Automatic segmentation of hemispheric CSF on MRI using deep learning: Quantifying cerebral edema following large hemispheric infarction

Background and objective

Cerebral edema (CED) is a serious complication of acute ischemic stroke (AIS), especially in patients with large hemispheric infarction (LHI). Herein, a deep learning-based approach is implemented to extract CSF from T2-Weighted Imaging (T2WI) and evaluate the relationship between quantified cerebrospinal fluid and outcomes.

Methods

Patients with acute LHI who underwent magnetic resonance imaging (MRI) were included. We used a deep learning algorithm to segment the CSF from T2WI. The hemispheric CSF ratio was calculated to evaluate its relationship with the degree of brain edema and prognosis in patients with LHI.

Results

For the 93 included patients, the left and right cerebrospinal fluid regions were automatically extracted with a mean Dice similarity coefficient of 0.830. Receiver operating characteristic analysis indicated that hemispheric CSF ratio was an accurate marker for qualitative severe cerebral edema (area under receiver-operating-characteristic curve 0.867 [95% CI, 0.781-0.929]). Multivariate logistic regression analysis of functional prognosis showed that previous stroke (OR = 5.229, 95% CI 1.013-26.984), ASPECT≤6 (OR = 13.208, 95% CI 1.136-153.540) and low hemispheric CSF ratio (OR = 0.966, 95% CI 0.937-0.997) were significantly associated with higher chances for unfavorable functional outcome in patients with LHI.

Conclusions

Automated assessment of CSF volume provides an objective biomarker of cerebral edema that can be leveraged to quantify the degree of cerebral edema and confirm its predictive effect on outcomes after LHI.

Correspondence between development of cytotoxic edema and cerebrospinal fluid volume and flow in the third ventricle after ischemic stroke

OBJECTIVES

The importance of monitoring cerebrospinal fluid for the development of edema in ischemic stroke has been emphasized; however, studies on the relationship between intraventricular cerebrospinal fluid behavior and edema through longitudinal observations and analysis are rare. This study aimed to investigate the correlation between the development of cytotoxic edema and cerebrospinal fluid volume and flow in the third ventricle after ischemic stroke.

MATERIALS AND METHODS

The ventricle and edema regions were obtained using apparent diffusion coefficients and T2 and subdivided into lateral/ventral 3rd ventricles and cytotoxic/vasogenic (or cyst) edema, respectively. In rat models of ischemic stroke, the volume and flow (via the pseudo-diffusion coefficient [D*]) of the ventricles and edema volumes were longitudinally monitored for up to 45 days after surgery.

RESULTS

The volume of cytotoxic edema increased in the hyperacute and acute phases, whereas the volume (r = -0.49) and median D* values (r = -0.48 in the anterior-posterior direction) of the ventral 3rd ventricle both decreased, showing negative correlations with the volume of cytotoxic edema. In contrast, the volume of vasogenic edema/cyst was positively correlated with the volume (r = 0.73) and median D* values (r = 0.78 in the anterior-posterior direction) of the lateral ventricle in the subacute and chronic phases.

CONCLUSIONS

This study showed that the evolution of cerebrospinal fluid volume and flow in the ventricles was associated with edema progression at different time points in the ischemic stroke brain. This provides an efficient framework for monitoring and quantifying the interplay between cerebrospinal fluid and edema.

D* from diffusion MRI reveals a correspondence between ventricular cerebrospinal fluid volume and flow in the ischemic rodent model

Quantitative measurement of cerebrospinal fluid (CSF) flow and volume and longitudinal monitoring of CSF dynamics provide insights into the compensatory characteristics of post-stroke CSF. In this study, we compared the MRI pseudo-diffusion index (D*) of live and sacrificed rat brains to confirm the effect of ventricular CSF flow on diffusion signals. We observed the relationship between the CSF peak velocities and D* through Monte Carlo (MC) simulations to further understand the source of D* contrast. We also determined the dominant CSF flow using D* in three directions. Finally, we investigated the dynamic evolutions of ventricular CSF flow and volume in a stroke rat model (n = 8) from preoperative to up to 45 days after surgery and determined the correlation between ventricular CSF volume and flow. MC simulations showed a strong positive correlation between the CSF peak velocity and D* (r = 0.99). The dominant CSF flow variations in the 3D ventricle could be measured using the maximum D* map. A longitudinal positive correlation between ventricular CSF volume and D* was observed in the lateral (r = 0.74) and ventral-third (r = 0.81) ventricles, respectively. The directional D* measurements provide quantitative CSF volume and flow information, which would provide useful insights into ischemic stroke with diffusion MRI.

Monoamine Neurotransmitter Metabolite Concentration as a Marker of Cerebrospinal Fluid Volume Changes

OBJECTIVE

In our previous papers we demonstrated that changes in blood and cerebrospinal fluid (CSF) osmolarity have a strong influence on CSF pressure and volume, which is in accordance with a new proposed hypothesis of CSF physiology. Thus, acute changes in CSF volume should be reflected in the CSF concentration of different central nervous system (CNS) metabolites.

METHODS

In anesthetized cats (n = 4) we measured the outflow volume of CSF by cisternal free drainage at a negative CSF pressure (-10 cmH2O) before and after the intraperitoneal (i.p.) application of a hypo-osmolar substance (distilled water). In samples of CSF collected at different time intervals (30 min) we measured the concentration of homovanillic acid (HVA).

RESULTS

In spite of fact that constant CSF outflow volume was obtained after a 30-min period in our model, the concentration of HVA gradually increased over time and became stable after 90 min. After the i.p. application of distilled water the outflow CSF volume increased significantly, whereas the concentration of HVA significantly decreased over 30 min.

CONCLUSIONS

The results observed suggest that alterations in serum osmolarity change the CSF volume and concentrations of neurotransmitter metabolites because of the osmotic arrival of water from CNS blood capillaries in all CSF compartments.