Browsing by Author "Sharif, Behzad"
Now showing 1 - 10 of 11
Results Per Page
Sort Options
Item A Patch-Wise Deep Learning Approach for Myocardial Blood Flow Quantification with Robustness to Noise and Nonrigid Motion(IEEE, 2021) Youssef, Khalid; Heydari, Bobby; Rivero, Luis Zamudio; Beaulieu, Taylor; Cheema, Karandeep; Dharmakumar, Rohan; Sharif, Behzad; Medicine, School of MedicineQuantitative analysis of dynamic contrast-enhanced cardiovascular MRI (cMRI) datasets enables the assessment of myocardial blood flow (MBF) for objective evaluation of ischemic heart disease in patients with suspected coronary artery disease. State-of-the-art MBF quantification techniques use constrained deconvolution and are highly sensitive to noise and motion-induced errors, which can lead to unreliable outcomes in the setting of high-resolution MBF mapping. To overcome these limitations, recent iterative approaches incorporate spatial-smoothness constraints to tackle pixel-wise MBF mapping. However, such iterative methods require a computational time of up to 30 minutes per acquired myocardial slice, which is a major practical limitation. Furthermore, they cannot enforce robustness to residual nonrigid motion which can occur in clinical stress/rest studies of patients with arrhythmia. We present a non-iterative patch-wise deep learning approach for pixel-wise MBF quantification wherein local spatio-temporal features are learned from a large dataset of myocardial patches acquired in clinical stress/rest cMRI studies. Our approach is scanner-independent, computationally efficient, robust to noise, and has the unique feature of robustness to motion-induced errors. Numerical and experimental results obtained using real patient data demonstrate the effectiveness of our approach.Clinical Relevance- The proposed patch-wise deep learning approach significantly improves the reliability of high-resolution myocardial blood flow quantification in cMRI by improving its robustness to noise and nonrigid myocardial motion and is up to 300-fold faster than state-of-the-art iterative approaches.Item Deep Learning-Based Segmentation and Uncertainty Assessment for Automated Analysis of Myocardial Perfusion MRI Datasets Using Patch-Level Training and Advanced Data Augmentation(IEEE, 2021) Yalcinkaya, Dilek Mirgun; Youssef, Khalid; Heydari, Bobby; Zamudio, Luis; Dharmakumar, Rohan; Sharif, Behzad; Medicine, School of MedicineIn this work, we develop a patch-level training approach and a task-driven intensity-based augmentation method for deep-learning-based segmentation of motion-corrected perfusion cardiac magnetic resonance imaging (MRI) datasets. Further, the proposed method generates an image-based uncertainty map thanks to a novel spatial sliding-window approach used during patch-level training, hence allowing for uncertainty quantification. Using the quantified uncertainty, we detect the out-of-distribution test data instances so that the end-user can be alerted that the test data is not suitable for the trained network. This feature has the potential to enable a more reliable integration of the proposed deep learning-based framework into clinical practice. We test our approach on external MRI data acquired using a different acquisition protocol to demonstrate the robustness of our performance to variations in pulse-sequence parameters. The presented results further demonstrate that our deep-learning image segmentation approach trained with the proposed data-augmentation technique incorporating spatiotemporal (2D+time) patches is superior to the state-of-the-art 2D approach in terms of generalization performance.Item Diastolic dysfunction in women with ischemia and no obstructive coronary artery disease: Mechanistic insight from magnetic resonance imaging(Elsevier, 2021) Samuel, T. Jake; Wei, Janet; Sharif, Behzad; Tamarappoo, Balaji K.; Pattisapu, Varun; Maughan, Jenna; Cipher, Daisha J.; Suppogu, Nissi; Aldiwani, Haider; Thomson, Louise E. J.; Shufelt, Chrisandra; Berman, Daniel S.; Li, Debiao; Bairey Merz, C. Noel; Nelson, Michael D.; Medicine, School of MedicineBackground: Ischemia with no obstructive coronary artery disease (INOCA) is prevalent in women and is associated with increased risk of developing heart failure with preserved ejection fraction (HFpEF); however, the mechanism(s) contributing to this progression remains unclear. Given that diastolic dysfunction is common in women with INOCA, defining mechanisms related to diastolic dysfunction in INOCA could identify therapeutic targets to prevent HFpEF. Methods: Cardiac MRI was performed in 65 women with INOCA and 12 reference controls. Diastolic function was defined by left ventricular early diastolic circumferential strain rate (eCSRd). Contributors to diastolic dysfunction were chosen a priori as coronary vascular dysfunction (myocardial perfusion reserve index [MPRI]), diffuse myocardial fibrosis (extracellular volume [ECV]), and aortic stiffness (aortic pulse wave velocity [aPWV]). Results: Compared to controls, eCSRd was lower in INOCA (1.61 ± 0.33/s vs. 1.36 ± 0.31/s, P = 0.016); however, this difference was not exaggerated when the INOCA group was sub-divided by low and high MPRI (P > 0.05) nor was ECV elevated in INOCA (29.0 ± 1.9% vs. 28.0 ± 3.2%, control vs. INOCA; P = 0.38). However, aPWV was higher in INOCA vs. controls (8.1 ± 3.2 m/s vs. 6.1 ± 1.5 m/s; P = 0.045), and was associated with eCSRd (r = -0.50, P < 0.001). By multivariable linear regression analysis, aPWV was an independent predictor of decreased eCSRd (standardized β = -0.39, P = 0.003), as was having an elevated left ventricular mass index (standardized β = -0.25, P = 0.024) and lower ECV (standardized β = 0.30, P = 0.003). Conclusions: These data provide mechanistic insight into diastolic dysfunction in women with INOCA, identifying aortic stiffness and ventricular remodeling as putative therapeutic targets.Item Enabling Reliable Visual Detection of Chronic Myocardial Infarction with Native T1 Cardiac MRI Using Data-Driven Native Contrast Mapping(Radiological Society of North America, 2024) Youssef, Khalid; Zhang, Xinheng; Yoosefian, Ghazal; Chen, Yinyin; Chan, Shing Fai; Yang, Hsin-Jung; Vora, Keyur; Howarth, Andrew; Kumar, Andreas; Sharif, Behzad; Dharmakumar, Rohan; Medicine, School of MedicinePurpose: To investigate whether infarct-to-remote myocardial contrast can be optimized by replacing generic fitting algorithms used to obtain native T1 maps with a data-driven machine learning pixel-wise approach in chronic reperfused infarct in a canine model. Materials and Methods: A controlled large animal model (24 canines, equal male and female animals) of chronic myocardial infarction with histologic evidence of heterogeneous infarct tissue composition was studied. Unsupervised clustering techniques using self-organizing maps and t-distributed stochastic neighbor embedding were used to analyze and visualize native T1-weighted pixel-intensity patterns. Deep neural network models were trained to map pixel-intensity patterns from native T1-weighted image series to corresponding pixels on late gadolinium enhancement (LGE) images, yielding visually enhanced noncontrast maps, a process referred to as data-driven native mapping (DNM). Pearson correlation coefficients and Bland-Altman analyses were used to compare findings from the DNM approach against standard T1 maps. Results: Native T1-weighted images exhibited distinct pixel-intensity patterns between infarcted and remote territories. Granular pattern visualization revealed higher infarct-to-remote cluster separability with LGE labeling as compared with native T1 maps. Apparent contrast-to-noise ratio from DNM (mean, 15.01 ± 2.88 [SD]) was significantly different from native T1 maps (5.64 ± 1.58; P < .001) but similar to LGE contrast-to-noise ratio (15.51 ± 2.43; P = .40). Infarcted areas based on LGE were more strongly correlated with DNM compared with native T1 maps (R2 = 0.71 for native T1 maps vs LGE; R2 = 0.85 for DNM vs LGE; P < .001). Conclusion: Native T1-weighted pixels carry information that can be extracted with the proposed DNM approach to maximize image contrast between infarct and remote territories for enhanced visualization of chronic infarct territories.Item Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis(ArXiv, 2024-08-09) Yalcinkaya, Dilek M.; Youssef, Khalid; Heydari, Bobak; Wei, Janet; Merz, Noel Bairey; Judd, Robert; Dharmakumar, Rohan; Simonetti, Orlando P.; Weinsaft, Jonathan W.; Raman, Subha V.; Sharif, Behzad; Medicine, School of MedicineBackground: Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge. Methods: Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.). Results: The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005). Conclusions: The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.Item Intramyocardial hemorrhage drives fatty degeneration of infarcted myocardium(Springer Nature, 2022-10-27) Cokic, Ivan; Chan, Shing Fai; Guan, Xingmin; Nair, Anand R.; Yang, Hsin-Jung; Liu, Ting; Chen, Yinyin; Hernando, Diego; Sykes, Jane; Tang, Richard; Butler, John; Dohnalkova, Alice; Kovarik, Libor; Finney, Robert; Kali, Avinash; Sharif, Behzad; Bouchard, Louis S.; Gupta, Rajesh; Krishnam, Mayil Singaram; Vora, Keyur; Tamarappoo, Balaji; Howarth, Andrew G.; Kumar, Andreas; Francis, Joseph; Reeder, Scott B.; Wood, John C.; Prato, Frank S.; Dharmakumar, Rohan; Medicine, School of MedicineSudden blockage of arteries supplying the heart muscle contributes to millions of heart attacks (myocardial infarction, MI) around the world. Although re-opening these arteries (reperfusion) saves MI patients from immediate death, approximately 50% of these patients go on to develop chronic heart failure (CHF) and die within a 5-year period; however, why some patients accelerate towards CHF while others do not remains unclear. Here we show, using large animal models of reperfused MI, that intramyocardial hemorrhage - the most damaging form of reperfusion injury (evident in nearly 40% of reperfused ST-elevation MI patients) - drives delayed infarct healing and is centrally responsible for continuous fatty degeneration of the infarcted myocardium contributing to adverse remodeling of the heart. Specifically, we show that the fatty degeneration of the hemorrhagic MI zone stems from iron-induced macrophage activation, lipid peroxidation, foam cell formation, ceroid production, foam cell apoptosis and iron recycling. We also demonstrate that timely reduction of iron within the hemorrhagic MI zone reduces fatty infiltration and directs the heart towards favorable remodeling. Collectively, our findings elucidate why some, but not all, MIs are destined to CHF and help define a potential therapeutic strategy to mitigate post-MI CHF independent of MI size.Item Left ventricular circumferential strain and coronary microvascular dysfunction: A report from the Women’s Ischemia Syndrome Evaluation Coronary Vascular Dysfunction (WISE-CVD) Project(Elsevier, 2021) Tamarappoo, Balaji; Samuel, T. Jake; Elboudwarej, Omeed; Thomson, Louise E. J.; Aldiwani, Haider; Wei, Janet; Mehta, Puja; Cheng, Susan; Sharif, Behzad; AlBadri, Ahmed; Handberg, Eileen M.; Petersen, John; Pepine, Carl J.; Nelson, Michael D.; Bairey Merz, C. Noel; Graduate Medical Education, School of MedicineAims: Women with ischemia but no obstructive coronary artery disease (INOCA) often have coronary microvascular dysfunction (CMD). Left ventricular (LV) circumferential strain (CS) is often lower in INOCA compared to healthy controls; however, it remains unclear whether CS differs between INOCA women with and without CMD. We hypothesized that CS would be lower in women with CMD, consistent with CMD-induced LV mechanical dysfunction. Methods and results: Cardiac magnetic resonance (cMR) images were examined from women enrolled in the Women's Ischemia Syndrome Evaluation-Coronary Vascular Dysfunction Project. CS by feature tracking in INOCA women with CMD, defined as myocardial perfusion reserve index (MPRI) <1.84 during adenosine-stress perfusion cMR, was compared with CS in women without CMD. In a subset who had invasive coronary function testing (CFT), the relationship between CS and CFT metrics, LV ejection fraction (LVEF) and cardiovascular risk factors was investigated. Among 317 women with INOCA, 174 (55%) had CMD measured by MPRI. CS was greater in women with CMD compared to those without CMD (23.2 ± 2.5% vs. 22.1 ± 3.0%, respectively, P = 0.001). In the subset with CFT (n = 153), greater CS was associated with increased likelihood of reduced vasodilator capacity (OR = 1.33, 95%CI = 1.02-1.72, p = 0.03) and discriminated abnormal vs. normal coronary vascular function compared to CAD risk factors, LVEF and LV concentricity (AUC: 0.82 [0.73-0.96 95%CI] vs. 0.65 [0.60-0.71 95%CI], respectively, P = 0.007). Conclusion: The data indicate that LV circumferential strain is related to and predicts CMD, although in a direction contrary with our hypothesis, which may represent an early sign of LV mechanical dysfunction in CMD.Item Reduced myocardial perfusion is common among subjects with ischemia and no obstructive coronary artery disease and heart failure with preserved ejection fraction: a report from the WISE-CVD continuation study(OAE, 2022) Aldiwani, Haider; Nelson, Michael D.; Sharif, Behzad; Wei, Janet; Samuel, T. Jake; Suppogu, Nissi; Quesada, Odayme; Cook-Wiens, Galen; Gill, Edward; Szczepaniak, Lidia S.; Thomson, Louise E. J.; Tamarappoo, Balaji; Asif, Anum; Shufelt, Chrisandra; Berman, Daniel; Merz, C. Noel Bairey; Medicine, School of MedicineAim: Women with evidence of ischemia and no obstructive coronary artery disease (INOCA) have an increased risk of major adverse cardiac events, including heart failure with preserved ejection fraction (HFpEF). To investigate potential links between INOCA and HFpEF, we examined pathophysiological findings present in both INOCA and HFpEF. Methods: We performed adenosine stress cardiac magnetic resonance imaging (CMRI) in 56 participants, including 35 women with suspected INOCA, 13 women with HFpEF, and 8 reference control women. Myocardial perfusion imaging was performed at rest and with vasodilator stress with intravenous adenosine. Myocardial perfusion reserve index was quantified as the ratio of the upslope of increase in myocardial contrast at stress vs. rest. All CMRI measures were quantified using CVI42 software (Circle Cardiovascular Imaging Inc). Statistical analysis was performed using linear regression models, Fisher's exact tests, ANOVA, or Kruskal-Wallis tests. Results: Age (P = 0.007), Body surface area (0.05) were higher in the HFpEF group. Left ventricular ejection fraction (P = 0.02) was lower among the INOCA and HFpEF groups than reference controls after age adjustment. In addition, there was a graded reduction in myocardial perfusion reserve index in HFpEF vs. INOCA vs. reference controls (1.5 ± 0.3, 1.8 ± 0.3, 1.9 ± 0.3, P = 0.02), which was attenuated with age-adjustment. Conclusion: Reduced myocardial perfusion reserve appears to be a common pathophysiologic feature in INOCA and HFpEF patients.Item Retrospective Detection and Suppression of Dark-Rim Artifacts in First-Pass Perfusion Cardiac MRI Enabled by Deep Learning(IEEE, 2021) Unal, Hazar Benan; Beaulieu, Taylor; Rivero, Luis Zamudio; Dharmakumar, Rohan; Sharif, Behzad; Medicine, School of MedicineThe dark-rim artifact (DRA) remains an important challenge in the routine clinical use of first-pass perfusion (FPP) cardiac magnetic resonance imaging (cMRI). The DRA mimics the appearance of perfusion defects in the subendocardial wall and reduces the accuracy of diagnosis in patients with suspected ischemic heart disease. The main causes for DRA are known to be Gibbs ringing and bulk motion of the heart. The goal of this work is to propose a deep-learning-enabled automatic approach for the detection of motion-induced DRAs in FPP cMRI datasets. To this end, we propose a new algorithm that can detect the DRA in individual time frames by analyzing multiple reconstructions of the same time frame (k-space data) with varying temporal windows. In addition to DRA detection, our approach is also capable of suppressing the extent and severity of DRAs as a byproduct of the same reconstruction-analysis process. In this proof-of-concept study, our proposed method showed a good performance for automatic detection of subendocardial DRAs in stress perfusion cMRI studies of patients with suspected ischemic heart disease. To the best of our knowledge, this is the first approach that performs deep-learning-enabled detection and suppression of DRAs in cMRI.Item Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets(ArXiv, 2023-11-13) Yalcinkaya, Dilek M.; Youssef, Khalid; Heydari, Bobak; Simonetti, Orlando; Dharmakumar, Rohan; Raman, Subha; Sharif, Behzad; Medicine, School of MedicineDynamic contrast-enhanced (DCE) cardiac magnetic resonance imaging (CMRI) is a widely used modality for diagnosing myocardial blood flow (perfusion) abnormalities. During a typical free-breathing DCE-CMRI scan, close to 300 time-resolved images of myocardial perfusion are acquired at various contrast "wash in/out" phases. Manual segmentation of myocardial contours in each time-frame of a DCE image series can be tedious and time-consuming, particularly when non-rigid motion correction has failed or is unavailable. While deep neural networks (DNNs) have shown promise for analyzing DCE-CMRI datasets, a "dynamic quality control" (dQC) technique for reliably detecting failed segmentations is lacking. Here we propose a new space-time uncertainty metric as a dQC tool for DNN-based segmentation of free-breathing DCE-CMRI datasets by validating the proposed metric on an external dataset and establishing a human-in-the-loop framework to improve the segmentation results. In the proposed approach, we referred the top 10% most uncertain segmentations as detected by our dQC tool to the human expert for refinement. This approach resulted in a significant increase in the Dice score (p < 0.001) and a notable decrease in the number of images with failed segmentation (16.2% to 11.3%) whereas the alternative approach of randomly selecting the same number of segmentations for human referral did not achieve any significant improvement. Our results suggest that the proposed dQC framework has the potential to accurately identify poor-quality segmentations and may enable efficient DNN-based analysis of DCE-CMRI in a human-in-the-loop pipeline for clinical interpretation and reporting of dynamic CMRI datasets.