Judgment of FLAIR signal change in DWI-FLAIR mismatch determination is a challenge to clinicians

Multi-grained contrastive representation learning for label-efficient lesion segmentation and onset time classification of acute ischemic stroke

Ischemic lesion segmentation and the time since stroke (TSS) onset classification from paired multi-modal MRI imaging of unwitnessed acute ischemic stroke (AIS) patients is crucial, which supports tissue plasminogen activator (tPA) thrombolysis decision-making. Deep learning methods demonstrate superiority in TSS classification. However, they often overfit task-irrelevant features due to insufficient paired labeled data, resulting in poor generalization. We observed that unpaired data are readily available and inherently carry task-relevant cues, but are less often considered and explored. Based on this, in this paper, we propose to fully excavate the potential of unpaired unlabeled data and use them to facilitate the downstream AIS analysis task. We first analyze the utility of features at the varied grain and propose a multi-grained contrastive learning (MGCL) framework to learn task-related prior representations from both coarse-grained and fine-grained levels. The former can learn global prior representations to enhance the location ability for the ischemic lesions and perceive the healthy surroundings, while the latter can learn local prior representations to enhance the perception ability for semantic relation between the ischemic lesion and other health regions. To better transfer and utilize the learned task-related representation, we designed a novel multi-task framework to simultaneously achieve ischemic lesion segmentation and TSS classification with limited labeled data. In addition, a multi-modal region-related feature fusion module is proposed to enable the feature correlation and synergy between multi-modal deep image features for more accurate TSS decision-making. Extensive experiments on the large-scale multi-center MRI dataset demonstrate the superiority of the proposed framework. Therefore, it is promising that it helps better stroke evaluation and treatment decision-making.

Automated Assessment of the DWI-FLAIR Mismatch in Patients with Acute Ischemic Stroke: Added Value to Routine Clinical Practice

BACKGROUND AND PURPOSE

The DWI-FLAIR mismatch is used to determine thrombolytic eligibility in patients with acute ischemic stroke when the time since stroke onset is unknown. Commercial software packages have been developed for automated DWI-FLAIR classification. We aimed to use e-Stroke software for automated classification of the DWI-FLAIR mismatch in a cohort of patients with acute ischemic stroke and in a comparative analysis with 2 expert neuroradiologists.

MATERIALS AND METHODS

In this retrospective study, patients with acute ischemic stroke who had MR imaging and known time since stroke onset were included. The DWI-FLAIR mismatch was evaluated by 2 neuroradiologists blinded to the time since stroke onset and automatically by the e-Stroke software. After 4 weeks, the neuroradiologists re-evaluated the MR images, this time equipped with automated predicted e-Stroke results as a computer-assisted tool. Diagnostic performances of e-Stroke software and the neuroradiologists were evaluated for prediction of DWI-FLAIR mismatch status.

RESULTS

A total of 157 patients met the inclusion criteria. A total of 82 patients (52%) had a time since stroke onset of ≤4.5 hours. By means of consensus reads, 81 patients (51.5%) had a DWI-FLAIR mismatch. The diagnostic accuracy (area under the curve/sensitivity/specificity) of e-Stroke software for the determination of the DWI-FLAIR mismatch was 0.72/90.0/53.9. The diagnostic accuracy (area under the curve/sensitivity/specificity) for neuroradiologists 1 and 2 was 0.76/69.1/84.2 and 0.82/91.4/73.7, respectively; both significantly (P < .05) improved to 0.83/79.0/86.8 and 0.89/92.6/85.5, respectively, following the use of e-Stroke predictions as a computer-assisted tool. The interrater agreement (κ) for determination of DWI-FLAIR status was improved from 0.49 to 0.57 following the use of the computer-assisted tool.

CONCLUSIONS

This automated quantitative approach for DWI-FLAIR mismatch provides results comparable with those of human experts and can improve the diagnostic accuracies of expert neuroradiologists in the determination of DWI-FLAIR status.

MRI of cerebral oedema in ischaemic stroke and its current use in routine clinical practice

Currently, with the knowledge of the role of collateral circulation in the development of cerebral ischaemia, traditional therapeutic windows are being prolonged, with time not being the only criterion. Instead, a more personalised approach is applied to select additional patients who might benefit from active treatment. This review briefly describes the current knowledge of the pathophysiology of the development of early ischaemic changes, the capabilities of MRI to depict such changes, and the basics of the routinely used imaging techniques broadly available for the assessment of individual phases of cerebral ischaemia, and summarises the possible clinical use of routine MR imaging, including patient selection for active treatment and assessment of the outcome on the basis of imaging.

Automatic triaging of acute ischemic stroke patients for reperfusion therapies using Artificial Intelligence methods and multiple MRI features: A review

BACKGROUND

The selection of appropriate treatments for Acute Ischemic Stroke (AIS), including Intravenous (IV) tissue plasminogen activator (tPA) and Mechanical thrombectomy, is a critical aspect of clinical decision-making. Timely treatment is essential, with recommended administration of therapies within 4.5 h of symptom onset. However, patients with unknown Time Since Stroke (TSS), are often excluded from thrombolysis, even if the stroke onset exceeds 6 h. Current clinical guidelines propose using multimodal Magnetic Resonance Imaging (MRI) to assess various mismatches.

METHODS

The review explores the significance of automatic methods based on Artificial Intelligence (AI) algorithms that utilize multiple MRI features to identify patients who are most likely to benefit from acute reperfusion therapies. These AI methods include TSS classification and patient selection for therapies in the late time window (>6 h) using MRI images to provide detailed stroke information.

RESULTS

The review discusses the challenges and limitations in the existing mismatch methods, which may lead to missed opportunities for reperfusion therapy. To address these limitations, AI approaches have been developed to enhance accuracy and support clinical decision-making. These AI methods have shown promising results, outperforming traditional mismatch assessments and providing improved sensitivity and specificity in identifying patients eligible for reperfusion therapies.

DISCUSSION

In summary, the integration of AI algorithms utilizing multiple MRI features has the potential to enhance accuracy, improve patient outcomes, and positively influence the decision-making process in AIS. However, ongoing research and collaboration among clinicians, researchers, and technologists are vital to realize the full potential of AI in optimizing stroke management.

Identifying acute ischemic stroke patients within the thrombolytic treatment window using deep learning

BACKGROUND AND PURPOSE

Treatment of acute ischemic stroke is heavily contingent upon time, as there is a strong relationship between time clock and tissue progression. Work has established imaging biomarker assessments as surrogates for time since stroke (TSS), namely, by comparing signal mismatch between diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) imaging. Our goal was to develop an automatic technique for determining TSS from imaging that does not require subspecialist radiology expertise.

METHODS

Using 772 patients (66 ± 9 years, 319 women), we developed and externally evaluated a deep learning network for classifying TSS from MR images and compared algorithm predictions to neuroradiologist assessments of DWI-FLAIR mismatch. Models were trained to classify TSS within 4.5 hours and performance metrics with confidence intervals were reported on both internal and external evaluation sets.

RESULTS

Three board-certified neuroradiologists' DWI-FLAIR mismatch assessments, based on majority vote, yielded a sensitivity of .62, a specificity of .86, and a Fleiss' kappa of .46 when used to classify TSS. The deep learning method performed similarly to radiologists and outperformed previously reported methods, with the best model achieving an average evaluation accuracy, sensitivity, and specificity of .726, .712, and .741, respectively, on an internal cohort and .724, .757, and .679, respectively, on an external cohort.

CONCLUSION

Our model achieved higher generalization performance on external evaluation datasets than the current state-of-the-art for TSS classification. These results demonstrate the potential of automatic assessment of onset time from imaging without the need for expertly trained radiologists.

MRI radiomic features-based machine learning approach to classify ischemic stroke onset time

PURPOSE

We aimed to investigate the ability of MRI radiomics features-based machine learning (ML) models to classify the time since stroke onset (TSS), which could aid in stroke assessment and treatment options.

METHODS

This study involved 84 patients with acute ischemic stroke due to anterior circulation artery occlusion (51 in the training cohort and 33 in the independent test cohort). Region of infarct segmentation was manually outlined by 3D-slicer software. Image processing including registration, normalization and radiomics features calculation were done in R (version 3.6.1). A total of 4312 radiomic features from each image sequence were captured and used in six ML models to estimate stroke onset time for binary classification (≤ 4.5 h). Receiver-operating characteristic curve (ROC) and other parameters were calculated to evaluate the performance of the models in both training and test cohorts.

RESULTS

Twelve radiomics and six clinic features were selected to construct the ML models for TSS classification. The deep learning model-based DWI/ADC radiomic features performed the best for binary TSS classification in the independent test cohort, with an AUC of 0.754, accuracy of 0.788, sensitivity of 0.952, specificity of 0.500, positive predictive value of 0.769, and negative predictive value of 0.857, respectively. Furthermore, adding clinical information did not improve the performance of the DWI/ADC-based deep learning model. The TSS prediction models can be visited at: http://123.57.65.199:3838/deeptss/ .

CONCLUSIONS

A unique deep learning model based on DWI/ADC radiomic features was constructed for TSS classification, which could aid in decision making for thrombolysis in patients with unknown stroke onset.

A Semi-Supervised Learning Framework to Leverage Proxy Information for Stroke MRI Analysis

Treating acute ischemic stroke (AIS) patients is a time-sensitive endeavor, as therapies target areas experiencing ischemia to prevent irreversible damage to brain tissue. Depending on how an AIS is progressing, thrombolytics such as tissue-plasminogen activator (tPA) may be administered within a short therapeutic window. The underlying conditions for optimal treatment are varied. While previous clinical guidelines only permitted tPA to be administered to patients with a known onset within 4.5 hours, clinical trials demonstrated that patients with signal intensity differences between diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) sequences in an MRI study can benefit from thrombolytic therapy. This intensity difference, known as DWI-FLAIR mismatch, is prone to high inter-reader variability. Thus, a paradigm exists where onset time serves as a weak proxy for DWI-FLAIR mismatch. In this study, we sought to detect DWI-FLAIR mismatch in an automated fashion, and we compared this to assessments done by three expert neuroradiologists. Our approach involved training a deep learning model on MRI to classify tissue clock and leveraging time clock as a weak proxy label to supplement training in a semi-supervised learning (SSL) framework. We evaluate our deep learning model by testing it on an unseen dataset from an external institution. In total, our proposed framework was able to improve detection of DWI-FLAIR mismatch, achieving a top ROC-AUC of 74.30%. Our study illustrated that incorporating clinical proxy information into SSL can improve model optimization by increasing the fidelity of unlabeled samples included in the training process.

A Machine Learning Approach for Classifying Ischemic Stroke Onset Time From Imaging

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.

Comparison of 3- and 20-Gradient Direction Diffusion-Weighted Imaging in a Clinical Subacute Cohort of Patients with Transient Ischemic Attack: Application of Standard Vendor Protocols for Lesion Detection and Final Infarct Size Projection

Objective

Diffusion tensor imaging may aid brain ischemia assessment but is more time consuming than conventional diffusion-weighted imaging (DWI). We compared 3-gradient direction DWI (3DWI) and 20-gradient direction DWI (20DWI) standard vendor protocols in a hospital-based prospective cohort of patients with transient ischemic attack (TIA) for lesion detection, lesion brightness, predictability of persisting infarction, and final infarct size.

Methods

We performed 3T-magnetic resonance imaging including diffusion and T2-fluid attenuated inversion recovery (FLAIR) within 72 h and 8 weeks after ictus. Qualitative lesion brightness was assessed by visual inspection. We measured lesion area and brightness with manual regions of interest and compared with homologous normal tissue.

Results

117 patients with clinical TIA showed 78 DWI lesions. 2 lesions showed only on 3DWI. No lesions were uniquely 20DWI positive. 3DWI was visually brightest for 34 lesions. 12 lesions were brightest on 20DWI. The median 3DWI lesion area was larger for lesions equally bright, or brightest on 20DWI [median (IQR) 39 (18–95) versus 18 (10–34) mm², P = 0.007]. 3DWI showed highest measured relative lesion signal intensity [median (IQR) 0.77 (0.48–1.17) versus 0.58 (0.34–0.81), P = 0.0006]. 3DWI relative lesion signal intensity was not correlated to absolute signal intensity, but 20DWI performed less well for low-contrast lesions. 3DWI lesion size was an independent predictor of persistent infarction. 3-gradient direction apparent diffusion coefficient areas were closest to 8-week FLAIR infarct size.

Conclusion

3DWI detected more lesions and had higher relative lesion SI than 20DWI. 20DWI appeared blurred and did not add information.

Clinical Trial Registration

http://www.clinicaltrials.gov. Unique Identifier NCT01531946.

The Effects of DWI-Infarct Lesion Volume on DWI-FLAIR Mismatch: Is There a Need for Size Stratification?

BACKGROUND

The lack of fluid-attenuated inversion-recovery (FLAIR) hyperintensity in areas of diffusion-weighted imaging (DWI) high signal, or DWI-FLAIR mismatch, is a potential imaging biomarker for timing of stroke onset. We aimed to determine the effects of DWI infarct lesion volume on DWI-FLAIR mismatch and its accuracy for identification of strokes within intravenous (IV) the thrombolytic therapy window.

METHODS

Acute ischemic stroke patients with magnetic resonance imaging scan within 12 hours of witnessed stroke were included. Two neuroradiologists independently reviewed DWI and FLAIR sequences for DWI-FLAIR mismatch in areas of restricted diffusion compared to the contralateral normal side.

RESULTS

DWI-FLAIR mismatch was identified in 21/82 (26%) patients. Infarct lesions with DWI-FLAIR mismatch were scanned earlier (3.8 ± .3 vs. 7.5 ± .3 hours from onset, P < .001) and were smaller in size (8.9±2.3 vs. 43.1±11.9 mL, P = .007) compared to lesions without mismatch. Multivariate regression analysis showed a significant interaction between lesion volume and time-from-onset in relationship with the presence of DWI-FLAIR mismatch (P = .045). The presence of DWI-FLAIR mismatch had 56% sensitivity, 83% specificity, 48% positive predictive value (PPV), and 87% negative predictive value (NPV) for identification of infarction within 4.5 hours of symptom onset; while for infarct lesions >15 mL, the DWI-FLAIR mismatch had 100% specificity and PPV for acute infarcts within 4.5 hours of onset.

CONCLUSION

The effects of stroke onset-to-scan time gap on DWI-FLAIR mismatch are not the same for different DWI lesion volumes. At DWI lesion volumes >15 mL, the DWI-FLAIR mismatch is highly specific for acute infarcts within IV thrombolytic therapy time, and can identify wake-up stroke patients eligible for treatment.

Can MRI quantification help evaluate stroke age?

BACKGROUND

Diffusion-weighted imaging (DWI) fluid-attenuated inversion recovery (FLAIR) mismatch has a proven ability to estimate stroke-to-magnetic resonance imaging (MRI) delay. We evaluated the possibility of enhancing this estimation by quantifying MRI (DWI and FLAIR) signals, and compared this approach to the visual evaluation of DWI-FLAIR mismatch.

MATERIALS AND METHODS

This retrospective study included 194 patients presenting an ischemic stroke in the middle cerebral artery territory that had been explored with 3T MRI within 12h. According to the study design, written informed consent was waived and patient information was anonymized and de-identified prior to analysis. DWI-FLAIR mismatch was visually estimated by two radiologists and a quantification of MRI signals based on a manual segmentation of stroke lesion volume was performed. Using their receiver operating curve and area under the curve (AUC), we identified the variables of MRI quantification that were predictive of stroke-to-MRI delay, then compared their performance against visual classification.

RESULTS

The quantitative variables identified as predictive of stroke-to-MRI delay were: 1st quartile, 3rd quartile and median values of B0; 1st quartile, 3rd quartile, median and relative values of B1000; 1st quartile and relative values of the apparent diffusion coefficient. FLAIR was not found to be predictive. The AUC values of these variables ranged between 0618±0.053 and 0.683±0.048. The relative value of B1000 appeared to be the best predictive quantitative variable, with predictive values comparable to visual classification.

CONCLUSIONS

The quantification of MRI signal may be a helpful tool for stroke dating but cannot outperform the visual estimation of stroke lesion age.

DWI intensity values predict FLAIR lesions in acute ischemic stroke

Background and Purpose

In acute stroke, the DWI-FLAIR mismatch allows for the allocation of patients to the thrombolysis window (<4.5 hours). FLAIR-lesions, however, may be challenging to assess. In comparison, DWI may be a useful bio-marker owing to high lesion contrast. We investigated the performance of a relative DWI signal intensity (rSI) threshold to predict the presence of FLAIR-lesions in acute stroke and analyzed its association with time-from-stroke-onset.

Methods

In a retrospective, dual-center MR-imaging study we included patients with acute stroke and time-from-stroke-onset ≤12 hours (group A: n = 49, 1.5T; group B: n = 48, 3T). DW- and FLAIR-images were coregistered. The largest lesion extent in DWI defined the slice for further analysis. FLAIR-lesions were identified by 3 raters, delineated as regions-of-interest (ROIs) and copied on the DW-images. Circular ROIs were placed within the DWI-lesion and labeled according to the FLAIR-pattern (FLAIR+ or FLAIR−). ROI-values were normalized to the unaffected hemisphere. Adjusted and nonadjusted receiver-operating-characteristics (ROC) curve analysis on patient level was performed to analyze the ability of a DWI- and ADC-rSI threshold to predict the presence of FLAIR-lesions. Spearman correlation and adjusted linear regression analysis was performed to assess the relationship between DWI-intensity and time-from-stroke-onset.

Results

DWI-rSI performed well in predicting lesions in FLAIR-imaging (mean area under the curve (AUC): group A: 0.84; group B: 0.85). An optimal mean DWI-rSI threshold was identified (A: 162%; B: 161%). ADC-maps performed worse (mean AUC: A: 0.58; B: 0.77). Adjusted regression models confirmed the superior performance of DWI-rSI. Correlation coefficents and linear regression showed a good association with time-from-stroke-onset for DWI-rSI, but not for ADC-rSI.

Conclusion

An easily assessable DWI-rSI threshold identifies the presence of lesions in FLAIR-imaging with good accuracy and is associated with time-from-stroke-onset in acute stroke. This finding underlines the potential of a DWI-rSI threshold as a marker of lesion age.

Fluid-attenuated inversion recovery hyperintensity correlates with matrix metalloproteinase-9 level and hemorrhagic transformation in acute ischemic stroke

BACKGROUND AND PURPOSE

Matrix metalloproteinase-9 (MMP-9) is elevated in patients with acute stroke who later develop hemorrhagic transformation (HT). It is controversial whether early fluid-attenuated inversion recovery (FLAIR) hyperintensity on brain MRI predicts hemorrhagic transformation (HT). We assessed whether FLAIR hyperintensity was associated with MMP-9 and HT.

METHODS

We analyzed a prospectively collected cohort of acute stroke subjects with acute brain MRI images and MMP-9 values within the first 12 hours after stroke onset. FLAIR hyperintensity was measured using a signal intensity ratio between the stroke lesion and corresponding normal contralateral hemisphere. MMP-9 was measured using enzyme-linked immunosorbent assay. The relationships between FLAIR ratio (FR), MMP-9, and HT were evaluated.

RESULTS

A total of 180 subjects were available for analysis. Patients were imaged with brain MRI at 5.6±4.3 hours from last seen well time. MMP-9 blood samples were drawn within 7.7±4.0 hours from last seen well time. The time to MRI (r=0.17, P=0.027) and MMP-9 level (r=0.29, P<0.001) were each associated with FR. The association between MMP-9 and FR remained significant after multivariable adjustment (P<0.001). FR was also associated with HT and symptomatic hemorrhage (P=0.012).

CONCLUSIONS

FR correlates with both MMP-9 level and risk of hemorrhage. FLAIR changes in the acute phase of stroke may predict hemorrhagic transformation, possibly as a reflection of altered blood-brain barrier integrity.

Visual and region of interest-based inter-rater agreement in the assessment of the diffusion-weighted imaging- fluid-attenuated inversion recovery mismatch

BACKGROUND AND PURPOSE

WAKE-UP is a randomized, placebo-controlled MRI-based trial of thrombolysis in wake-up stroke using the mismatch between a lesion's visibility in diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR) sequences as its main imaging inclusion criterion. Visual judgment of lesion conspicuity on FLAIR is however methodically limited by moderate inter-rater agreement. We therefore sought to improve rating homogeneity by incorporating quantitative signal intensity measurements.

METHODS

One hundred forty-three data sets of patients with acute ischemic stroke were visually rated by 8 raters with respect to WAKE-UP study inclusion and exclusion criteria, and inter-rater agreement was calculated. A subanalysis was performed on 45 cases to determine a threshold value of relative signal intensity (rSI) between the ischemic lesion and contralateral healthy tissue which best corresponded to a visually established verdict of FLAIR positivity. The usefulness of this threshold in improving inter-rater agreement was evaluated in an additional sample of 50 patients.

RESULTS

Inter-rater agreement for inclusion into the WAKE-UP trial was 73% with a free-marginal κ of 0.46. A threshold of rSI which best correlated with the visual rating of lesions as FLAIR positive was 1.20. The addition of rSI measurements to visual evaluation did not change the inter-rater agreement.

CONCLUSIONS

Introducing a semiquantitative measure for FLAIR rSI did not improve the agreement between individual raters. However, enhancing visual assessment with rSI measurements can provide reassurance to local investigators in cases of uncertainty.

Diffusion-weighted image and fluid-attenuated inversion recovery image mismatch: unclear-onset versus clear-onset stroke

BACKGROUND AND PURPOSE

Mismatch in lesion visibility between diffusion-weighted image and fluid-attenuated inversion recovery image (DWI-FLAIR mismatch) has been proposed as a biomarker for the estimation of ischemic lesion age. The actual onset in some patients with unclear-onset stroke (UnCOS) may be close to the first-found abnormal time. We hypothesized that patients with UnCOS within a particular time window might have a similar DWI-FLAIR mismatch profile with patients with clear-onset stroke (COS).

METHODS

Patients who underwent MRI within 6 hours from first-found abnormal time were recruited retrospectively. Clinical characteristics and the proportion of DWI-FLAIR and perfusion-weighted image-DWI mismatch in each time window were compared between UnCOS and COS.

RESULTS

The final analysis included 259 patients (114 with UnCOS and 145 with COS). Patients with UnCOS were older and had more severe stroke at baseline. Risk factors, stroke subtypes, and perfusion-weighted image-DWI mismatch did not differ between the 2 groups. The proportion of patients with DWI-FLAIR mismatch in UnCOS did not differ from COS within 2 hours of first-found abnormal time (50.0% versus 51.5%; P=0.92), but it was significantly lower in UnCOS than in COS at 2 to 3 hours (16.1% versus 44.4%; P=0.02), 3 to 4 hours (13.8% versus 36.4%; P=0.04), and 4 to 5 hours (5.6% versus 29.6%; P=0.05).

CONCLUSIONS

The proportion of DWI-FLAIR mismatch in UnCOS within the first 2 hours from first-found abnormal time was similar with COS, but it sharply decreased beyond 2 hours. These data suggest that patients with UnCOS within 2 hours of symptom detection may be good candidates for multimodal imaging-based thrombolysis.

Quantitative measurements of relative fluid-attenuated inversion recovery (FLAIR) signal intensities in acute stroke for the prediction of time from symptom onset

In acute stroke magnetic resonance imaging, a 'mismatch' between visibility of an ischemic lesion on diffusion-weighted imaging (DWI) and missing corresponding parenchymal hyperintensities on fluid-attenuated inversion recovery (FLAIR) data sets was shown to identify patients with time from symptom onset ≤4.5 hours with high specificity. However, moderate sensitivity and suboptimal interpreter agreement are limitations of a visual rating of FLAIR lesion visibility. We tested refined image analysis methods in patients included in the previously published PREFLAIR study using refined visual analysis and quantitative measurements of relative FLAIR signal intensity (rSI) from a three-dimensional, segmented stroke lesion volume. A total of 399 patients were included. The rSI of FLAIR lesions showed a moderate correlation with time from symptom onset (r=0.382, P<0.001). A FLAIR rSI threshold of <1.0721 predicted symptom onset ≤4.5 hours with slightly increased specificity (0.85 versus 0.78) but also slightly decreased sensitivity (0.47 versus 0.58) as compared with visual analysis. Refined visual analysis differentiating between 'subtle' and 'obvious' FLAIR hyperintensities and classification and regression tree algorithms combining information from visual and quantitative analysis also did not improve diagnostic accuracy. Our results raise doubts whether the prediction of stroke onset time by visual image judgment can be improved by quantitative rSI measurements.