Quantitative prediction of acute ischemic tissue fate using support vector machine

Emerging role of artificial intelligence in stroke imaging

Introduction: The recognition and therapy of patients with stroke is becoming progressively intricate as additional treatment choices become accessible and new associations between disease characteristics and treatment response are incessantly uncovered. Therefore, clinicians must regularly learn new skill, stay up to date with the literature and integrate advances into daily practice. The application of artificial intelligence (AI) to assist clinical decision making could diminish inter-rater variation in routine clinical practice and accelerate the mining of vital data that could expand recognition of patients with stroke, forecast of treatment responses and patient outcomes.Areas covered: In this review, the authors provide an up-to-date review of AI in stroke, analyzing the latest papers on this subject. These have been divided in two main groups: stroke diagnosis and outcome prediction.Expert opinion: The highest value of AI is its capability to merge, select and condense a large amount of clinical and imaging features of a single patient and to associate these with fitted models that have gone through robust assessment and optimization with large cohorts of data to support clinical decision making.

Artificial Intelligence shaping the future of neurology practice

Neurology practice has faced many challenges since Jean-Martin Charcot established its sacred tenets. Artificial Intelligence (AI) promises to revolutionize the time-tested neurology practice in unimaginable ways. AI can now diagnose stroke from CT/MRI scans, detect papilledema and diabetic retinopathy from retinal scans, interpret electroencephalogram (EEG) to prognosticate coma, detect seizure well before ictus, predict conversion of mild cognitive impairment to Alzheimer's dementia, classify neurodegenerative diseases based on gait and handwriting. Clinical practice would likely change in near future to accommodate AI as a complementary tool. The clinician should be prepared to change the perception of AI from nemesis to opportunity.

Interventional Radiology ex-machina: impact of Artificial Intelligence on practice

Artificial intelligence (AI) is a branch of Informatics that uses algorithms to tirelessly process data, understand its meaning and provide the desired outcome, continuously redefining its logic. AI was mainly introduced via artificial neural networks, developed in the early 1950s, and with its evolution into "computational learning models." Machine Learning analyzes and extracts features in larger data after exposure to examples; Deep Learning uses neural networks in order to extract meaningful patterns from imaging data, even deciphering that which would otherwise be beyond human perception. Thus, AI has the potential to revolutionize the healthcare systems and clinical practice of doctors all over the world. This is especially true for radiologists, who are integral to diagnostic medicine, helping to customize treatments and triage resources with maximum effectiveness. Related in spirit to Artificial intelligence are Augmented Reality, mixed reality, or Virtual Reality, which are able to enhance accuracy of minimally invasive treatments in image guided therapies by Interventional Radiologists. The potential applications of AI in IR go beyond computer vision and diagnosis, to include screening and modeling of patient selection, predictive tools for treatment planning and navigation, and training tools. Although no new technology is widely embraced, AI may provide opportunities to enhance radiology service and improve patient care, if studied, validated, and applied appropriately.

Machine learning identifies stroke features between species

Identification and localization of ischemic stroke (IS) lesions is routinely performed to confirm diagnosis, assess stroke severity, predict disability and plan rehabilitation strategies using magnetic resonance imaging (MRI). In basic research, stroke lesion segmentation is necessary to study complex peri-infarction tissue changes. Moreover, final stroke volume is a critical outcome evaluated in clinical and preclinical experiments to determine therapy or intervention success. Manual segmentations are performed but they require a specialized skill set, are prone to inter-observer variation, are not entirely objective and are often not supported by histology. The task is even more challenging when dealing with large multi-center datasets, multiple experimenters or large animal cohorts. On the other hand, current automatized segmentation approaches often lack histological validation, are not entirely user independent, are often based on single parameters, or in the case of complex machine learning methods, require vast training datasets and are prone to a lack of model interpretation.

Methods: We induced IS using the middle cerebral artery occlusion model on two rat cohorts. We acquired apparent diffusion coefficient (ADC) and T2-weighted (T2W) images at 24 h and 1-week after IS induction. Subsets of the animals at 24 h and 1-week post IS were evaluated using histology and immunohistochemistry. Using a Gaussian mixture model, we segmented voxel-wise interactions between ADC and T2W parameters at 24 h using one of the rat cohorts. We then used these segmentation results to train a random forest classifier, which we applied to the second rat cohort. The algorithms' stroke segmentations were compared to manual stroke delineations, T2W and ADC thresholding methods and the final stroke segmentation at 1-week. Volume correlations to histology were also performed for every segmentation method. Metrics of success were calculated with respect to the final stroke volume. Finally, the trained random forest classifier was tested on a human dataset with a similar temporal stroke on-set. Manual segmentations, ADC and T2W thresholds were again used to evaluate and perform comparisons with the proposed algorithms' output.

Results: In preclinical rat data our framework significantly outperformed commonly applied automatized thresholding approaches and segmented stroke regions similarly to manual delineation. The framework predicted the localization of final stroke regions in 1-week post-stroke MRI with a median Dice similarity coefficient of 0.86, Matthew's correlation coefficient of 0.80 and false positive rate of 0.04. The predicted stroke volumes also strongly correlated with final histological stroke regions (Pearson correlation = 0.88, P < 0.0001). Lastly, the stroke region characteristics identified by our framework in rats also identified stroke lesions in human brains, largely outperforming thresholding approaches in stroke volume prediction (P<0.01).

Conclusion: Our findings reveal that the segmentation produced by our proposed framework using 24 h MRI rat data strongly correlated with the final stroke volume, denoting a predictive effect. In addition, we show for the first time that the stroke imaging features can be directly translated between species, allowing identification of acute stroke in humans using the model trained on animal data. This discovery reduces the gap between the clinical and preclinical fields, unveiling a novel approach to directly co-analyze clinical and preclinical data. Such methods can provide further biological insights into human stroke and highlight the differences between species in order to help improve the experimental setups and animal models of the disease.

Artificial intelligence in stroke imaging: Current and future perspectives

Artificial intelligence (AI) is a fast-growing research area in computer science that aims to mimic cognitive processes through a number of techniques. Supervised machine learning, a subfield of AI, includes methods that can identify patterns in high-dimensional data using labeled 'ground truth' data and apply these learnt patterns to analyze, interpret, or make predictions on new datasets. Supervised machine learning has become a significant area of interest within the medical community. Radiology and neuroradiology in particular are especially well suited for application of machine learning due to the vast amount of data that is generated. One devastating disease for which neuroimaging plays a significant role in the clinical management is stroke. Within this context, AI techniques can play pivotal roles for image-based diagnosis and management of stroke. This overview focuses on the recent advances of artificial intelligence methods - particularly supervised machine learning and deep learning - with respect to workflow, image acquisition and reconstruction, and image interpretation in patients with acute stroke, while also discussing potential pitfalls and future applications.

Machine learning-based segmentation of ischemic penumbra by using diffusion tensor metrics in a rat model

Background

Recent trials have shown promise in intra-arterial thrombectomy after the first 6–24 h of stroke onset. Quick and precise identification of the salvageable tissue is essential for successful stroke management. In this study, we examined the feasibility of machine learning (ML) approaches for differentiating the ischemic penumbra (IP) from the infarct core (IC) by using diffusion tensor imaging (DTI)-derived metrics.

Methods

Fourteen male rats subjected to permanent middle cerebral artery occlusion (pMCAO) were included in this study. Using a 7 T magnetic resonance imaging, DTI metrics such as fractional anisotropy, pure anisotropy, diffusion magnitude, mean diffusivity (MD), axial diffusivity, and radial diffusivity were derived. The MD and relative cerebral blood flow maps were coregistered to define the IP and IC at 0.5 h after pMCAO. A 2-level classifier was proposed based on DTI-derived metrics to classify stroke hemispheres into the IP, IC, and normal tissue (NT). The classification performance was evaluated using leave-one-out cross validation.

Results

The IC and non-IC can be accurately segmented by the proposed 2-level classifier with an area under the receiver operating characteristic curve (AUC) between 0.99 and 1.00, and with accuracies between 96.3 and 96.7%. For the training dataset, the non-IC can be further classified into the IP and NT with an AUC between 0.96 and 0.98, and with accuracies between 95.0 and 95.9%. For the testing dataset, the classification accuracy for IC and non-IC was 96.0 ± 2.3% whereas for IP and NT, it was 80.1 ± 8.0%. Overall, we achieved the accuracy of 88.1 ± 6.7% for classifying three tissue subtypes (IP, IC, and NT) in the stroke hemisphere and the estimated lesion volumes were not significantly different from those of the ground truth (p = .56, .94, and .78, respectively).

Conclusions

Our method achieved comparable results to the conventional approach using perfusion–diffusion mismatch. We suggest that a single DTI sequence along with ML algorithms is capable of dichotomizing ischemic tissue into the IC and IP.

Comparison of classification methods for tissue outcome after ischaemic stroke

In acute ischaemic stroke, identifying brain tissue at high risk of infarction is important for clinical decision-making. This tissue may be identified with suitable classification methods from magnetic resonance imaging data. The aim of the present study was to assess and compare the performance of five popular classification methods (adaptive boosting, logistic regression, artificial neural networks, random forest and support vector machine) in identifying tissue at high risk of infarction on human voxel-based brain imaging data. The classification methods were used with eight MRI parameters, including diffusion-weighted imaging and perfusion-weighted imaging obtained in 55 patients. The five criteria used to assess the performance of the methods were the area under the receiver operating curve (AUC_roc ), the area under the precision-recall curve (AUC_pr ), sensitivity, specificity and the Dice coefficient. The methods performed equally in terms of sensitivity and specificity, while the results of AUC_roc and the Dice coefficient were significantly better for adaptive boosting, logistic regression, artificial neural networks and random forest. However, there was no statistically significant difference between the performances of these five classification methods regarding AUC_pr , which was the main comparison metric. Machine learning methods can provide valuable prognostic information using multimodal imaging data in acute ischaemic stroke, which in turn can assist in developing personalized treatment decision for clinicians after a thorough validation of methods with an independent data set.

Individualized quantification of the benefit from reperfusion therapy using stroke predictive models

PURPOSE

Recent imaging developments have shown the potential of voxel-based models in assessing infarct growth after stroke. Many models have been proposed but their relevance in predicting the benefit of a reperfusion therapy remains unclear. We searched for a predictive model whose volumetric predictions would identify stroke patients who are to benefit from tissue plasminogen activator (t-PA)-induced reperfusion.

MATERIAL AND METHODS

Forty-five cases were used to study retrospectively stroke progression from admission to end of follow-up. Predictive approaches based on various statistical models, predictive variables and spatial filtering methods were compared. The optimal approach was chosen according to the area under the precision-recall curve (AUPRC). The final lesion volume was then predicted assuming that the patient would or would not reperfuse. Patients, with an acute lesion of ≤50 ml and a predicted reduction in the presence of reperfusion >6 ml and >25% of the acute lesion, were classified as responders.

RESULTS

The optimal model was a logistic regression using the voxel distance to the acute lesion, the volume of the acute lesion and Gaussian-filtered MRI contrast parameters as predictive variables. The predictions gave a median AUPRC of 0.655, a median AUC of 0.976 and a median volumetric error of 8.29 ml. Nineteen patients matched the responder profile. A non-significant trend of improved reduction in NIHSS score (-42.8%, p = .09) and in lesion volume (-78.1%, p = 0.21) following reperfusion was observed for responder patients.

CONCLUSION

Despite limited volumetric accuracy, predictive stroke models can be used to quantify the benefit of reperfusion therapies.

Machine Learning in Acute Ischemic Stroke Neuroimaging

Machine Learning (ML) through pattern recognition algorithms is currently becoming an essential aid for the diagnosis, treatment, and prediction of complications and patient outcomes in a number of neurological diseases. The evaluation and treatment of Acute Ischemic Stroke (AIS) have experienced a significant advancement over the past few years, increasingly requiring the use of neuroimaging for decision-making. In this review, we offer an insight into the recent developments and applications of ML in neuroimaging focusing on acute ischemic stroke.

Automated Infarct Core Volumetry Within the Hypoperfused Tissue: Technical Implementation and Evaluation

OBJECTIVE

The aim of this study was to develop a rapid and fully automatic infarct core and tissue at risk volumetry approach in acute ischemic stroke.

METHODS

We evaluated an algorithm in which segmentation was restricted to 1 hemisphere and the potential lesion characterized on the basis of the perfusion parameter Tmax with a region-wise comparison of local histograms to its mirrored counterpart.

RESULTS

We applied the "Tmax inside" method to 30 cases of a public data set with ground-truth segmentations for diffusion-weighted and perfusion magnetic resonance imaging. Lesions were robustly identified with significantly higher dice coefficients (apparent diffusion coefficient, 0.83 ± 0.22; Tmax, 0.80 ± 0.05, compared with 0.53 ± 0.27 and 0.56 ± 0.18) than for a global thresholding approach.

CONCLUSIONS

The proposed "Tmax inside" method is superior to the commonly used global thresholding approach. Furthermore, the method allows evaluating changes in cerebral blood volume and blood flow by taking the counterpart in the healthy hemisphere as a patient-individual reference.

Prediction of hemorrhagic transformation after experimental ischemic stroke using MRI-based algorithms

Estimation of hemorrhagic transformation (HT) risk is crucial for treatment decision-making after acute ischemic stroke. We aimed to determine the accuracy of multiparametric MRI-based predictive algorithms in calculating probability of HT after stroke. Spontaneously, hypertensive rats were subjected to embolic stroke and, after 3 h treated with tissue plasminogen activator (Group I: n = 6) or vehicle (Group II: n = 7). Brain MRI measurements of T₂, T₂*, diffusion, perfusion, and blood-brain barrier permeability were obtained at 2, 24, and 168 h post-stroke. Generalized linear model and random forest (RF) predictive algorithms were developed to calculate the probability of HT and infarction from acute MRI data. Validation against seven-day outcome on MRI and histology revealed that highest accuracy of hemorrhage prediction was achieved with a RF-based model that included spatial brain features (Group I: area under the receiver-operating characteristic curve (AUC) = 0.85 ± 0.14; Group II: AUC = 0.89 ± 0.09), with significant improvement over perfusion- or permeability-based thresholding methods. However, overlap between predicted and actual tissue outcome was significantly lower for hemorrhage prediction models (maximum Dice's Similarity Index (DSI) = 0.20 ± 0.06) than for infarct prediction models (maximum DSI = 0.81 ± 0.06). Multiparametric MRI-based predictive algorithms enable early identification of post-ischemic tissue at risk of HT and may contribute to improved treatment decision-making after acute ischemic stroke.

Magnetic Resonance Imaging of Cerebral Blood Flow in Animal Stroke Models

Perfusion could provide useful information on the metabolic status and functional status of tissues and organs. This review summarizes the most commonly used perfusion measurement methods: Dynamic susceptibility contrast (DSC) and arterial spin labeling (ASL) and their applications in experimental stroke. Some new developments of cerebral blood flow (CBF) techniques in animal models are also discussed.

Infarct Volume Prediction by Early Magnetic Resonance Imaging in a Murine Stroke Model Depends on Ischemia Duration and Time of Imaging

BACKGROUND AND PURPOSE

Despite standardization of experimental stroke models, final infarct sizes after middle cerebral artery occlusion (MCAO) vary considerably. This introduces uncertainties in the evaluation of drug effects on stroke. Magnetic resonance imaging may detect variability of surgically induced ischemia before treatment and thus improve treatment effect evaluation.

METHODS

MCAO of 45 and 90 minutes induced brain infarcts in 83 mice. During, and 3 and 6 hours after MCAO, we performed multiparametric magnetic resonance imaging. We evaluated time courses of cerebral blood flow, apparent diffusion coefficient (ADC), T1, T2, accuracy of infarct prediction strategies, and impact on statistical evaluation of experimental stroke studies.

RESULTS

ADC decreased during MCAO but recovered completely on reperfusion after 45 and partially after 90-minute MCAO, followed by a secondary decline. ADC lesion volumes during MCAO or at 6 hours after MCAO largely determined final infarct volumes for 90 but not for 45 minutes MCAO. The majority of chance findings of final infarct volume differences in random group allocations of animals were associated with significant differences in early ADC lesion volumes for 90, but not for 45-minute MCAO.

CONCLUSIONS

The prediction accuracy of early magnetic resonance imaging for infarct volumes depends on timing of magnetic resonance imaging and MCAO duration. Variability of the posterior communicating artery in C57Bl6 mice contributes to differences in prediction accuracy between short and long MCAO. Early ADC imaging may be used to reduce errors in the interpretation of post MCAO treatment effects on stroke volumes.

Infarct volume prediction using apparent diffusion coefficient maps during middle cerebral artery occlusion and soon after reperfusion in the rat

Middle cerebral artery occlusion (MCAO) in rodents causes brain infarctions of variable sizes that depend on multiple factors, particularly in models of ischemia/reperfusion. This is a major problem for infarct volume comparisons between different experimental groups since unavoidable variability can induce biases in the results and imposes the use of large number of subjects. MRI can help to minimize these difficulties by ensuring that the severity of ischemia is comparable between groups. Furthermore, several studies showed that infarct volumes can be predicted with MRI data obtained soon after ischemia onset. However, such predictive studies require multiparametric MRI acquisitions that cannot be routinely performed, and data processing using complex algorithms that are often not available. The aim here was to provide a simplified method for infarct volume prediction using apparent diffusion coefficient (ADC) data in a model of transient MCAO in rats. ADC images were obtained before, during MCAO and after 60 min of reperfusion. Probability histograms were generated using ADC data obtained either during MCAO, after reperfusion, or both combined. The results were compared to real infarct volumes, i.e.T2 maps obtained at day 7. Assessment of the performance of the estimations showed better results combining ADC data obtained during occlusion and at reperfusion. Therefore, ADC data alone can provide sufficient information for a reasonable prediction of infarct volume if the MRI information is obtained both during the occlusion and soon after reperfusion. This approach can be used to check whether drug administration after MRI acquisition can change infarct volume prediction.

Usefulness of the heart-rate variability complex for predicting cardiac mortality after acute myocardial infarction

Background

Previous studies indicate that decreased heart-rate variability (HRV) is related to the risk of death in patients after acute myocardial infarction (AMI). However, the conventional indices of HRV have poor predictive value for mortality. Our aim was to develop novel predictive models based on support vector machine (SVM) to study the integrated features of HRV for improving risk stratification after AMI.

Methods

A series of heart-rate dynamic parameters from 208 patients were analyzed after a mean follow-up time of 28 months. Patient electrocardiographic data were classified as either survivals or cardiac deaths. SVM models were established based on different combinations of heart-rate dynamic variables and compared to left ventricular ejection fraction (LVEF), standard deviation of normal-to-normal intervals (SDNN) and deceleration capacity (DC) of heart rate. We tested the accuracy of predictors by assessing the area under the receiver-operator characteristics curve (AUC).

Results

We evaluated a SVM algorithm that integrated various electrocardiographic features based on three models: (A) HRV complex; (B) 6 dimension vector; and (C) 8 dimension vector. Mean AUC of HRV complex was 0.8902, 0.8880 for 6 dimension vector and 0.8579 for 8 dimension vector, compared with 0.7424 for LVEF, 0.7932 for SDNN and 0.7399 for DC.

Conclusions

HRV complex yielded the largest AUC and is the best classifier for predicting cardiac death after AMI.

A review of current imaging methods used in stroke research

Stroke is a serious healthcare problem with high mortality and long-term disability. However, to date, our ability to prevent and cure stroke remains limited. One important goal in stroke research is to identify the extent and location of lesion for treatment. In addition, accurately differentiating salvageable tissue from infarct and evaluating therapeutic efficacies are indispensible. These objectives could potentially be met with the assistance of modern neuroimaging techniques. This paper reviews current imaging methods commonly used in ischemic stroke research. These methods include positron emission tomography, computed tomography, T1 MRI, T2 MRI, diffusion and perfusion MRI, diffusion tensor imaging, blood-brain barrier permeability MRI, pH-weighted MRI, and functional MRI.

Early identification of potentially salvageable tissue with MRI-based predictive algorithms after experimental ischemic stroke

Individualized stroke treatment decisions can be improved by accurate identification of the extent of salvageable tissue. Magnetic resonance imaging (MRI)-based approaches, including measurement of a 'perfusion-diffusion mismatch' and calculation of infarction probability, allow assessment of tissue-at-risk; however, the ability to explicitly depict potentially salvageable tissue remains uncertain. In this study, five predictive algorithms (generalized linear model (GLM), generalized additive model, support vector machine, adaptive boosting, and random forest) were tested in their potency to depict acute cerebral ischemic tissue that can recover after reperfusion. Acute T2-, diffusion-, and perfusion-weighted MRI, and follow-up T2 maps were collected from rats subjected to right-sided middle cerebral artery occlusion without subsequent reperfusion, for training of algorithms (Group I), and with spontaneous (Group II) or thrombolysis-induced reperfusion (Group III), to determine infarction probability-based viability thresholds and prediction accuracies. The infarction probability difference between irreversible-i.e., infarcted after reperfusion-and salvageable tissue injury-i.e., noninfarcted after reperfusion-was largest for GLM (20±7%) with highest accuracy of risk-based identification of acutely ischemic tissue that could recover on subsequent reperfusion (Dice's similarity index=0.79±0.14). Our study shows that assessment of the heterogeneity of infarction probability with MRI-based algorithms enables estimation of the extent of potentially salvageable tissue after acute ischemic stroke.

Stroke neuroprotection: targeting mitochondria

Stroke is the fourth leading cause of death and the leading cause of long-term disability in the United States. Blood flow deficit results in an expanding infarct core with a time-sensitive peri-infarct penumbra that is considered salvageable and is the primary target for treatment strategies. The only current FDA-approved drug for treating ischemic stroke is recombinant tissue plasminogen activator (rt-PA). However, this treatment is limited to within 4.5 h of stroke onset in a small subset of patients. The goal of this review is to focus on mitochondrial-dependent therapeutic agents that could provide neuroprotection following stroke. Dysfunctional mitochondria are linked to neurodegeneration in many disease processes including stroke. The mechanisms reviewed include: (1) increasing ATP production by purinergic receptor stimulation, (2) decreasing the production of ROS by superoxide dismutase, or (3) increasing antioxidant defenses by methylene blue, and their benefits in providing neuroprotection following a stroke.

Magnetic resonance imaging of perfusion-diffusion mismatch in rodent and non-human primate stroke models

Stroke is a leading cause of death and long-term disability. Non-invasive magnetic resonance imaging (MRI) has been widely used for the early detection of ischemic stroke and the longitudinal monitoring of novel treatment strategies. Recent advances in MRI techniques have enabled improved sensitivity and specificity to detecting ischemic brain injury and monitoring functional recovery. This review describes recent progresses in the development and application of multimodal MRI and image analysis techniques to study experimental stroke in rats and non-human primates.

Incorporating ADC temporal profiles to predict ischemic tissue fate in acute stroke

Algorithms to predict ischemic tissue fate based on acute stroke MRI typically utilized data at a single time point. The goal of this study was to investigate the potential improvement in prediction accuracy when incorporating MRI diffusion data from multiple time points during acute phase to improve prediction accuracy. This study was carried out using MRI data from rats subjected to permanent, 60-min and 30-min of middle cerebral artery occlusion (MCAO). The sensitivity and specificity of prediction accuracy were calculated. In the permanent MCAO group, prediction with multiple time-point diffusion data improved sensitivity and specificity compared with prediction using a single time point. In the 60-min MCAO group, multiple time-point analysis improved specificity but decreased sensitivity compared to the single time-point analysis. In the 30-min MCAO group, multiple time-point analysis showed no statistically significant improvement in specificity and sensitivity compared with the single time point analysis. This is because reperfusion transiently or permanently reversed the decline in ADC values, resulting in increased uncertainty and thus decreased prediction accuracy. Incorporating this a priori information could further improve prediction accuracy in the reperfusion group. These findings suggest that incorporating MRI data from multiple time points could improve prediction accuracy under certain ischemic conditions.

Multimodal MRI of experimental stroke

Stroke is the fourth leading cause of death and the leading cause of long-term disability in USA. Brain imaging data from experimental stroke models and stroke patients have shown that there is often a gradual progression of potentially reversible ischemic injury toward infarction. Reestablishing tissue perfusion and/or treating with neuroprotective drugs in a timely fashion are expected to salvage some ischemic tissues. Diffusion-weighted imaging based on magnetic resonance imaging (MRI) in which contrast is based on water motion can detect ischemic injury within minutes after onsets, whereas computed tomography and other imaging modalities fail to detect stroke injury for at least a few hours. Along with quantitative perfusion imaging, the perfusion-diffusion mismatch which approximates the ischemic penumbra could be imaged noninvasively. This review describes recent progresses in the development and application of multimodal MRI and image analysis techniques to study ischemic tissue at risk in experimental stroke in rats.

Probing ischemic tissue fate with BOLD fMRI of brief oxygen challenge

It has been recently shown that at-risk tissue exhibits exaggerated T(2)⁎-weighted MRI signal increases during transient oxygen challenge (OC), suggesting that the tissue is still metabolically active. This study further characterized the effects of transient OC on T(2)⁎-weighted MRI in permanent focal stroke rats (N=8) using additional quantitative measures. The major findings were: i) the ischemic core cluster showed no significant response, whereas the mismatch cluster showed markedly higher percent changes relative to normal tissue in the acute phase. ii) Many of the mismatch pixels showed exaggerated OC responses which became hyperintense on T(2)-weighted MRI at 24h. The area with exaggerated OC responses was larger than the mismatch, suggesting that some tissue with reduced diffusion were potentially at risk. iii) Basal T(2)⁎-weighted intensities on the perfusion-diffusion contourplot were high in normal tissue and low in the core, with a sharp transition in the mismatch. iv) OC-induced changes on the perfusion-diffusion contourplot dropped as perfusion and diffusion values fell below their respective viability thresholds. v) Basal T(1) increased slightly in the ischemic core (P<0.05). OC decreased T(1) in normal (P<0.05) but not in mismatch and core pixels. vi) OC decreased CBF in normal (P<0.05) but not in mismatch and core pixels. T(2)⁎-weighted MRI of OC has the potential to offer unique clinically relevant data.