Acute Stroke Imaging Part II: The Ischemic Penumbra

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.

Predictive value of whole-brain CT perfusion combined with ABCD3 score for short-term secondary cerebral infarction after TIA

Objective

To investigate the predictive value of Whole Brain CT Perfusion (WB-CTP) combined with the ABCD3 score in patients with transient ischemic attack (TIA).

Methods

A total of 336 TIA patients with TIA underwent WB-CTP and ABCD3 score assessment within 48 h of admission. Spearman correlation test was performed to analyze the relationship between the degree of vascular stenosis, relative perfusion values, and ABCD3 score. Logistic regression analysis was used to identify independent risk factors for secondary cerebral infarction. Receiver operating characteristic (ROC) curves were generated to evaluate the predictive value of relative cerebral blood flow (rCBF), degree of vascular stenosis, ABCD3 score, and the WB-CTP-ABCD3 combined model for secondary cerebral infarction after TIA. Calibration curves and H-L tests were used to evaluate the predictive efficacy of the model.

Results

Among the 336 TIA patients, 143 showed abnormal perfusion areas and 146 had responsible vessel stenosis. The degree of vascular stenosis, relative time-to-maximum (rTmax), and relative mean transit time (rMTT) were positively correlated with the ABCD3 score, while rCBF and relative cerebral blood volume (rCBV) were negatively correlated with the ABCD3 score. ROC curve analysis identified a cutoff value of 0.8205 for rCBF, with a sensitivity of 84.10% and specificity of 58.10% for distinguishing the cerebral infarction group from the non-cerebral infarction group. Furthermore, rCBF ≤ 0.8205, degree of vascular stenosis, and ABCD3 score > 6 were identified as independent risk factors for secondary cerebral infarction in TIA patients within 90 days in TIA patients. The AUC of the WB-CTP-ABCD3 combined model for predicting secondary cerebral infarction within 90 days was 0.836. The model risk was assessed by plotting calibration curves. The value of p for the H-L goodness of fit test was 0.366 (p > 0.05), which indicated that the difference between the obtained model and the perfect model were statistically insignificant.

Conclusion

The combined model of WB-CTP-ABCD3 shows promise as a valuable method for predicting secondary cerebral infarction within 90 days following TIA.

Combining unsupervised and supervised learning for predicting the final stroke lesion

Predicting the final ischaemic stroke lesion provides crucial information regarding the volume of salvageable hypoperfused tissue, which helps physicians in the difficult decision-making process of treatment planning and intervention. Treatment selection is influenced by clinical diagnosis, which requires delineating the stroke lesion, as well as characterising cerebral blood flow dynamics using neuroimaging acquisitions. Nonetheless, predicting the final stroke lesion is an intricate task, due to the variability in lesion size, shape, location and the underlying cerebral haemodynamic processes that occur after the ischaemic stroke takes place. Moreover, since elapsed time between stroke and treatment is related to the loss of brain tissue, assessing and predicting the final stroke lesion needs to be performed in a short period of time, which makes the task even more complex. Therefore, there is a need for automatic methods that predict the final stroke lesion and support physicians in the treatment decision process. We propose a fully automatic deep learning method based on unsupervised and supervised learning to predict the final stroke lesion after 90 days. Our aim is to predict the final stroke lesion location and extent, taking into account the underlying cerebral blood flow dynamics that can influence the prediction. To achieve this, we propose a two-branch Restricted Boltzmann Machine, which provides specialized data-driven features from different sets of standard parametric Magnetic Resonance Imaging maps. These data-driven feature maps are then combined with the parametric Magnetic Resonance Imaging maps, and fed to a Convolutional and Recurrent Neural Network architecture. We evaluated our proposal on the publicly available ISLES 2017 testing dataset, reaching a Dice score of 0.38, Hausdorff Distance of 29.21 mm, and Average Symmetric Surface Distance of 5.52 mm.

Multimodal CT in Acute Stroke

PURPOSE OF REVIEW

Multimodal CT imaging (non-contrast CT, NCCT; CT angiography, CTA; and CT Perfusion, CTP) is central to acute ischemic stroke diagnosis and treatment. We reviewed the purpose and interpretation of each component of multimodal CT, as well as the evidence for use in routine care.

RECENT FINDINGS

Acute stroke thrombolysis can be administered immediately following NCCT in acute ischemic stroke patients assessed within 4.5 h of symptom onset. Definitive identification of a large vessel occlusion (LVO) requires vascular imaging, which is easily achieved with CTA. This is critical, as the standard of care for LVO within 6 h of onset is now endovascular thrombectomy (EVT). CTA source images can also be used to estimate the efficacy of collateral flow in LVO patients. The final component (CTP) permits a more accurate assessment of the extent of the ischemic penumbra. Complete multimodal CT, including objective penumbral measurement with CTP, has been used to extend the EVT window to 24 h. There is also randomized controlled trial evidence for extension of the IV thrombolysis window to 9 h with multimodal CT. Although there have been attempts to assess for responders to reperfusion strategies beyond 6 h ("late window") using collateral grades, the only evidence for treatment of this group of patients is based on selection using multimodal CT including CTP. The development of fully automated software providing quantitative ischemic penumbral and core volumes has facilitated the adoption of CTP and complete multimodal CT into routine clinical use. Multimodal CT is a powerful imaging algorithm that is central to current ischemic stroke patient care.

Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information

In developed countries, the second leading cause of death is stroke, which has the ischemic stroke as the most common type. The preferred diagnosis procedure involves the acquisition of multi-modal Magnetic Resonance Imaging. Besides detecting and locating the stroke lesion, Magnetic Resonance Imaging captures blood flow dynamics that guides the physician in evaluating the risks and benefits of the reperfusion procedure. However, the decision process is an intricate task due to the variability of lesion size, shape, and location, as well as the complexity of the underlying cerebral hemodynamic process. Therefore, an automatic method that predicts the stroke lesion outcome, at a 3-month follow-up, would provide an important support to the physicians' decision process. In this work, we propose an automatic deep learning-based method for stroke lesion outcome prediction. Our main contribution resides in the combination of multi-modal Magnetic Resonance Imaging maps with non-imaging clinical meta-data: the thrombolysis in cerebral infarction scale, which categorizes the success of recanalization, achieved through mechanical thrombectomy. In our proposal, this clinical information is considered at two levels. First, at a population level by embedding the clinical information in a custom loss function used during training of our deep learning architecture. Second, at a patient-level through an extra input channel of the neural network used at testing time for a given patient case. By merging imaging with non-imaging clinical information, we aim to obtain a model aware of the principal and collateral blood flow dynamics for cases where there is no perfusion beyond the point of occlusion and for cases where the perfusion is complete after the occlusion point.

Gene interference regulates aquaporin-4 expression in swollen tissue of rats with cerebral ischemic edema: Correlation with variation in apparent diffusion coefficient

To investigate the effects of mRNA interference on aquaporin-4 expression in swollen tissue of rats with ischemic cerebral edema, and diagnose the significance of diffusion-weighted MRI, we injected 5 μL shRNA- aquaporin-4 (control group) or siRNA- aquaporin-4 solution (1:800) (RNA interference group) into the rat right basal ganglia immediately before occlusion of the middle cerebral artery. At 0.25 hours after occlusion of the middle cerebral artery, diffusion-weighted MRI displayed a high signal; within 2 hours, the relative apparent diffusion coefficient decreased markedly, aquaporin-4 expression increased rapidly, and intracellular edema was obviously aggravated; at 4 and 6 hours, the relative apparent diffusion coefficient slowly returned to control levels, aquaporin-4 expression slightly increased, and angioedema was observed. In the RNA interference group, during 0.25–6 hours after injection of siRNA- aquaporin-4 solution, the relative apparent diffusion coefficient slightly fluctuated and aquaporin-4 expression was upregulated; during 0.5–4 hours, the relative apparent diffusion coefficient was significantly higher, while aquaporin-4 expression was significantly lower when compared with the control group, and intracellular edema was markedly reduced; at 0.25 and 6 hours, the relative apparent diffusion coefficient and aquaporin-4 expression were similar when compared with the control group; obvious angioedema remained at 6 hours. Pearson's correlation test results showed that aquaporin-4 expression was negatively correlated with the apparent diffusion coefficient (r = −0.806, P < 0.01). These findings suggest that upregulated aquaporin-4 expression is likely to be the main molecular mechanism of intracellular edema and may be the molecular basis for decreased relative apparent diffusion coefficient. Aquaporin-4 gene interference can effectively inhibit the upregulation of aquaporin-4 expression during the stage of intracellular edema with time-effectiveness. Moreover, diffusion-weighted MRI can accurately detect intracellular edema.

Anoxic-ischemic encephalopathy and strokes causing impaired consciousness

Coma due to global or focal ischemia or hemorrhage is reviewed. Impaired consciousness due to anoxic-ischemic encephalopathy after cardiac arrest is common but prognostically problematic. Recent guidelines need to be refined for those patients who have received therapeutic hypothermia. Strokes, both ischemic and hemorrhagic, can affect the level of consciousness by damaging specific brain structures involved in alertness because of widespread cerebral injury or secondary cerebral or systemic complications.

Cerebral blood flow and the injured brain: how should we monitor and manipulate it?

PURPOSE OF REVIEW

Cerebral ischemia plays a major role in the pathophysiology of the injured brain, including traumatic brain injury and subarachnoid hemorrhage, thus improvement in outcome may necessitate monitoring and optimization of cerebral blood flow (CBF). To interpret CBF results in a meaningful way, it may be necessary to quantify cerebral autoregulation as well as cerebral metabolism. This review addresses the recent evidence related to the changes in CBF and its monitoring/management in traumatic brain injury.

RECENT FINDINGS

Recent evidence on the management of patients with traumatic brain injury have focused on the importance of cerebral autoregulation in maintaining perfusion, which necessitates the measurement of CBF. However, adequate CBF measurements alone would not indicate the amount of oxygen delivered to neuronal tissues. Technologic advancements in measurement devices have enabled the assessment of the metabolic state of the cerebral tissue for the purpose of guiding therapy, progress as well as prognostification.

SUMMARY

Current neurocritical care management strategies are focused on the prevention and limitation of secondary brain injury where neuronal insult continues to evolve during the hours and days after the primary injury. Appropriately chosen multimodal monitoring including CBF and management measures can result in reduction in mortality and morbidity.

Therapeutic time window for the neuroprotective effects of NGF when administered after focal cerebral ischemia

In the present study, we evaluated the neuroprotection time window for nerve growth factor (NGF) after ischemia/reperfusion brain injury in rabbits as related to this anti-apoptosis mechanism. Male New Zealand rabbits were subjected to 2 h of middle cerebral artery occlusion (MCAO), followed by 70 h of reperfusion. NGF was administered after injury to evaluate the time window. Neurological deficits, infarct volume, neural cell apoptosis and expressions of caspase-3 and Bcl-2 were measured. Compared to saline-treated control, NGF treatment at 2, 3 and 5 h after MCAO significantly reduced infarct volume, neural cell apoptosis and expression of caspase-3 (P < 0.01), up-regulated the expression of Bcl-2 and improved functional recovery (P < 0.01). However, treatment at latter time points did not produce significant neuroprotection. Neuroprotection treatment with NGF provides an extended time window of up to 5 h after ischemia/reperfusion brain injury, in part by attenuating the apoptosis.

Brain extracellular fluid protein changes in acute stroke patients

In vivo human brain extracellular fluids (ECF) of acute stroke patients were investigated to assess the changes in protein levels associated with ischemic damages. Microdialysates (MDs) from the infarct core (IC), the penumbra (P), and the unaffected contralateral (CT) brain regions of patients suffering an ischemic stroke (n = 6) were compared using a shotgun proteomic approach based on isobaric tagging and mass spectrometry. Quantitative analysis showed 53 proteins with increased amounts in the IC or P with respect to the CT samples. Glutathione S-transferase P (GSTP1), peroxiredoxin-1 (PRDX1), and protein S100-B (S100B) were further assessed with ELISA on the blood of unrelated control (n = 14) and stroke (n = 14) patients. Significant increases of 8- (p = 0.0002), 20- (p = 0.0001), and 11-fold (p = 0.0093) were found, respectively. This study highlights the value of ECF as an efficient source to further discover blood stroke markers.

The apnea test: rationale, confounders, and criticism

The apnea test is recommended for the diagnosis of brain death. There are several reasons this test should be reconsidered. Confounding factors for performing the test are vaguely and poorly specified. The following 2 confounders are usually present and not considered: potentially reversible high cervical spinal cord injury and central endocrine failure of adrenal and thyroid axes. There are case reports of breathing at a higher partial pressure of arterial carbon dioxide threshold and cases of recovery of breathing after brain death is diagnosed. The test is dangerous for an injured brain in the setting of high intracranial pressure. It can convert viable penumbral brain tissue to irreversibly nonfunctioning tissue via a transient increase in intracranial pressure and no-reflow phenomena. Hyperoxia during the apnea test can further suppress the function of medullary respiratory rhythm centers. Finally, the philosophical rationale for the need to show lack of spontaneous breathing in brain death is lacking.