Browsing by Author "Youssef, Khalid"

Now showing 1 - 7 of 7
  • Thumbnail Image
    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 Medicine
    Quantitative 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.
  • Thumbnail Image
    Item
    Accurate Intramyocardial Hemorrhage Assessment with Fast, Free-running, Cardiac Quantitative Susceptibility Mapping
    (Radiological Society of North America, 2024) Huang, Yuheng; Guan, Xingmin; Zhang, Xinheng; Yoosefian, Ghazal; Ho, Hao; Huang, Li-Ting; Lin, Hsin-Yao; Anthony, Gregory; Lee, Hsu-Lei; Bi, Xiaoming; Han, Fei; Chan, Shing Fai; Vora, Keyur P.; Sharif, Behzad; Singh, Dhirendra P.; Youssef, Khalid; Li, Debiao; Han, Hui; Christodoulou, Anthony G.; Dharmakumar, Rohan; Yang, Hsin-Jung; Medicine, School of Medicine
    Purpose: To evaluate the performance of a high-dynamic-range quantitative susceptibility mapping (HDR-QSM) cardiac MRI technique to detect intramyocardial hemorrhage (IMH) and quantify iron content using phantom and canine models. Materials and Methods: A free-running whole-heart HDR-QSM technique for IMH assessment was developed and evaluated in calibrated iron phantoms and 14 IMH female canine models. IMH detection and iron content quantification performance of this technique was compared with the conventional iron imaging approaches, R2*(1/T2*) maps, using measurements from ex vivo imaging as the reference standard. Results: Phantom studies confirmed HDR-QSM’s accurate iron content quantification and artifact mitigation ability by revealing a strong linear relationship between iron concentration and QSM values (R2, 0.98). In in vivo studies, HDR-QSM showed significantly improved image quality and susceptibility homogeneity in nonaffected myocardium by alleviating motion and off-resonance artifacts (HDR-QSM vs R2*: coefficient of variation, 0.31 ± 0.16 [SD] vs 0.73 ± 0.36 [P < .001]; image quality score [five-point Likert scale:], 3.58 ± 0.75 vs 2.87 ± 0.51 [P < .001]). Comparison between in vivo susceptibility maps and ex vivo measurements showed higher performance of HDR-QSM compared with R2* mapping for IMH detection (area under the receiver operating characteristic curve, 0.96 vs 0.75; P < .001) and iron content quantification (R2, 0.71 vs 0.14). Conclusion: In a canine model of IMH, the fast and free-running cardiac QSM technique accurately detected IMH and quantified intramyocardial iron content of the entire heart within 5 minutes without requiring breath holding.
  • Thumbnail Image
    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 Medicine
    In 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.
  • Thumbnail Image
    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 Medicine
    Purpose: 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.
  • Thumbnail Image
    Item
    Improved robustness for deep learning-based segmentation of multi-center myocardial perfusion cardiovascular MRI datasets using data-adaptive uncertainty–guided space-time analysis
    (Elsevier, 2024) Yalcinkaya, Dilek M.; Youssef, Khalid; Heydari, Bobak; Wei, Janet; Merz, C. Noel Bairey; Judd, Robert; Dharmakumar, Rohan; Simonetti, Orlando P.; Weinsaft, Jonathan W.; Raman, Subha V.; Sharif, Behzad; Medicine, School of Medicine
    Background: Fully automatic analysis of myocardial perfusion cardiovascular magnetic resonance imaging 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 three 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 inD (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 exDs (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). Conclusion: 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.
  • Thumbnail Image
    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 Medicine
    Background: 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.
  • Thumbnail Image
    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 Medicine
    Dynamic 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.