insight into disease prognosis as novel biomarkers. For each subject, we can construct a matrix whose entries are a common set of image features (e.g., area, orientation, eccentricity) that are measured for each tubule from that subject’s biopsy. Previous scalar-on-matrix regression approaches which can predict scalar outcomes using image feature matrices cannot handle varying numbers of tubules across subjects. We propose the CLUstering Structured laSSO (CLUSSO), a novel scalar-on-matrix regression technique that allows for unbalanced numbers of tubules, to predict scalar outcomes from the image feature matrices. Through classifying tubules into one of two different clusters, CLUSSO averages and weights tubular feature values within-subject and within-cluster to create balanced feature matrices that can then be used with structured lasso regression. We develop the theoretical large tubule sample properties for the error bounds of the feature coefficient estimates. Simulation study results indicate that CLUSSO often achieves a lower false positive rate and higher true positive rate for identifying the image features which truly affect outcomes relative to a naive method that averages feature values across all tubules. Additionally, we find that CLUSSO has lower bias and can predict outcomes with a competitive accuracy to the naïve approach. Finally, we applied CLUSSO to tubular image features from kidney biopsies of glomerular disease subjects from the Nephrotic Syndrome Study Network (NEPTUNE) to predict kidney function and used subjects from the Cure Glomerulonephropathy (CureGN) study as an external validation set.
- Top Cited Papers
- 1 March 2025
- Published by Wolters Kluwer Health in Stroke
- Vol. 56 (3) , 737-740
Prevalence of High-Risk CTA-Based Carotid Plaque-RADS Subtypes in Patients With Embolic Stroke of Undetermined Source
BACKGROUND: A modified computed tomography angiography (CTA)–based Carotid Plaque Reporting and Data System (Plaque-RADS) classification was applied to a cohort of patients with embolic stroke of undetermined source to test whether high-risk Plaque-RADS subtypes are more prevalent on the ipsilateral side of stroke. With the widespread use of CTA for stroke evaluation, a CTA-based Plaque-RADS would be valuable for generalizability. METHODS: A retrospective observational cross-sectional study was conducted at a single integrated health system comprised of 3 hospitals with a comprehensive stroke center between October 1, 2015, and April 1, 2017. Patients with unilateral anterior circulation stroke and 3 irrespective of plaque thickness. High-risk plaque subtypes (Plaque-RADS 3 and 4) were compared with low-risk subtypes (Plaque-RADS 1 and 2). RESULTS: Ninety-four patients (55% women; median age, 66 years) were included. CTA-based Plaque-RADS categories for plaques ipsilateral to the stroke side were as follows: (1) 14.9%, (2) 42.6%, (3) 41.5%, and (4) 1.1%. Carotid plaques contralateral to stroke side were Plaque-RADS: (1) 21.3%, (2) 46.8%, (3) 31.9%, and (4) 0%. When compared with the contralateral side, plaques ipsilateral to the stroke side were significantly associated with high-risk Plaque-RADS subtypes in a mixed-effects logistic model adjusting for age and sex (adjusted odds ratio, 2.10 [95% CI, 1.20–3.71]; P =0.01). CONCLUSIONS: Carotid plaque ipsilateral to the stroke side was significantly associated with CTA-based high-risk Plaque-RADS subtypes in an embolic stroke of undetermined source cohort. A CTA-based Plaque-RADS classification may be useful for identifying potentially causative carotid plaque phenotypes in patients with embolic stroke of undetermined source.
- 1 March 2025
- Published by Wolters Kluwer Health in Stroke
- Vol. 56 (3) , 737-740
Top Cited PapersPrevalence of High-Risk CTA-Based Carotid Plaque-RADS Subtypes in Patients With Embolic Stroke of Undetermined Source
BACKGROUND: A modified computed tomography angiography (CTA)–based Carotid Plaque Reporting and Data System (Plaque-RADS) classification was applied to a cohort of patients with embolic stroke of undetermined source to test whether high-risk Plaque-RADS subtypes are more prevalent on the ipsilateral side of stroke. With the widespread use of CTA for stroke evaluation, a CTA-based Plaque-RADS would be valuable for generalizability. METHODS: A retrospective observational cross-sectional study was conducted at a single integrated health system comprised of 3 hospitals with a comprehensive stroke center between October 1, 2015, and April 1, 2017. Patients with unilateral anterior circulation stroke and 3 irrespective of plaque thickness. High-risk plaque subtypes (Plaque-RADS 3 and 4) were compared with low-risk subtypes (Plaque-RADS 1 and 2). RESULTS: Ninety-four patients (55% women; median age, 66 years) were included. CTA-based Plaque-RADS categories for plaques ipsilateral to the stroke side were as follows: (1) 14.9%, (2) 42.6%, (3) 41.5%, and (4) 1.1%. Carotid plaques contralateral to stroke side were Plaque-RADS: (1) 21.3%, (2) 46.8%, (3) 31.9%, and (4) 0%. When compared with the contralateral side, plaques ipsilateral to the stroke side were significantly associated with high-risk Plaque-RADS subtypes in a mixed-effects logistic model adjusting for age and sex (adjusted odds ratio, 2.10 [95% CI, 1.20–3.71]; P =0.01). CONCLUSIONS: Carotid plaque ipsilateral to the stroke side was significantly associated with CTA-based high-risk Plaque-RADS subtypes in an embolic stroke of undetermined source cohort. A CTA-based Plaque-RADS classification may be useful for identifying potentially causative carotid plaque phenotypes in patients with embolic stroke of undetermined source.
- Open Access
- 5 December 2023
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 12 (23) , e031797
Imaging Biomarkers and Prevalence of Complex Aortic Plaque in Cryptogenic Stroke: A Systematic Review
Background: Complex aortic plaque (CAP) is a potential embolic source in patients with cryptogenic stroke (CS). We review CAP imaging criteria for transesophageal echocardiogram (TEE), computed tomography angiography (CTA), and magnetic resonance imaging and calculate CAP prevalence in patients with acute CS. Methods and Results: PubMed and EMBASE databases were searched up to December 2022 in accordance with the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses guideline. Two independent reviewers extracted data on study design, imaging techniques, CAP criteria, and prevalence. The Cochrane Collaboration tool and Guideline for Reporting Reliability and Agreement Studies were used to assess risk of bias and reporting completeness, respectively. From 2293 studies, 45 were reviewed for CAP imaging biomarker criteria in patients with acute CS (N=37 TEE; N=9 CTA; N=6 magnetic resonance imaging). Most studies (74%) used ≥4 mm plaque thickness as the imaging criterion for CAP although ≥1 mm (N=1, CTA), ≥5 mm (N=5, TEE), and ≥6 mm (N=2, CTA) were also reported. Additional features included mobility, ulceration, thrombus, protrusions, and assessment of plaque composition. From 23 prospective studies, CAP was detected in 960 of 2778 patients with CS (0.32 [95% CI, 0.24–0.41], I 2 =94%). By modality, prevalence estimates were 0.29 (95% CI, 0.20–0.40; I 2 =95%) for TEE; 0.23 (95% CI, 0.15–0.34; I 2 =87%) for CTA and 0.22 (95% CI, 0.06–0.54; I 2 =92%) for magnetic resonance imaging. Conclusions: TEE was commonly used to assess CAP in patients with CS. The most common CAP imaging biomarker was ≥4 mm plaque thickness. CAP was observed in one‐third of patients with acute CS. However, high study heterogeneity suggests a need for reproducible imaging methods.
- 5 December 2023
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 12 (23) , e031797
Open AccessImaging Biomarkers and Prevalence of Complex Aortic Plaque in Cryptogenic Stroke: A Systematic Review
Background: Complex aortic plaque (CAP) is a potential embolic source in patients with cryptogenic stroke (CS). We review CAP imaging criteria for transesophageal echocardiogram (TEE), computed tomography angiography (CTA), and magnetic resonance imaging and calculate CAP prevalence in patients with acute CS. Methods and Results: PubMed and EMBASE databases were searched up to December 2022 in accordance with the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses guideline. Two independent reviewers extracted data on study design, imaging techniques, CAP criteria, and prevalence. The Cochrane Collaboration tool and Guideline for Reporting Reliability and Agreement Studies were used to assess risk of bias and reporting completeness, respectively. From 2293 studies, 45 were reviewed for CAP imaging biomarker criteria in patients with acute CS (N=37 TEE; N=9 CTA; N=6 magnetic resonance imaging). Most studies (74%) used ≥4 mm plaque thickness as the imaging criterion for CAP although ≥1 mm (N=1, CTA), ≥5 mm (N=5, TEE), and ≥6 mm (N=2, CTA) were also reported. Additional features included mobility, ulceration, thrombus, protrusions, and assessment of plaque composition. From 23 prospective studies, CAP was detected in 960 of 2778 patients with CS (0.32 [95% CI, 0.24–0.41], I 2 =94%). By modality, prevalence estimates were 0.29 (95% CI, 0.20–0.40; I 2 =95%) for TEE; 0.23 (95% CI, 0.15–0.34; I 2 =87%) for CTA and 0.22 (95% CI, 0.06–0.54; I 2 =92%) for magnetic resonance imaging. Conclusions: TEE was commonly used to assess CAP in patients with CS. The most common CAP imaging biomarker was ≥4 mm plaque thickness. CAP was observed in one‐third of patients with acute CS. However, high study heterogeneity suggests a need for reproducible imaging methods.
- Open Access
- 5 April 2023
- Published by Wolters Kluwer Health in Kidney360
- Vol. 4 (5) , 648-658
Clinical Relevance of Computationally Derived Attributes of Peritubular Capillaries from Kidney Biopsies
Key Points: Computational image analysis allows for the extraction of new information from whole-slide images with potential clinical relevance. Peritubular capillary (PTC) density is decreased in areas of interstitial fibrosis and tubular atrophy when measured in interstitial fractional space. PTC shape (aspect ratio) is associated with clinical outcome in glomerular diseases. Background: The association between peritubular capillary (PTC) density and disease progression has been studied in a variety of kidney diseases using immunohistochemistry. However, other PTC attributes, such as PTC shape, have not been explored yet. The recent development of computer vision techniques provides the opportunity for the quantification of PTC attributes using conventional stains and whole-slide images. Methods: To explore the relationship between PTC characteristics and clinical outcome, n=280 periodic acid–Schiff-stained kidney biopsies (88 minimal change disease, 109 focal segmental glomerulosclerosis, 46 membranous nephropathy, and 37 IgA nephropathy) from the Nephrotic Syndrome Study Network digital pathology repository were computationally analyzed. A previously validated deep learning model was applied to segment cortical PTCs. Average PTC aspect ratio (PTC major to minor axis ratio), size (PTC pixels per PTC segmentation), and density (PTC pixels per unit cortical area) were computed for each biopsy. Cox proportional hazards models were used to assess associations between these PTC parameters and outcome (40% eGFR decline or kidney failure). Cortical PTC characteristics and interstitial fractional space PTC density were compared between areas of interstitial fibrosis and tubular atrophy (IFTA) and areas without IFTA. Results: When normalized PTC aspect ratio was below 0.6, a 0.1, increase in normalized PTC aspect ratio was significantly associated with disease progression, with a hazard ratio (95% confidence interval) of 1.28 (1.04 to 1.59) (P = 0.019), while PTC density and size were not significantly associated with outcome. Interstitial fractional space PTC density was lower in areas of IFTA compared with non-IFTA areas. Conclusions: Computational image analysis enables quantification of the status of the kidney microvasculature and the discovery of a previously unrecognized PTC biomarker (aspect ratio) of clinical outcome.
- 5 April 2023
- Published by Wolters Kluwer Health in Kidney360
- Vol. 4 (5) , 648-658
Open AccessClinical Relevance of Computationally Derived Attributes of Peritubular Capillaries from Kidney Biopsies
Key Points: Computational image analysis allows for the extraction of new information from whole-slide images with potential clinical relevance. Peritubular capillary (PTC) density is decreased in areas of interstitial fibrosis and tubular atrophy when measured in interstitial fractional space. PTC shape (aspect ratio) is associated with clinical outcome in glomerular diseases. Background: The association between peritubular capillary (PTC) density and disease progression has been studied in a variety of kidney diseases using immunohistochemistry. However, other PTC attributes, such as PTC shape, have not been explored yet. The recent development of computer vision techniques provides the opportunity for the quantification of PTC attributes using conventional stains and whole-slide images. Methods: To explore the relationship between PTC characteristics and clinical outcome, n=280 periodic acid–Schiff-stained kidney biopsies (88 minimal change disease, 109 focal segmental glomerulosclerosis, 46 membranous nephropathy, and 37 IgA nephropathy) from the Nephrotic Syndrome Study Network digital pathology repository were computationally analyzed. A previously validated deep learning model was applied to segment cortical PTCs. Average PTC aspect ratio (PTC major to minor axis ratio), size (PTC pixels per PTC segmentation), and density (PTC pixels per unit cortical area) were computed for each biopsy. Cox proportional hazards models were used to assess associations between these PTC parameters and outcome (40% eGFR decline or kidney failure). Cortical PTC characteristics and interstitial fractional space PTC density were compared between areas of interstitial fibrosis and tubular atrophy (IFTA) and areas without IFTA. Results: When normalized PTC aspect ratio was below 0.6, a 0.1, increase in normalized PTC aspect ratio was significantly associated with disease progression, with a hazard ratio (95% confidence interval) of 1.28 (1.04 to 1.59) (P = 0.019), while PTC density and size were not significantly associated with outcome. Interstitial fractional space PTC density was lower in areas of IFTA compared with non-IFTA areas. Conclusions: Computational image analysis enables quantification of the status of the kidney microvasculature and the discovery of a previously unrecognized PTC biomarker (aspect ratio) of clinical outcome.
- 30 January 2018
- Published by Optica Publishing Group in Applied Optics
- Vol. 57 (4) , 788-793
Acceleration of diffraction calculations in cylindrically symmetrical optics
We have significantly accelerated diffraction calculations using three independent acceleration devices. These innovations are restricted to cylindrically symmetrical systems. In the first case, we consider Wolf’s formula for integrated flux in a circular region following diffraction of light from a point source by a circular aperture or a circular lens. Although the formula involves a double sum, we evaluate it with the effort of a single sum by use of fast Fourier transforms (FFTs) to perform convolutions. In the second case, we exploit properties of the Fresnel–Kirchhoff propagator in the Gaussian, paraxial optics approximation to achieve the propagation of a partial wave from one optical element to the next. Ordinarily, this would involve a double loop over the radial variables on each element, but we have reduced the computational cost by a factor approximately equal to the smaller number of radius values. In the third case, we reduce the number of partial waves, for which the propagation needs to be calculated, to determine the throughput of an optical system of interest in radiometry when at least one element is very small, such as a pinhole aperture. As a demonstration of the benefits of the second case, we analyze intricate diffraction effects that occur in a satellite-based solar radiometry instrument.
- 30 January 2018
- Published by Optica Publishing Group in Applied Optics
- Vol. 57 (4) , 788-793
Acceleration of diffraction calculations in cylindrically symmetrical optics
We have significantly accelerated diffraction calculations using three independent acceleration devices. These innovations are restricted to cylindrically symmetrical systems. In the first case, we consider Wolf’s formula for integrated flux in a circular region following diffraction of light from a point source by a circular aperture or a circular lens. Although the formula involves a double sum, we evaluate it with the effort of a single sum by use of fast Fourier transforms (FFTs) to perform convolutions. In the second case, we exploit properties of the Fresnel–Kirchhoff propagator in the Gaussian, paraxial optics approximation to achieve the propagation of a partial wave from one optical element to the next. Ordinarily, this would involve a double loop over the radial variables on each element, but we have reduced the computational cost by a factor approximately equal to the smaller number of radius values. In the third case, we reduce the number of partial waves, for which the propagation needs to be calculated, to determine the throughput of an optical system of interest in radiometry when at least one element is very small, such as a pinhole aperture. As a demonstration of the benefits of the second case, we analyze intricate diffraction effects that occur in a satellite-based solar radiometry instrument.