Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning.

Introduction: Organ-at-risk segmentation for head and neck cancer radiation therapy is a complex and time-consuming process (requiring up to 42 individual structure, and may delay start of treatment or even limit access to function-preserving care. Feasibility of using a deep learning (DL) based autosegmentation model to reduce contouring time without compromising contour accuracy is assessed through a blinded randomized trial of radiation oncologists (ROs) using retrospective, de-identified patient data. Methods: Two head and neck expert ROs used dedicated time to create gold standard (GS) contours on computed tomography (CT) images. 445 CTs were used to train a custom 3D U-Net DL model covering 42 organs-at-risk, with an additional 20 CTs were held out for the randomized trial. For each held-out patient dataset, one of the eight participant ROs was randomly allocated to review and revise the contours produced by the DL model, while another reviewed contours produced by a medical dosimetry assistant (MDA), both blinded to their origin. Time required for MDAs and ROs to contour was recorded, and the unrevised DL contours, as well as the RO-revised contours by the MDAs and DL model were compared to the GS for that patient. Results: Mean time for initial MDA contouring was 2.3 hours (range 1.6-3.8 hours) and RO-revision took 1.1 hours (range, 0.4-4.4 hours), compared to 0.7 hours (range 0.1-2.0 hours) for the RO-revisions to DL contours. Total time reduced by 76% (95%-Confidence Interval: 65%-88%) and RO-revision time reduced by 35% (95%-CI,-39%-91%). All geometric and dosimetric metrics computed, agreement with GS was equivalent or significantly greater (p<0.05) for RO-revised DL contours compared to the RO-revised MDA contours, including volumetric Dice similarity coefficient (VDSC), surface DSC, added path length, and the 95%-Hausdorff distance. 32 OARs (76%) had mean VDSC greater than 0.8 for the RO-revised DL contours, compared to 20 (48%) for RO-revised MDA contours, and 34 (81%) for the unrevised DL OARs. Conclusion: DL autosegmentation demonstrated significant time-savings for organ-at-risk contouring while improving agreement with the institutional GS, indicating comparable accuracy of DL model. Integration into the clinical practice with a prospective evaluation is currently underway.

Anatomical labeling of intracranial arteries with deep learning in patients with cerebrovascular disease.

Brain arteries are routinely imaged in the clinical setting by various modalities, e.g., time-of-flight magnetic resonance angiography (TOF-MRA). These imaging techniques have great potential for the diagnosis of cerebrovascular disease, disease progression, and response to treatment. Currently, however, only qualitative assessment is implemented in clinical applications, relying on visual inspection. While manual or semi-automated approaches for quantification exist, such solutions are impractical in the clinical setting as they are time-consuming, involve too many processing steps, and/or neglect image intensity information. In this study, we present a deep learning-based solution for the anatomical labeling of intracranial arteries that utilizes complete information from 3D TOF-MRA images. We adapted and trained a state-of-the-art multi-scale Unet architecture using imaging data of 242 patients with cerebrovascular disease to distinguish 24 arterial segments. The proposed model utilizes vessel-specific information as well as raw image intensity information, and can thus take tissue characteristics into account. Our method yielded a performance of 0.89 macro F1 and 0.90 balanced class accuracy (bAcc) in labeling aggregated segments and 0.80 macro F1 and 0.83 bAcc in labeling detailed arterial segments on average. In particular, a higher F1 score than 0.75 for most arteries of clinical interest for cerebrovascular disease was achieved, with higher than 0.90 F1 scores in the larger, main arteries. Due to minimal pre-processing, simple usability, and fast predictions, our method could be highly applicable in the clinical setting.

Generating 3D TOF-MRA volumes and segmentation labels using generative adversarial networks.

Deep learning requires large labeled datasets that are difficult to gather in medical imaging due to data privacy issues and time-consuming manual labeling. Generative Adversarial Networks (GANs) can alleviate these challenges enabling synthesis of shareable data. While 2D GANs have been used to generate 2D images with their corresponding labels, they cannot capture the volumetric information of 3D medical imaging. 3D GANs are more suitable for this and have been used to generate 3D volumes but not their corresponding labels. One reason might be that synthesizing 3D volumes is challenging owing to computational limitations. In this work, we present 3D GANs for the generation of 3D medical image volumes with corresponding labels applying mixed precision to alleviate computational constraints. We generated 3D Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) patches with their corresponding brain blood vessel segmentation labels. We used four variants of 3D Wasserstein GAN (WGAN) with: 1) gradient penalty (GP), 2) GP with spectral normalization (SN), 3) SN with mixed precision (SN-MP), and 4) SN-MP with double filters per layer (c-SN-MP). The generated patches were quantitatively evaluated using the Fréchet Inception Distance (FID) and Precision and Recall of Distributions (PRD). Further, 3D U-Nets were trained with patch-label pairs from different WGAN models and their performance was compared to the performance of a benchmark U-Net trained on real data. The segmentation performance of all U-Net models was assessed using Dice Similarity Coefficient (DSC) and balanced Average Hausdorff Distance (bAVD) for a) all vessels, and b) intracranial vessels only. Our results show that patches generated with WGAN models using mixed precision (SN-MP and c-SN-MP) yielded the lowest FID scores and the best PRD curves. Among the 3D U-Nets trained with synthetic patch-label pairs, c-SN-MP pairs achieved the highest DSC (0.841) and lowest bAVD (0.508) compared to the benchmark U-Net trained on real data (DSC 0.901; bAVD 0.294) for intracranial vessels. In conclusion, our solution generates realistic 3D TOF-MRA patches and labels for brain vessel segmentation. We demonstrate the benefit of using mixed precision for computational efficiency resulting in the best-performing GAN-architecture. Our work paves the way towards sharing of labeled 3D medical data which would increase generalizability of deep learning models for clinical use.

To explain or not to explain?-Artificial intelligence explainability in clinical decision support systems.

Explainability for artificial intelligence (AI) in medicine is a hotly debated topic. Our paper presents a review of the key arguments in favor and against explainability for AI-powered Clinical Decision Support System (CDSS) applied to a concrete use case, namely an AI-powered CDSS currently used in the emergency call setting to identify patients with life-threatening cardiac arrest. More specifically, we performed a normative analysis using socio-technical scenarios to provide a nuanced account of the role of explainability for CDSSs for the concrete use case, allowing for abstractions to a more general level. Our analysis focused on three layers: technical considerations, human factors, and the designated system role in decision-making. Our findings suggest that whether explainability can provide added value to CDSS depends on several key questions: technical feasibility, the level of validation in case of explainable algorithms, the characteristics of the context in which the system is implemented, the designated role in the decision-making process, and the key user group(s). Thus, each CDSS will require an individualized assessment of explainability needs and we provide an example of how such an assessment could look like in practice.

Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study.

BACKGROUND: Over half a million individuals are diagnosed with head and neck cancer each year globally. Radiotherapy is an important curative treatment for this disease, but it requires manual time to delineate radiosensitive organs at risk. This planning process can delay treatment while also introducing interoperator variability, resulting in downstream radiation dose differences. Although auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying, and achieving expert performance remain. OBJECTIVE: Adopting a deep learning approach, we aim to demonstrate a 3D U-Net architecture that achieves expert-level performance in delineating 21 distinct head and neck organs at risk commonly segmented in clinical practice. METHODS: The model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practice and segmentations created by experienced radiographers as part of this research, all in accordance with consensus organ at risk definitions. RESULTS: We demonstrated the model's clinical applicability by assessing its performance on a test set of 21 computed tomography scans from clinical practice, each with 21 organs at risk segmented by 2 independent experts. We also introduced surface Dice similarity coefficient, a new metric for the comparison of organ delineation, to quantify the deviation between organ at risk surface contours rather than volumes, better reflecting the clinical task of correcting errors in automated organ segmentations. The model's generalizability was then demonstrated on 2 distinct open-source data sets, reflecting different centers and countries to model training. CONCLUSIONS: Deep learning is an effective and clinically applicable technique for the segmentation of the head and neck anatomy for radiotherapy. With appropriate validation studies and regulatory approvals, this system could improve the efficiency, consistency, and safety of radiotherapy pathways.

A novel approach for assessing hypoperfusion in stroke using spatial independent component analysis of resting-state fMRI.

Individualized treatment of acute stroke depends on the timely detection of ischemia and potentially salvageable tissue in the brain. Using functional MRI (fMRI), it is possible to characterize cerebral blood flow from blood-oxygen-level-dependent (BOLD) signals without the administration of exogenous contrast agents. In this study, we applied spatial independent component analysis to resting-state fMRI data of 37 stroke patients scanned within 24 hr of symptom onset, 17 of whom received follow-up scans the next day. Our analysis revealed "Hypoperfusion spatially-Independent Components" (HICs) whose spatial patterns of BOLD signal resembled regions of delayed perfusion depicted by dynamic susceptibility contrast MRI. These HICs were detected even in the presence of excessive patient motion, and disappeared following successful tissue reperfusion. The unique spatial and temporal features of HICs allowed them to be distinguished with high accuracy from other components in a user-independent manner (area under the curve = 0.93, balanced accuracy = 0.90, sensitivity = 1.00, and specificity = 0.85). Our study therefore presents a new, noninvasive method for assessing blood flow in acute stroke that minimizes interpretative subjectivity and is robust to severe patient motion.

A precision medicine framework for personalized simulation of hemodynamics in cerebrovascular disease.

BACKGROUND: Cerebrovascular disease, in particular stroke, is a major public health challenge. An important biomarker is cerebral hemodynamics. To measure and quantify cerebral hemodynamics, however, only invasive, potentially harmful or time-to-treatment prolonging methods are available. RESULTS: We present a simulation-based approach which allows calculation of cerebral hemodynamics based on the patient-individual vessel configuration derived from structural vessel imaging. For this, we implemented a framework allowing segmentation and annotation of brain vessels from structural imaging followed by 0-dimensional lumped simulation modeling of cerebral hemodynamics. For annotation, a 3D-graphical user interface was implemented. For 0D-simulation, we used a modified nodal analysis, which was adapted for easy implementation by code. The simulation enables identification of areas vulnerable to stroke and simulation of changes due to different systemic blood pressures. Moreover, sensitivity analysis was implemented allowing the live simulation of changes to simulate procedures and disease progression. Beyond presentation of the framework, we demonstrated in an exploratory analysis in 67 patients that the simulation has a high specificity and low-to-moderate sensitivity to detect perfusion changes in classic perfusion imaging. CONCLUSIONS: The presented precision medicine approach using novel biomarkers has the potential to make the application of harmful and complex perfusion methods obsolete.

Synthesizing anonymized and labeled TOF-MRA patches for brain vessel segmentation using generative adversarial networks.

Anonymization and data sharing are crucial for privacy protection and acquisition of large datasets for medical image analysis. This is a big challenge, especially for neuroimaging. Here, the brain's unique structure allows for re-identification and thus requires non-conventional anonymization. Generative adversarial networks (GANs) have the potential to provide anonymous images while preserving predictive properties. Analyzing brain vessel segmentation, we trained 3 GANs on time-of-flight (TOF) magnetic resonance angiography (MRA) patches for image-label generation: 1) Deep convolutional GAN, 2) Wasserstein-GAN with gradient penalty (WGAN-GP) and 3) WGAN-GP with spectral normalization (WGAN-GP-SN). The generated image-labels from each GAN were used to train a U-net for segmentation and tested on real data. Moreover, we applied our synthetic patches using transfer learning on a second dataset. For an increasing number of up to 15 patients we evaluated the model performance on real data with and without pre-training. The performance for all models was assessed by the Dice Similarity Coefficient (DSC) and the 95th percentile of the Hausdorff Distance (95HD). Comparing the 3 GANs, the U-net trained on synthetic data generated by the WGAN-GP-SN showed the highest performance to predict vessels (DSC/95HD 0.85/30.00) benchmarked by the U-net trained on real data (0.89/26.57). The transfer learning approach showed superior performance for the same GAN compared to no pre-training, especially for one patient only (0.91/24.66 vs. 0.84/27.36). In this work, synthetic image-label pairs retained generalizable information and showed good performance for vessel segmentation. Besides, we showed that synthetic patches can be used in a transfer learning approach with independent data. This paves the way to overcome the challenges of scarce data and anonymization in medical imaging.

Outcome prediction in aneurysmal subarachnoid hemorrhage: a comparison of machine learning methods and established clinico-radiological scores.

Reliable prediction of outcomes of aneurysmal subarachnoid hemorrhage (aSAH) based on factors available at patient admission may support responsible allocation of resources as well as treatment decisions. Radiographic and clinical scoring systems may help clinicians estimate disease severity, but their predictive value is limited, especially in devising treatment strategies. In this study, we aimed to examine whether a machine learning (ML) approach using variables available on admission may improve outcome prediction in aSAH compared to established scoring systems. Combined clinical and radiographic features as well as standard scores (Hunt & Hess, WFNS, BNI, Fisher, and VASOGRADE) available on patient admission were analyzed using a consecutive single-center database of patients that presented with aSAH (n = 388). Different ML models (seven algorithms including three types of traditional generalized linear models, as well as a tree bosting algorithm, a support vector machine classifier (SVMC), a Naive Bayes (NB) classifier, and a multilayer perceptron (MLP) artificial neural net) were trained for single features, scores, and combined features with a random split into training and test sets (4:1 ratio), ten-fold cross-validation, and 50 shuffles. For combined features, feature importance was calculated. There was no difference in performance between traditional and other ML applications using traditional clinico-radiographic features. Also, no relevant difference was identified between a combined set of clinico-radiological features available on admission (highest AUC 0.78, tree boosting) and the best performing clinical score GCS (highest AUC 0.76, tree boosting). GCS and age were the most important variables for the feature combination. In this cohort of patients with aSAH, the performance of functional outcome prediction by machine learning techniques was comparable to traditional methods and established clinical scores. Future work is necessary to examine input variables other than traditional clinico-radiographic features and to evaluate whether a higher performance for outcome prediction in aSAH can be achieved.

Opening the black box of artificial intelligence for clinical decision support: A study predicting stroke outcome.

State-of-the-art machine learning (ML) artificial intelligence methods are increasingly leveraged in clinical predictive modeling to provide clinical decision support systems to physicians. Modern ML approaches such as artificial neural networks (ANNs) and tree boosting often perform better than more traditional methods like logistic regression. On the other hand, these modern methods yield a limited understanding of the resulting predictions. However, in the medical domain, understanding of applied models is essential, in particular, when informing clinical decision support. Thus, in recent years, interpretability methods for modern ML methods have emerged to potentially allow explainable predictions paired with high performance. To our knowledge, we present in this work the first explainability comparison of two modern ML methods, tree boosting and multilayer perceptrons (MLPs), to traditional logistic regression methods using a stroke outcome prediction paradigm. Here, we used clinical features to predict a dichotomized 90 days post-stroke modified Rankin Scale (mRS) score. For interpretability, we evaluated clinical features' importance with regard to predictions using deep Taylor decomposition for MLP, Shapley values for tree boosting and model coefficients for logistic regression. With regard to performance as measured by Area under the Curve (AUC) values on the test dataset, all models performed comparably: Logistic regression AUCs were 0.83, 0.83, 0.81 for three different regularization schemes; tree boosting AUC was 0.81; MLP AUC was 0.83. Importantly, the interpretability analysis demonstrated consistent results across models by rating age and stroke severity consecutively amongst the most important predictive features. For less important features, some differences were observed between the methods. Our analysis suggests that modern machine learning methods can provide explainability which is compatible with domain knowledge interpretation and traditional method rankings. Future work should focus on replication of these findings in other datasets and further testing of different explainability methods.

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease.

Introduction: Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Non-invasive neuroimaging techniques, such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods: BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from three different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high- and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD); and via visual qualitative rating. Results: The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165, and 95HD = 29.153. The BRAVE-NET model was also the most resistant toward false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion: We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease and an external set of healthy volunteers. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.

A U-Net Deep Learning Framework for High Performance Vessel Segmentation in Patients With Cerebrovascular Disease.

Brain vessel status is a promising biomarker for better prevention and treatment in cerebrovascular disease. However, classic rule-based vessel segmentation algorithms need to be hand-crafted and are insufficiently validated. A specialized deep learning method-the U-net-is a promising alternative. Using labeled data from 66 patients with cerebrovascular disease, the U-net framework was optimized and evaluated with three metrics: Dice coefficient, 95% Hausdorff distance (95HD) and average Hausdorff distance (AVD). The model performance was compared with the traditional segmentation method of graph-cuts. Training and reconstruction was performed using 2D patches. A full and a reduced architecture with less parameters were trained. We performed both quantitative and qualitative analyses. The U-net models yielded high performance for both the full and the reduced architecture: A Dice value of ~0.88, a 95HD of ~47 voxels and an AVD of ~0.4 voxels. The visual analysis revealed excellent performance in large vessels and sufficient performance in small vessels. Pathologies like cortical laminar necrosis and a rete mirabile led to limited segmentation performance in few patients. The U-net outperfomed the traditional graph-cuts method (Dice ~0.76, 95HD ~59, AVD ~1.97). Our work highly encourages the development of clinically applicable segmentation tools based on deep learning. Future works should focus on improved segmentation of small vessels and methodologies to deal with specific pathologies.

Diagnostic and prognostic benefit of arterial spin labeling in subacute stroke.

BACKGROUND AND PURPOSE: Brain perfusion measurement in the subacute phase of stroke may support therapeutic decisions. We evaluated whether arterial spin labeling (ASL), a noninvasive perfusion imaging technique based on magnetic resonance imaging (MRI), adds diagnostic and prognostic benefit to diffusion-weighted imaging (DWI) in subacute stroke. METHODS: In a single-center imaging study, patients with DWI lesion(s) in the middle cerebral artery (MCA) territory were included. Onset to imaging time was ≤7 days and imaging included ASL and DWI sequences. Qualitative (standardized visual analysis) and quantitative perfusion analyses (region of interest analysis) were performed. Dichotomized early outcome (modified Rankin Scale [mRS] 0-2 vs. 3-6) was analyzed in two logistic regression models. Model 1 included DWI lesion volume, age, vascular pathology, admission NIHSS, and acute stroke treatment as covariates. Model 2 added the ASL-based perfusion pattern to Model 1. Receiver-operating-characteristic (ROC) and area-under-the-curve (AUC) were calculated for both models to assess their predictive power. The likelihood-ratio-test compared both models. RESULTS: Thirty-eight patients were included (median age 70 years, admission NIHSS 4, onset to imaging time 67 hr, discharge mRS 2). Qualitative perfusion analysis yielded additional diagnostic information in 84% of the patients. In the quantitative analysis, AUC for outcome prediction was 0.88 (95% CI 0.77-0.99) for Model 1 and 0.97 (95% CI 0.91-1.00) for Model 2. Inclusion of perfusion data significantly improved performance and outcome prediction (p = 0.002) of stroke imaging. CONCLUSIONS: In patients with subacute stroke, our study showed that adding perfusion imaging to structural imaging and clinical data significantly improved outcome prediction. This highlights the usefulness of ASL and noninvasive perfusion biomarkers in stroke diagnosis and management.

Boosted Tree Model Reforms Multimodal Magnetic Resonance Imaging Infarct Prediction in Acute Stroke.

BACKGROUND AND PURPOSE: Stroke imaging is pivotal for diagnosis and stratification of patients with acute ischemic stroke to treatment. The potential of combining multimodal information into reliable estimates of outcome learning calls for robust machine learning techniques with high flexibility and accuracy. We applied the novel extreme gradient boosting algorithm for multimodal magnetic resonance imaging-based infarct prediction. METHODS: In a retrospective analysis of 195 patients with acute ischemic stroke, fluid-attenuated inversion recovery, diffusion-weighted imaging, and 10 perfusion parameters were derived from acute magnetic resonance imaging scans. They were integrated to predict final infarct as seen on follow-up T2-fluid-attenuated inversion recovery using the extreme gradient boosting and compared with a standard generalized linear model approach using cross-validation. Submodels for recanalization and persistent occlusion were calculated and were used to identify the important imaging markers. Performance in infarct prediction was analyzed with receiver operating characteristics. Resulting areas under the curve and accuracy rates were compared using Wilcoxon signed-rank test. RESULTS: The extreme gradient boosting model demonstrated significantly higher performance in infarct prediction compared with generalized linear model in both cross-validation approaches: 5-folds (P<10e-16) and leave-one-out (P<0.015). The imaging parameters time-to-peak, mean transit time, time-to-maximum, and diffusion-weighted imaging were indicated as most valuable for infarct prediction by the systematic algorithm rating. Notably, the performance improvement was higher with 5-folds cross-validation approach than leave-one-out. CONCLUSIONS: We demonstrate extreme gradient boosting as a state-of-the-art method for clinically applicable multimodal magnetic resonance imaging infarct prediction in acute ischemic stroke. Our findings emphasize the role of perfusion parameters as important biomarkers for infarct prediction. The effect of cross-validation techniques on performance indicates that the intrapatient variability is expressed in nonlinear dynamics of the imaging modalities.

Multiparametric Model for Penumbral Flow Prediction in Acute Stroke.

BACKGROUND AND PURPOSE: Identification of salvageable penumbra tissue by dynamic susceptibility contrast magnetic resonance imaging is a valuable tool for acute stroke patient stratification for treatment. However, prior studies have not attempted to combine the different perfusion maps into a predictive model. In this study, we established a multiparametric perfusion imaging model and cross-validated it using positron emission tomography perfusion for detection of penumbral flow. METHODS: In a retrospective analysis of 17 subacute stroke patients with consecutive magnetic resonance imaging and H2O15 positron emission tomography scans, perfusion maps of cerebral blood flow, cerebral blood volume, mean transit time, time-to-maximum, and time-to-peak were constructed and combined using a generalized linear model (GLM). Both the GLM maps and the single perfusion maps alone were cross-validated with positron emission tomography-cerebral blood flow scans to predict penumbral flow on a voxel-wise level. Performance was tested by receiver-operating characteristics curve analysis, that is, the area under the curve, and the models' fits were compared using the likelihood ratio test. RESULTS: The GLM demonstrated significantly improved model fit compared with each of the single perfusion maps (P<1×e-5) and demonstrated higher performance, with an area under the curve of 0.91. However, the absolute difference between the performance of GLM and the best-performing single perfusion parameter (time-to-maximum) was relatively low (area under the curve difference =0.04). CONCLUSIONS: Our results support a dynamic susceptibility contrast magnetic resonance imaging-based GLM as an improved model for penumbral flow prediction in stroke patients. With given perfusion maps, this model is a straightforward and observer-independent alternative for therapy stratification.

A PET-Guided Framework Supports a Multiple Arterial Input Functions Approach in DSC-MRI in Acute Stroke.

BACKGROUND AND PURPOSE: In acute stroke, arterial-input-function (AIF) determination is essential for obtaining perfusion estimates with dynamic susceptibility-weighted contrast-enhanced magnetic resonance imaging (DSC-MRI). Standard DSC-MRI postprocessing applies single AIF selection, ie, global AIF. Physiological considerations, however, suggest that a multiple AIFs selection method would improve perfusion estimates to detect penumbral flow. In this study, we developed a framework based on comparable DSC-MRI and positron emission tomography (PET) images to compare the two AIF selection approaches and assess their performance in penumbral flow detection in acute stroke. METHODS: In a retrospective analysis of 17 sub(acute) stroke patients with consecutive MRI and PET scans, voxel-wise optimized AIFs were calculated based on the kinetic model as derived from both imaging modalities. Perfusion maps were calculated based on the optimized-AIF using two methodologies: (1) Global AIF and (2) multiple AIFs as identified by cluster analysis. Performance of penumbral-flow detection was tested by receiver-operating characteristics (ROC) curve analysis, ie, the area under the curve (AUC). RESULTS: Large variation of optimized AIFs across brain voxels demonstrated that there is no optimal single AIF. Subsequently, the multiple-AIF method (AUC range over all maps: .82-.90) outperformed the global AIF methodology (AUC .72-.85) significantly. CONCLUSIONS: We provide PET imaging-based evidence that a multiple AIF methodology is beneficial for penumbral flow detection in comparison with the standard global AIF methodology in acute stroke.

Comparison of the 2 Most Popular Deconvolution Techniques for the Detection of Penumbral Flow in Acute Stroke.

BACKGROUND AND PURPOSE: Dynamic susceptibility-weighted contrast-enhanced (DSC) magnetic resonance imaging (MRI) is used to identify the tissue-at-risk in acute stroke, but the choice of optimal DSC postprocessing in the clinical setting remains a matter of debate. Using 15O-water positron emission tomography (PET), we validated the performance of 2 common deconvolution methods for DSC-MRI. METHODS: In (sub)acute stroke patients with consecutive MRI and PET imaging, DSC maps were calculated applying 2 deconvolution methods, standard and block-circulant single value decomposition. We used 2 standardized analysis methods, a region of interest-based and a voxel-based analysis, where PET cerebral blood flow masks of <20 mL/100 g per minute (penumbral flow) and gray matter masks were overlaid on DSC parameter maps. For both methods, receiver operating characteristic curve analysis was performed to identify the accuracy of each DSC-MR map for the detection of PET penumbral flow. RESULTS: In 18 data sets (median time after stroke onset: 18 hours; median time PET to MRI: 101 minutes), block-circulant single value decomposition showed significantly better performance to detect PET penumbral flow only for mean transit time maps. Time-to-maximum (Tmax) had the highest performance independent of the deconvolution method. CONCLUSIONS: Block-circulant single value decomposition seems only significantly beneficial for mean transit time maps in (sub)acute stroke. Tmax is likely the most stable deconvolved parameter for the detection of tissue-at-risk using DSC-MRI.