Search

AIM: We tested the hypothesis that visual field (VF) progression can be predicted with a deep learning model based on longitudinal pairs of optic disc photographs (ODP) acquired at earlier time points during follow-up. METHODS: 3919 eyes (2259 patients) with ≥2 ODPs at least 2 years apart, and ≥5 24-2 VF exams spanning ≥3 years of follow-up were included. Serial VF mean deviation (MD) rates of change were estimated starting at the fifth visit and subsequently by adding visits until final visit. VF progression was defined as a statistically significant negative slope at two consecutive visits and final visit. We built a twin-neural network with ResNet50-backbone. A pair of ODPs acquired up to a year before the VF progression date or the last VF in non-progressing eyes were included as input. Primary outcome measures were area under the receiver operating characteristic curve (AUC) and model accuracy. RESULTS: The average (SD) follow-up time and baseline VF MD were 8.1 (4.8) years and -3.3 (4.9) dB, respectively. VF progression was identified in 761 eyes (19%). The median (IQR) time to progression in progressing eyes was 7.3 (4.5-11.1) years. The AUC and accuracy for predicting VF progression were 0.862 (0.812-0.913) and 80.0% (73.9%-84.6%). When only fast-progressing eyes were considered (MD rate < -1.0 dB/year), AUC increased to 0.926 (0.857-0.994). CONCLUSIONS: A deep learning model can predict subsequent glaucoma progression from longitudinal ODPs with clinically relevant accuracy. This model may be implemented, after validation, for predicting glaucoma progression in the clinical setting.

BACKGROUND: The monitoring and analysis of quasi-periodic biological signals such as electrocardiography (ECG), intracranial pressure (ICP), and cerebral blood flow velocity (CBFV) waveforms plays an important role in the early detection of adverse patient events and contributes to improved care management in the intensive care unit (ICU). This work quantitatively evaluates existing computational frameworks for automatically extracting peaks within ICP waveforms. METHODS: Peak detection techniques based on state-of-the-art machine learning models were evaluated in terms of robustness to varying noise levels. The evaluation was performed on a dataset of ICP signals assembled from 700 h of monitoring from 64 neurosurgical patients. The groundtruth of the peak locations was established manually on a subset of 13, 611 pulses. Additional evaluation was performed using a simulated dataset of ICP with controlled temporal dynamics and noise. RESULTS: The quantitative analysis of peak detection algorithms applied to individual waveforms indicates that most techniques provide acceptable accuracy with a mean absolute error (MAE) ≤ 10 ms without noise. In the presence of a higher noise level, however, only kernel spectral regression and random forest remain below that error threshold while the performance of other techniques deteriorates. Our experiments also demonstrated that tracking methods such as Bayesian inference and long short-term memory (LSTM) can be applied continuously and provide additional robustness in situations where single pulse analysis methods fail, such as missing data. CONCLUSION: While machine learning-based peak detection methods require manually labeled data for training, these models outperform conventional signal processing ones based on handcrafted rules and should be considered for peak detection in modern frameworks. In particular, peak tracking methods that incorporate temporal information between successive periods of the signals have demonstrated in our experiments to provide more robustness to noise and temporary artifacts that commonly arise as part of the monitoring setup in the clinical setting.

Multi-parametric MRI (mpMRI) is widely used for prostate cancer (PCa) diagnosis. Deep learning models show good performance in detecting PCa on mpMRI, but domain-specific PCa-related anatomical information is sometimes overlooked and not fully explored even by state-of-the-art deep learning models, causing potential suboptimal performances in PCa detection. Symmetric-related anatomical information is commonly used when distinguishing PCa lesions from other visually similar but benign prostate tissue. In addition, different combinations of mpMRI findings are used for evaluating the aggressiveness of PCa for abnormal findings allocated in different prostate zones. In this study, we investigate these domain-specific anatomical properties in PCa diagnosis and how we can adopt them into the deep learning framework to improve the models detection performance. We propose an anatomical-aware PCa detection Network (AtPCa-Net) for PCa detection on mpMRI. Experiments show that the AtPCa-Net can better utilize the anatomical-related information, and the proposed anatomical-aware designs help improve the overall model performance on both PCa detection and patient-level classification.

INTRODUCTION: Despite significant advances in managing acute stroke and reducing stroke mortality, preventing complications like post-stroke epilepsy (PSE) has seen limited progress. PSE research has been scattered worldwide with varying methodologies and data reporting. To address this, we established the International Post-stroke Epilepsy Research Consortium (IPSERC) to integrate global PSE research efforts. This protocol outlines an individual patient data meta-analysis (IPD-MA) to determine outcomes in patients with post-stroke seizures (PSS) and develop/validate PSE prediction models, comparing them with existing models. This protocol informs about creating the International Post-stroke Epilepsy Research Repository (IPSERR) to support future collaborative research. METHODS AND ANALYSIS: We utilised a comprehensive search strategy and searched MEDLINE, Embase, PsycInfo, Cochrane, and Web of Science databases until 30 January 2023. We extracted observational studies of stroke patients aged ≥18 years, presenting early or late PSS with data on patient outcome measures, and conducted the risk of bias assessment. We did not apply any restriction based on the date or language of publication. We will invite these study authors and the IPSERC collaborators to contribute IPD to IPSERR. We will review the IPD lodged within IPSERR to identify patients who developed epileptic seizures and those who did not. We will merge the IPD files of individual data and standardise the variables where possible for consistency. We will conduct an IPD-MA to estimate the prognostic value of clinical characteristics in predicting PSE. ETHICS AND DISSEMINATION: Ethics approval is not required for this study. The results will be published in peer-reviewed journals. This study will contribute to IPSERR, which will be available to researchers for future PSE research projects. It will also serve as a platform to anchor future clinical trials. TRIAL REGISTRATION NUMBER: NCT06108102.

PURPOSE: Predict central 10° global and local visual field (VF) measurements from macular optical coherence tomography (OCT) volume scans with deep learning (DL). METHODS: This study included 1121 OCT volume scans and 10-2 VFs from 289 eyes (257 patients). Macular scans were used to estimate 10-2 VF mean deviation (MD), threshold sensitivities (TS), and total deviation (TD) values at 68 locations. A three-dimensional (3D) convolutional neural network based on the 3D DenseNet121 architecture was used for prediction. We compared DL predictions to those from baseline linear models. We carried out 10-fold stratified cross-validation to optimize generalizability. The performance of the DL and baseline models was compared based on correlations between ground truth and predicted VF measures and mean absolute error (MAE; ground truth - predicted values). RESULTS: Average (SD) MD was -9.3 (7.7) dB. Average (SD) correlations between predicted and ground truth MD and MD MAE were 0.74 (0.09) and 3.5 (0.4) dB, respectively. Estimation accuracy deteriorated with worsening MD. Average (SD) Pearson correlations between predicted and ground truth TS and MAEs for DL and baseline model were 0.71 (0.05) and 0.52 (0.05) (P < 0.001) and 6.5 (0.6) and 7.5 (0.5) dB (P < 0.001), respectively. For TD, correlation (SD) and MAE (SD) for DL and baseline models were 0.69 (0.02) and 0.48 (0.05) (P < 0.001) and 6.1 (0.5) and 7.8 (0.5) dB (P < 0.001), respectively. CONCLUSIONS: Macular OCT volume scans can be used to predict global central VF parameters with clinically relevant accuracy. TRANSLATIONAL RELEVANCE: Macular OCT imaging may be used to confirm and supplement central VF findings using deep learning.

Background Perfusion imaging is important to identify a target mismatch in stroke but requires contrast agents and postprocessing software. Purpose To use a deep learning model to predict the hypoperfusion lesion in stroke and identify patients with a target mismatch profile from diffusion-weighted imaging (DWI) and clinical information alone, using perfusion MRI as the reference standard. Materials and Methods Imaging data sets of patients with acute ischemic stroke with baseline perfusion MRI and DWI were retrospectively reviewed from multicenter data available from 2008 to 2019 (Imaging Collaterals in Acute Stroke, Diffusion and Perfusion Imaging Evaluation for Understanding Stroke Evolution 2, and University of California, Los Angeles stroke registry). For perfusion MRI, rapid processing of perfusion and diffusion software automatically segmented the hypoperfusion lesion (time to maximum, ≥6 seconds) and ischemic core (apparent diffusion coefficient [ADC], ≤620 × 10-6 mm2/sec). A three-dimensional U-Net deep learning model was trained using baseline DWI, ADC, National Institutes of Health Stroke Scale score, and stroke symptom sidedness as inputs, with the union of hypoperfusion and ischemic core segmentation serving as the ground truth. Model performance was evaluated using the Dice score coefficient (DSC). Target mismatch classification based on the model was compared with that of the clinical-DWI mismatch approach defined by the DAWN trial by using the McNemar test. Results Overall, 413 patients (mean age, 67 years ± 15 [SD]; 207 men) were included for model development and primary analysis using fivefold cross-validation (247, 83, and 83 patients in the training, validation, and test sets, respectively, for each fold). The model predicted the hypoperfusion lesion with a median DSC of 0.61 (IQR, 0.45-0.71). The model identified patients with target mismatch with a sensitivity of 90% (254 of 283; 95% CI: 86, 93) and specificity of 77% (100 of 130; 95% CI: 69, 83) compared with the clinical-DWI mismatch sensitivity of 50% (140 of 281; 95% CI: 44, 56) and specificity of 89% (116 of 130; 95% CI: 83, 94) (P < .001 for all). Conclusion A three-dimensional U-Net deep learning model predicted the hypoperfusion lesion from diffusion-weighted imaging (DWI) and clinical information and identified patients with a target mismatch profile with higher sensitivity than the clinical-DWI mismatch approach. ClinicalTrials.gov registration nos. NCT02225730, NCT01349946, NCT02586415 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Kallmes and Rabinstein in this issue.

Patients with obstructive sleep apnea (OSA) show autonomic, mood, cognitive, and breathing dysfunctions that are linked to increased morbidity and mortality, which can be improved with early screening and intervention. The gold standard and other available methods for OSA diagnosis are complex, require whole-night data, and have significant wait periods that potentially delay intervention. Our aim was to examine whether using faster and less complicated machine learning models, including support vector machine (SVM) and random forest (RF), with brain diffusion tensor imaging (DTI) data can classify OSA from healthy controls. We collected two DTI series from 59 patients with OSA [age: 50.2 ± 9.9 years; body mass index (BMI): 31.5 ± 5.6 kg/m2 ; apnea-hypopnea index (AHI): 34.1 ± 21.2 events/h 23 female] and 96 controls (age: 51.8 ± 9.7 years; BMI: 26.2 ± 4.1 kg/m2 ; 51 female) using a 3.0-T magnetic resonance imaging scanner. Using DTI data, mean diffusivity maps were calculated from each series, realigned and averaged, normalised to a common space, and used to conduct cross-validation for model training and selection and to predict OSA. The RF model showed 0.73 OSA and controls classification accuracy and 0.85 area under the curve (AUC) value on the receiver-operator curve. Cross-validation showed the RF model with comparable fitting over SVM for OSA and control data (SVM; accuracy, 0.77; AUC, 0.84). The RF ML model performs similar to SVM, indicating the comparable statistical fitness to DTI data. The findings indicate that RF model has similar AUC and accuracy over SVM, and either model can be used as a faster OSA screening tool for subjects having brain DTI data.

Prostate-specific membrane antigen (PSMA) positron emission tomography (PET)/computed tomography (CT) is a molecular and functional imaging modality with better restaging accuracy over conventional imaging for detecting prostate cancer in men suspected of lymph node (LN) progression after definitive therapy. However, the availability of PSMA PET/CT is limited in both low-resource settings and for repeating imaging surveillance. In contrast, CT is widely available, cost-effective, and routinely performed as part of patient follow-up or radiotherapy workflow. Compared with the molecular activities, the morphological and texture changes of subclinical LNs in CT are subtle, making manual detection of positive LNs infeasible. Instead, we harness the power of artificial intelligence for automated LN detection on CT. We examined 68Ga-PSMA-11 PET/CT images from 88 patients (including 739 PSMA PET/CT-positive pelvic LNs) who experienced a biochemical recurrence after radical prostatectomy and presented for salvage radiotherapy with prostate-specific antigen

GOAL: Identifying population differences can serve as an insightful tool for diagnostic radiology. To do so, a reliable preprocessing framework and data representation are vital. METHODS: We build a machine learning model to visualize gender differences in the circle of Willis (CoW), an integral part of the brains vasculature. We start with a dataset of 570 individuals and process them for analysis using 389 for the final analysis. RESULTS: We find statistical differences between male and female patients in one image plane and visualize where they are. We can see differences between the right and left-hand sides of the brain confirmed using Support Vector Machines (SVM). CONCLUSION: This process can be applied to detect population variations in the vasculature automatically. SIGNIFICANCE: It can guide debugging and inferring complex machine learning algorithms such as SVM and deep learning models.

OBJECTIVE: To identify which patient with prostate cancer (PCa) could safely avoid extended pelvic lymph node dissection (ePLND) by predicting lymph node invasion (LNI), via a radiomics-based machine learning approach. METHODS: An integrative radiomics model (IRM) was proposed to predict LNI, confirmed by the histopathologic examination, integrating radiomics features, extracted from prostatic index lesion regions on MRI images, and clinical features via SVM. The study cohort comprised 244 PCa patients with MRI and followed by radical prostatectomy (RP) and ePLND within 6 months between 2010 and 2019. The proposed IRM was trained in training/validation set and evaluated in an internal independent testing set. The models performance was measured by area under the curve (AUC), sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). AUCs were compared via Delong test with 95% confidence interval (CI), and the rest measurements were compared via chi-squared test or Fishers exact test. RESULTS: Overall, 17 (10.6%) and 14 (16.7%) patients with LNI were included in training/validation set and testing set, respectively. Shape and first-order radiomics features showed usefulness in building the IRM. The proposed IRM achieved an AUC of 0.915 (95% CI: 0.846-0.984) in the testing set, superior to pre-existing nomograms whose AUCs were from 0.698 to 0.724 (p < 0.05). CONCLUSION: The proposed IRM could be potentially feasible to predict the risk of having LNI for patients with PCa. With the improved predictability, it could be utilized to assess which patients with PCa could safely avoid ePLND, thus reduce the number of unnecessary ePLND. KEY POINTS: • The combination of MRI-based radiomics features with clinical information improved the prediction of lymph node invasion, compared with the model using only radiomics features or clinical features. • With improved prediction performance on predicting lymph node invasion, the number of extended pelvic lymph node dissection (ePLND) could be reduced by the proposed integrative radiomics model (IRM), compared with the existing nomograms.

BACKGROUND: Early prehospital stroke identification is crucial for goal directed hospital admission especially in rural areas. However, clinical prehospital stroke scales are designed to identify any stroke but cannot sufficiently differentiate hemorrhagic from ischemic stroke, including large vessel occlusion (LVO) amenable to mechanical thrombectomy. We report on a novel small, portable and battery driven point-of-care ultrasound system (SONAS®) specifically developed for mobile non-invasive brain perfusion ultrasound (BPU) measurement after bolus injection of an echo-enhancing agent suitable for the use in prehospital stroke diagnosis filling a current, unmet and critical need for LVO identification. METHODS: In a phase I study of healthy volunteers we performed comparative perfusion-weighted magnetic resonance imaging (PWI) and BPU measurements, including safety analysis. RESULTS: Twelve volunteers (n = 7 females, n = 5 males, age ranging between 19 and 55 years) tolerated the measurement extremely well including analysis of blood-brain barrier integrity, and the correlation coefficient between the generated time kinetic curves after contrast agent bolus between PWI and BPU transducers ranged between 0.89 and 0.76. CONCLUSIONS: Mobile BPU using the SONAS® device is feasible and safe with results comparable to PWI. When applied in conjunction with prehospital stroke scales this may lead to a more accurate stroke diagnosis and patients bypassing regular stroke units to comprehensive stroke centers. Further studies are needed in acute stroke patients and in the prehospital phase including assessment of immediate and long-term morbidity and mortality in stroke. TRIAL REGISTRATION: Clinical trials.gov, registered 28.Sep.2017, Identifier: NCT03296852.

In stroke care, the extent of irreversible brain injury, termed infarct core, plays a key role in determining eligibility for acute treatments, such as intravenous thrombolysis and endovascular reperfusion therapies. Many of the pivotal randomized clinical trials testing those therapies used MRI Diffusion-Weighted Imaging (DWI) or CT Perfusion (CTP) to define infarct core. Unfortunately, these modalities are not available 24/7 outside of large stroke centers. As such, there is a need for accurate infarct core determination using faster and more widely available imaging modalities including Non-Contrast CT (NCCT) and CT Angiography (CTA). Prior studies have suggested that CTA provides improved predictions of infarct core relative to NCCT; however, this assertion has never been numerically quantified by automatic medical image computing pipelines using acquisition protocols not confounded by different scanner manufacturers, or other protocol settings such as exposure times, kilovoltage peak, or imprecision due to contrast bolus delays. In addition, single-phase CTA protocols are at present designed to optimize contrast opacification in the arterial phase. This approach works well to maximize the sensitivity to detect vessel occlusions, however, it may not be the ideal timing to enhance the ischemic infarct core signal (ICS). In this work, we propose an image analysis pipeline on CT-based images of 88 acute ischemic stroke (AIS) patients drawn from a single dynamic acquisition protocol acquired at the acute ischemic phase. We use the first scan at the time of the dynamic acquisition as a proxy for NCCT, and the rest of the scans as a proxy for CTA scans, with bolus imaged at different brain enhancement phases. Thus, we use the terms NCCT and CTA to refer to them. This pipeline enables us to answer the questions Does the injection of bolus enhance the infarct core signal? and What is the ideal bolus timing to enhance the infarct core signal? without being influenced by aforementioned factors such as scanner model, acquisition settings, contrast bolus delay, and human reader errors. We use reference MRI DWI images acquired after successful recanalization acting as our gold standard for infarct core. The ICS is quantified by calculating the difference in intensity distribution between the infarct core region and its symmetrical healthy counterpart on the contralateral hemisphere of the brain using a metric derived from information theory, the Kullback-Leibler divergence (KL divergence). We compare the ICS provided by NCCT and CTA and retrieve the optimal timing of CTA bolus to maximize the ICS. In our experiments, we numerically confirm that CTAs provide greater ICS compared to NCCT. Then, we find that, on average, the ideal CTA acquisition time to maximize the ICS is not the current target of standard CTA protocols, i.e., during the peak of arterial enhancement, but a few seconds afterward (median of 3 s; 95% CI [1.5, 3.0]). While there are other studies comparing the prediction potential of ischemic infarct core from NCCT and CTA images, to the best of our knowledge, this analysis is the first to perform a quantitative comparison of the ICS among CT based scans, with and without bolus injection, acquired using the same scanning sequence and a precise characterization of the bolus uptake, hence, reducing potential confounding factors.

BackgroundMultiparametric MRI (mpMRI) is commonly recommended as a triage test prior to any prostate biopsy. However, there exists limited consensus on which patients with a negative prostate mpMRI could avoid prostate biopsy.PurposeTo identify which patient could safely avoid prostate biopsy when the prostate mpMRI is negative, via a radiomics-based machine learning approach.Study typeRetrospective.SubjectsThree hundred thirty patients with negative prostate 3T mpMRI between January 2016 and December 2018 were included.Field strength/sequenceA 3.0 T/T2-weighted turbo spin echo (TSE) imaging (T2 WI) and diffusion-weighted imaging (DWI).AssessmentThe integrative machine learning (iML) model was trained to predict negative prostate biopsy results, utilizing both radiomics and clinical features. The final study cohort comprised 330 consecutive patients with negative mpMRI (PI-RADS

Multi-parametric MRI (mpMRI) is a powerful non-invasive tool for diagnosing prostate cancer (PCa) and is widely recommended to be performed before prostate biopsies. Prostate Imaging Reporting and Data System version (PI-RADS) is used to interpret mpMRI. However, when the pre-biopsy mpMRI is negative, PI-RADS 1 or 2, there exists no consensus on which patients should undergo prostate biopsies. Recently, radiomics has shown great abilities in quantitative imaging analysis with outstanding performance on computer-aid diagnosis tasks. We proposed an integrative radiomics-based approach to predict the prostate biopsy results when pre-biopsy mpMRI is negative. Specifically, the proposed approach combined radiomics features and clinical features with machine learning to stratify positive and negative biopsy groups among negative mpMRI patients. We retrospectively reviewed all clinical prostate MRIs and identified 330 negative mpMRI scans, followed by biopsy results. Our proposed model was trained and validated with 10-fold cross-validation and reached the negative predicted value (NPV) of 0.99, the sensitivity of 0.88, and the specificity of 0.63 in receiver operating characteristic (ROC) analysis. Compared with results from existing methods, ours achieved 11.2% higher NPV and 87.2% higher sensitivity with a cost of 23.2% less specificity.

Background: Several deep learning-based techniques have been developed for prostate cancer (PCa) detection using multi-parametric MRI (mpMRI), but few of them have been rigorously evaluated relative to radiologists’ performance or whole-mount histopathology (WMHP).Purpose: To compare the performance of a previously proposed deep learning algorithm, FocalNet, and expert radiologists in the detection of PCa on mpMRI with WMHP as the reference.Study type: Retrospective, single-center study.Subjects: 553 patients (development cohort: 427 patients; evaluation cohort: 126 patients) who underwent 3 T mpMRI prior to radical prostatectomy from October 2010 to February 2018.Field Strength/Sequence: 3 T, T2-weighted imaging and diffusion-weighted imaging.Assessment: FocalNet was trained on the development cohort to predict PCa locations by detection points, with a confidence value for each point, on the evaluation cohort. Four fellowship-trained genitourinary (GU) radiologists independently evaluated the evaluation cohort to detect suspicious PCa foci, annotate detection point locations, and assign a five-point suspicion score (1:least suspicious, 5:most suspicious) for each annotated detection point. The PCa detection performance of FocalNet and radiologists were evaluated by the lesion detection sensitivity versus the number of false-positive detections at different thresholds on suspicion scores. Clinically significant lesions: Gleason Group≥2 or pathological size≥10 mm. Index lesions: the highest Gleason Group and the largest pathological size (secondary).Statistical tests:  Bootstrap hypothesis test for the detection sensitivity between radiologists and FocalNet.Results: For the overall differential detection sensitivity, FocalNet was 5.1% and 4.7% below the radiologists for clinically significant and index lesions, respectively; however, the differences were not statistically significant (P=0.413 and P=0.282, respectively).Data Conclusion: FocalNet achieved slightly lower but not statistically significant PCa detection performance compared to GU radiologists. Compared with radiologists, FocalNet demonstrated similar detection performance for a highly sensitive setting (suspicion score≥1) or a highly specific setting (suspicion score=5) while lower performance in between.

Background and Purpose- Selection of patients with acute ischemic stroke for endovascular treatment generally relies on dynamic susceptibility contrast magnetic resonance imaging or computed tomography perfusion. Dynamic susceptibility contrast magnetic resonance imaging requires injection of contrast, whereas computed tomography perfusion requires high doses of ionizing radiation. The purpose of this work was to develop and evaluate a deep learning (DL)-based algorithm for assisting the selection of suitable patients with acute ischemic stroke for endovascular treatment based on 3-dimensional pseudo-continuous arterial spin labeling (pCASL). Methods- A total of 167 image sets of 3-dimensional pCASL data from 137 patients with acute ischemic stroke scanned on 1.5T and 3.0T Siemens MR systems were included for neural network training. The concurrently acquired dynamic susceptibility contrast magnetic resonance imaging was used to produce labels of hypoperfused brain regions, analyzed using commercial software. The DL and 6 machine learning (ML) algorithms were trained with 10-fold cross-validation. The eligibility for endovascular treatment was determined retrospectively based on the criteria of perfusion/diffusion mismatch in the DEFUSE 3 trial (Endovascular Therapy Following Imaging Evaluation for Ischemic Stroke). The trained DL algorithm was further applied on twelve 3-dimensional pCASL data sets acquired on 1.5T and 3T General Electric MR systems, without fine-tuning of parameters. Results- The DL algorithm can predict the dynamic susceptibility contrast-defined hypoperfusion region in pCASL with a voxel-wise area under the curve of 0.958, while the 6 ML algorithms ranged from 0.897 to 0.933. For retrospective determination for subject-level endovascular treatment eligibility, the DL algorithm achieved an accuracy of 92%, with a sensitivity of 0.89 and specificity of 0.95. When applied to the GE pCASL data, the DL algorithm achieved a voxel-wise area under the curve of 0.94 and a subject-level accuracy of 92% for endovascular treatment eligibility. Conclusions- pCASL perfusion magnetic resonance imaging in conjunction with the DL algorithm provides a promising approach for assisting decision-making for endovascular treatment in patients with acute ischemic stroke.

Cerebral Blood Flow Velocity waveforms acquired via Transcranial Doppler (TCD) can provide evidence for cerebrovascular occlusion and stenosis. Thrombolysis in Brain Ischemia (TIBI) flow grades are widely used for this purpose, but require subjective assessment by expert evaluators to be reliable. In this work we seek to determine whether TCD morphology can be objectively assessed using an unsupervised machine learning approach to waveform categorization. TCD beat waveforms were recorded at multiple depths from the Middle Cerebral Arteries of 106 subjects; 33 with Large Vessel Occlusion (LVO). From each waveform, three morphological features were extracted, quantifying onset of maximal velocity, systolic canopy length, and the number/prominence of peaks/troughs. Spectral clustering identified groups implicit in the resultant three-dimensional feature space, with gap statistic criteria establishing the optimal cluster number. We found that gap statistic disparity was maximized at four clusters, referred to as flow types I, II, III, and IV. Types I and II were primarily composed of control subject waveforms, whereas types III and IV derived mainly from LVO patients. Cluster morphologies for types I and IV aligned clearly with Normal and Blunted TIBI flows, respectively. Types II and III represented commonly observed flow-types not delineated by TIBI, which nonetheless deviate from normal and blunted flows. We conclude that important morphological variability exists beyond that currently quantified by TIBI in populations experiencing or at-risk for acute ischemic stroke, and posit that the observed flow-types provide the foundation for objective methods of real-time automated flow type classification.

Stroke is the fifth leading cause of death in the United States and a major cause of severe disability worldwide. Yet, recognizing the signs of stroke in an acute setting is still challenging and leads to loss of opportunity to intervene, given the narrow therapeutic window. A decision support system using artificial intelligence (AI) and clinical data from electronic health records combined with patients presenting symptoms can be designed to support emergency department providers in stroke diagnosis and subsequently reduce the treatment delay. In this article, we present a practical framework to develop a decision support system using AI by reflecting on the various stages, which could eventually improve patient care and outcome. We also discuss the technical, operational, and ethical challenges of the process.

Data regarding the association between subclinical thyroid dysfunction and clinical outcomes in ischemic stroke patients with intravenous thrombolysis (IVT) are limited. We aimed to investigate the predictive value of subclinical thyroid dysfunction in END, functional outcome and mortality at 3 months among IVT patients. We prospectively recruited 563 IVT patients from 5 stroke centers in China. Thyroid function status was classified as subclinical hypothyroidism, subclinical hyperthyroidism (SHyper) and euthyroidism. The primary outcome was END, defined as ≥ 4 point in the NIHSS score within 24 h after IVT. Secondary outcomes included 3-month functional outcome and mortality. Of the 563 participants, END occurred in 14.7%, poor outcome in 50.8%, and mortality in 9.4%. SHyper was an independent predictor of END [odd ratio (OR), 4.35; 95% confidence interval [CI], 1.86-9.68, P = 0.003], 3-month poor outcome (OR, 3.24; 95% CI, 1.43-7.33, P = 0.005) and mortality [hazard ratio, 2.78; 95% CI, 1.55-5.36, P = 0.003]. Subgroup analysis showed that there was no significant relationship between SHyper and clinical outcomes in IVT patients with endovascular therapy. In summary, SHyper is associated with increased risk of END, and poor outcome and mortality at 3 months in IVT patients without endovascular therapy.

Current clinical practice relies on clinical history to determine the time since stroke (TSS) onset. Imaging-based determination of acute stroke onset time could provide critical information to clinicians in deciding stroke treatment options, such as thrombolysis. The patients with unknown or unwitnessed TSS are usually excluded from thrombolysis, even if their symptoms began within the therapeutic window. In this paper, we demonstrate a machine learning approach for TSS classification using routinely acquired imaging sequences. We develop imaging features from the magnetic resonance (MR) images and train machine learning models to classify the TSS. We also propose a deep-learning model to extract hidden representations for the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional deep features. The cross-validation results show that our best classifier achieved an area under the curve of 0.765, with a sensitivity of 0.788 and a negative predictive value of 0.609, outperforming existing methods. We show that the features generated by our deep-learning algorithm correlate with the MR imaging features, and validate the robustness of the model on imaging parameter variations (e.g., year of imaging). This paper advances magnetic resonance imaging analysis one-step-closer to an operational decision support tool for stroke treatment guidance.

Predicting infarct volume from magnetic resonance perfusion-weighted imaging can provide helpful information to clinicians in deciding how aggressively to treat acute stroke patients. Models have been developed to predict tissue fate, yet these models are mostly built using hand-crafted features (e.g., time-to-maximum) derived from perfusion images, which are sensitive to deconvolution methods. We demonstrate the application of deep convolution neural networks (CNNs) on predicting final stroke infarct volume using only the source perfusion images. We propose a deep CNN architecture that improves feature learning and achieves an area under the curve of 0.871±0.024 , outperforming existing tissue fate models. We further validate the proposed deep CNN with existing 2-D and 3-D deep CNNs for images/video classification, showing the importance of the proposed architecture. Our work leverages deep learning techniques in stroke tissue outcome prediction, advancing magnetic resonance imaging perfusion analysis one step closer to an operational decision support tool for stroke treatment guidance.

BACKGROUND: This study investigated cerebrospinal fluid (CSF) hydrodynamics using cine phase-contrast MRI in the cerebral aqueduct and the prepontine cistern between three distinct groups: pre-shunt normal pressure hydrocephalus (NPH) patients, post-shunt NPH patients, and controls. We hypothesized that the hyperdynamic flow of CSF through the cerebral aqueduct seen in NPH patients was due to a reduction in cisternal CSF volume buffering. Both hydrodynamic (velocity, flow, stroke volume) and peak flow latency (PFL) parameters were investigated. METHODS: Scans were conducted on 30 pre-treatment patients ranging in age from 58 to 88 years along with an additional 12 controls. Twelve patients also received scans following either ventriculoatrial (VA) or ventriculoperitoneal (VP) shunt treatment (9 VP, 3 VA), ranging in age from 74 to 89 years with a mean follow up time of 6 months. RESULTS: Significant differences in area, velocity, flow, and stroke volume for the cerebral aqueduct were found between the pre-treatment NPH group and the healthy controls. Shunting caused a significant decrease in both caudal and cranial mean flow and stroke volume in the cerebral aqueduct. No significant changes were found in the prepontine cistern between the pre-treatment group and healthy controls. For the PFL, no significant differences were seen in the cerebral aqueduct between any of the three groups; however, the prepontine cistern PFL was significantly decreased in the pre-treatment NPH group when compared to the control group. CONCLUSIONS: Although several studies have quantified the changes in aqueductal flow between hydrocephalic groups and controls, few studies have investigated prepontine cistern flow. Our study was the first to investigate both regions in the same patients for NPH pre- and post- treatment. Following shunt treatment, the aqueductal CSF metrics decreased toward control values, while the prepontine cistern metrics trended up (not significantly) from the normal values established in this study. The opposing trend of the two locations suggests a redistribution of CSF pulsatility in NPH patients. Furthermore, the significantly decreased latency of the prepontine cisternal CSF flow suggests additional evidence for CSF pulsatility dysfunction.

The low cost, simple, noninvasive, and continuous measurement of cerebral blood flow velocity (CBFV) by transcranial Doppler is becoming a common clinical tool for the assessment of cerebral hemodynamics. CBFV monitoring can also help with noninvasive estimation of intracranial pressure and evaluation of mild traumatic brain injury. Reliable CBFV waveform analysis depends heavily on its accurate beat-to-beat delineation. However, CBFV is inherently contaminated with various types of noise/artifacts and has a wide range of possible pathological waveform morphologies. Thus, pulse onset detection is in general a challenging task for CBFV signal. In this paper, we conducted a comprehensive comparative analysis of three popular pulse onset detection methods using a large annotated dataset of 92,794 CBFV pulses-collected from 108 subarachnoid hemorrhage patients admitted to UCLA Medical Center. We compared these methods not only in terms of their accuracy and computational complexity, but also for their sensitivity to the selection of their parameters values. The results of this comprehensive study revealed that using optimal values of the parameters obtained from sensitivity analysis, one method can achieve the highest accuracy for CBFV pulse onset detection with true positive rate (TPR) of 97.06% and positive predictivity value (PPV) of 96.48%, when error threshold is set to just less than 10 ms. We conclude that the high accuracy and low computational complexity of this method (average running time of 4ms/pulse) makes it a reliable algorithm for CBFV pulse onset detection.

Transcranial Doppler (TCD) ultrasound has been demonstrated to be a valuable tool for assessing cerebral hemodynamics via measurement of cerebral blood flow velocity (CBFV), with a number of established clinical indications. However, CBFV waveform analysis depends on reliable pulse onset detection, an inherently difficult task for CBFV signals acquired via TCD. We study the application of a new algorithm for CBFV pulse segmentation, which locates pulse onsets in a sequential manner using a moving difference filter and adaptive thresholding. The test data set used in this study consists of 92,012 annotated CBFV pulses, whose quality is representative of real world data. On this test set, the algorithm achieves a true positive rate of 99.998% (2 false negatives), positive predictive value of 99.998% (2 false positives), and mean temporal offset error of 6.10 ± 4.75 ms. We do note that in this context, the way in which true positives, false positives, and false negatives are defined caries some nuance, so care should be taken when drawing comparisons to other algorithms. Additionally, we find that 97.8% and 99.5% of onsets are detected within 10 and 30 ms, respectively, of the true onsets. The algorithms performance in spite of the large degree of variation in signal quality and waveform morphology present in the test data suggests that it may serve as a valuable tool for the accurate and reliable identification of CBFV pulse onsets in neurocritical care settings.

Previous studies have reported that miR-27a-3p is down-regulated in the serum of patients with intracerebral hemorrhage (ICH), but the implication of miR-27a-3p down-regulation in post-ICH complications remains elusive. Here we verified miR-27a-3p levels in the serum of ICH patients by real-time PCR and observed that miR-27a-3p is also significantly reduced in the serum of these patients. We then further investigated the effect of miR-27a-3p on post-ICH complications by intraventricular administration of a miR-27a-3p mimic in rats with collagenase-induced ICH. We found that the hemorrhage markedly reduced miR-27a-3p levels in the hematoma, perihematomal tissue, and serum and that intracerebroventricular administration of the miR-27a-3p mimic alleviated behavioral deficits 24 h after ICH. Moreover, ICH-induced brain edema, vascular leakage, and leukocyte infiltration were also attenuated by this mimic. Of note, miR-27a-3p mimic treatment also inhibited neuronal apoptosis and microglia activation in the perihematomal zone. We further observed that the miR-27a-3p mimic suppressed the up-regulation of aquaporin-11 (AQP11) in the perihematomal area and in rat brain microvascular endothelial cells (BMECs). Moreover, miR-27a-3p down-regulation increased BMEC monolayer permeability and impaired BMEC proliferation and migration. In conclusion, miR-27a-3p down-regulation contributes to brain edema, blood-brain barrier disruption, neuron loss, and neurological deficits following ICH. We conclude that application of exogenous miR-27a-3p may protect against post-ICH complications by targeting AQP11 in the capillary endothelial cells of the brain.

The purpose of this study was to develop and evaluate a scoring system for assessing reperfusion status based on arterial spin labeled (ASL) perfusion MRI in acute ischemic stroke (AIS) patients receiving thrombolysis and/or endovascular treatment. Pseudo-continuous ASL with background suppressed 3D GRASE was acquired along with DWI in 90 patients within 24 h post-treatment. An automatic reperfusion scoring system (auto-RPS) was devised based on the Alberta Stroke Program Early CT Score (ASPECTS) template, and compared with manual RPS and DWI-ASPECTS. TICI (thrombolysis in cerebral infarction) scores were graded in 48 patients who received endovascular treatment. Favorable outcomes were defined by a modified Rankin Scale score of 0-2 at three months. Auto-RPS was positively correlated with DWI-ASPECTS (ρ = 0.6, P

The microvasculature is prominently affected by traumatic brain injury (TBI), including mild TBI (concussion). Assessment of cerebral hemodynamics shows promise as biomarkers of TBI, and may help inform development of therapies aimed at promoting neurologic recovery. The objective of this study was to assess the evolution in cerebral hemodynamics observable with transcranial Doppler (TCD) ultrasound in subjects suffering from a concussion at different intervals during recovery. Pediatric subjects between the ages of 14 and 19 years clinically diagnosed with a concussion were observed at different points post-injury. Blood flow velocity in the middle cerebral artery was measured with TCD. After a baseline period, subjects participated in four breath holding challenges. Pulsatility index (PI), resistivity index (RI), the ratio of the first two pulse peaks (P2R), and the mean velocity (MV) were computed from the baseline section. The breath hold index (BHI) was computed from the challenge sections. TCD detected two phases of hemodynamic changes after concussion. Within the first 48 h, PI, RI, and P2R show a significant difference from the controls (U = -3.10; P

BACKGROUND: The pivotal impact of collateral circulation on outcomes in endovascular therapy has fueled the development of numerous CTA collateral scales, yet synchronized validation with conventional angiography has never occurred. We validated multiphase flat-detector CTA (mpFDCTA) for collateral imaging in patients undergoing endovascular stroke treatment. MATERIALS AND METHODS: Consecutive acute ischemic stroke patient data, including mpFDCTA shortly followed by digital subtraction angiography (DSA), in the setting of acute ICA- or MCA-occlusions were analyzed. An independent core lab scored mpFDCTA with an established collateral scale and separately graded American Society of Interventional and Therapeutic Neuroradiology (ASITN) collateral score on DSA, blind to all other data. RESULTS: 24 consecutive cases (age 76.7 ± 7.3 years; 58.3% women; baseline NIHSS median 17 (4-23)) of acute ICA- or MCA-occlusion were analyzed. Time from mpFDCTA to intracranial DSA was 23.04 ± 7.6 minutes. Median mpFDCTA collateral score was 3 (0-5) and median DSA ASITN collateral score was 2 (0-3), including the full range of potential collateral grades. mpFDCTA and ASITN collateral score were strongly correlated (r = 0.86, p

BACKGROUND AND PURPOSE: Anemia is associated with worse outcome in stroke, but the impact of anemia with intravenous thrombolysis or endovascular therapy has hardly been delineated. The aim of this study was to analyze the role of anemia on infarct evolution and outcome after acute stroke treatment. METHODS: 1158 patients from Bern and 321 from Los Angeles were included. Baseline data and 3 months outcome assessed with the modified Rankin Scale were recorded prospectively. Baseline DWI lesion volumes were measured in 345 patients and both baseline and final infarct volumes in 180 patients using CT or MRI. Multivariable and linear regression analysis were used to determine predictors of outcome and infarct growth. RESULTS: 712 patients underwent endovascular treatment and 446 intravenous thrombolysis. Lower hemoglobin at baseline, at 24h, and nadir until day 5 predicted poor outcome (OR 1.150-1.279) and higher mortality (OR 1.131-1.237) independently of treatment. Decrease of hemoglobin after hospital arrival, mainly induced by hemodilution, predicted poor outcome and had a linear association with final infarct volumes and the amount and velocity of infarct growth. Infarcts of patients with newly observed anemia were twice as large as infarcts with normal hemoglobin levels. CONCLUSION: Anemia at hospital admission and any hemoglobin decrease during acute stroke treatment affect outcome negatively, probably by enlarging and accelerating infarct growth. Our results indicate that hemodilution has an adverse effect on penumbral evolution. Whether hemoglobin decrease in acute stroke could be avoided and whether this would improve outcome would need to be studied prospectively.

Background: Dynamic susceptibility contrast (DSC) MR perfusion is a frequently-used technique for neurovascular imaging. The progress of a bolus of contrast agent through the tissue of the brain is imaged via a series of T2*-weighted MRI scans. Clinically relevant parameters such as blood flow and Tmax can be calculated by deconvolving the contrast-time curves with the bolus shape (arterial input function). In acute stroke, for instance, these parameters may help distinguish between the likely salvageable tissue and irreversibly damaged infarct core. Deconvolution typically relies on singular value decomposition (SVD): however, studies have shown that these algorithms are very sensitive to noise and artifacts present in the image and therefore may introduce distortions that influence the estimated output parameters. Methods: In this work, we present a machine learning approach to the estimation of perfusion parameters in DSC-MRI. Various machine learning models using as input the raw MR source data were trained to reproduce the output of an FDA approved commercial implementation of the SVD deconvolution algorithm. Experiments were conducted to determine the effect of training set size, optimal patch size, and the effect of using different machine-learning models for regression. Results: Model performance increased with training set size, but after 5,000 samples (voxels) this effect was minimal. Models inferring perfusion maps from a 5 by 5 voxel patch outperformed models able to use the information in a single voxel, but larger patches led to worse performance. Random Forest models produced had the lowest root mean squared error, with neural networks performing second best: however, a phantom study revealed that the random forest was highly susceptible to noise levels, while the neural network was more robust. Conclusion: The machine learning-based approach produces estimates of the perfusion parameters invariant to the noise and artifacts that commonly occur as part of MR acquisition. As a result, better robustness to noise is obtained, when evaluated against the FDA approved software on acute stroke patients and simulated phantom data.