Core and penumbra estimation using deep learning-based AIF in association with clinical measures in computed tomography perfusion (CTP).

OBJECTIVES: To investigate whether utilizing a convolutional neural network (CNN)-based arterial input function (AIF) improves the volumetric estimation of core and penumbra in association with clinical measures in stroke patients. METHODS: The study included 160 acute ischemic stroke patients (male = 87, female = 73, median age = 73 years) with approval from the institutional review board. The patients had undergone CTP imaging, NIHSS and ASPECTS grading. convolutional neural network (CNN) model was trained to fit a raw AIF curve to a gamma variate function. CNN AIF was utilized to estimate the core and penumbra volumes which were further validated with clinical scores. RESULTS: Penumbra estimated by CNN AIF correlated positively with the NIHSS score (r = 0.69; p < 0.001) and negatively with the ASPECTS (r = - 0.43; p < 0.001). The CNN AIF estimated penumbra and core volume matching the patient symptoms, typically in patients with higher NIHSS (> 20) and lower ASPECT score (< 5). In group analysis, the median CBF < 20%, CBF < 30%, rCBF < 38%, Tmax > 10 s, Tmax > 10 s volumes were statistically significantly higher (p < .05). CONCLUSIONS: With inclusion of the CNN AIF in perfusion imaging pipeline, penumbra and core estimations are more reliable as they correlate with scores representing neurological deficits in stroke. CRITICAL RELEVANCE STATEMENT: With CNN AIF perfusion imaging pipeline, penumbra and core estimations are more reliable as they correlate with scores representing neurological deficits in stroke.

Arterial input function segmentation based on a contour geodesic model for tissue at risk identification in ischemic stroke.

PURPOSE: Perfusion parameters such as cerebral blood flow (CBF) and Tmax have been proven to be useful in the diagnosis and prognosis for ischemic stroke. Arterial input function (AIF) is required as an input to estimate perfusion parameters. This makes the AIF selection paradigm of clinical importance. METHODS: This study proposes a new technique to address the problem of AIF selection, based on a variational segmentation model that combines geometric constraint in a distance function. The modified model uses discrete total variation in the distance term and via minimizing energy locates the arterial regions. Matrix analysis is utilized to identify the AIF with maximum peak height within the segmented region. RESULTS: Group mean differences indicate that overall the AIF selected by the purposed method has better arterial features of higher peak position (16.7 and 26.1 a.u.) and fast attenuation (1.08 s and 0.9 s) as compared to the other state-of-the-art methods. Utilizing the selected AIF, mean CBF, and Tmax values were estimated higher than the traditional methods. Ischemic regions were precisely located through the perfusion maps. CONCLUSIONS: This AIF segmentation framework worked on perfusion images at levels superior to the current clinical state of the art. Consequently, the perfusion parameters derived from AIF selected by the purposed method were more accurate and reliable. The proposed method could potentially be considered as part of the calculation for perfusion imaging in general.

Optimal Scaling Approaches for Perfusion MRI with Distorted Arterial Input Function (AIF) in Patients with Ischemic Stroke.

BACKGROUND: Diagnosis and timely treatment of ischemic stroke depends on the fast and accurate quantification of perfusion parameters. Arterial input function (AIF) describes contrast agent concentration over time as it enters the brain through the brain feeding artery. AIF is the central quantity required to estimate perfusion parameters. Inaccurate and distorted AIF, due to partial volume effects (PVE), would lead to inaccurate quantification of perfusion parameters. METHODS: Fifteen patients suffering from stroke underwent perfusion MRI imaging at the Tri-Service General Hospital, Taipei. Various degrees of the PVE were induced on the AIF and subsequently corrected using rescaling methods. RESULTS: Rescaled AIFs match the exact reference AIF curve either at peak height or at tail. Inaccurate estimation of CBF values estimated from non-rescaled AIFs increase with increasing PVE. Rescaling of the AIF using all three approaches resulted in reduced deviation of CBF values from the reference CBF values. In most cases, CBF map generated by rescaled AIF approaches show increased CBF and Tmax values on the slices in the left and right hemispheres. CONCLUSION: Rescaling AIF by VOF approach seems to be a robust and adaptable approach for correction of the PVE-affected multivoxel AIF. Utilizing an AIF scaling approach leads to more reasonable absolute perfusion parameter values, represented by the increased mean CBF/Tmax values and CBF/Tmax images.

White Matter Differences in Networks in Elders with Mild Cognitive Impairment and Alzheimer's Disease.

Background: Alzheimer's disease (AD) is associated with impairment of large-scale brain networks, disruption in structural connections, and functional disconnection between distant brain regions. Although decreased functional connectivity has been thoroughly investigated and reported by existing functional neuroimaging literature, this study investigated network-based differences due to the structural changes in white matter pathways in AD patients. We hypothesize that diffusion metrics of disrupted tracts that go through cognitive networks related with intrinsic awareness, motor movement, and executive control can be utilized as biomarkers to distinguish prodromal stage from AD stage. Methods: Diffusion MRI data of a total 154 subjects, including patients with clinical AD (n = 47) and patients with mild cognitive impairment (MCI) (n = 107) was used. To study structural changes associated with white matter fiber pathways voxel-averaged diffusion metrics and fiber density metrics were calculated. Results: Study revealed that AD patients exhibit disruptions in intrahemispheric tracts and projection fiber tracts as suggested by diffusion indices. Our whole brain analysis revealed that network differences within default mode network (DMN), sensory motor network, and frontoparietal networks are associated with disruption in inferior fronto-occipital fasciculus (IFOF), corticospinal tract, and superior longitudinal fasciculus. Global function revealed by Mini Mental State Examination correlate with those fiber pathways that form reciprocal connections within networks associated with motor movement and executive control. Conclusion: Diffusion metrics appear to be more sensitive than fiber density metrics in differentiating the structural changes in the white matter. Decreased fractional anisotropy along with increased mean diffusivity and radial diffusivity in forceps minor, corticospinal tract, and IFOF as an imaging biomarker would be ideal to distinguish AD patients from MCI patients. Difference of DMN, sensory motor network, and frontal parietal network in our study reveals that AD patients may suffer from poor motor movement and degraded executive control.

Mathematical Framework of Deconvolution Algorithms for Quantification of Perfusion Parameters.

PURPOSE: MR perfusion weighted imaging (PWI) has been used as sensitive indicator of tissue at risk for infarction. Quantitative perfusion parameters such as cerebral blood flow (CBF), mean transit time (MTT) and cerebral blood volume (CBV) can be obtained from post processing of PWI data using standard singular value decomposition algorithm (SVD). Assumption regarding absence of arterial - tissue delay (ATD) used in SVD algorithm results in underestimation of perfusion parameters. To estimate accurate values for perfusion parameters it is important to understand the mathematical framework behind SVD and improved SVD algorithms (bSVD and rSVD). METHOD: This study explains the mathematical framework of SVD and improved SVD algorithms and uses computational techniques that use bSVD algorithm to obtain perfusion parameters maps of CBF, CBV and MTT for acute stroke patient. RESULT: Computational techniques based on mathematical deconvolution algorithms are used to post process CBV, CBF and MTT maps where decrease in CBF and CBV were seen in left hemisphere. CONCLUSION: The bSVD algorithm is found to be sensitive to ATD and provides more accurate estimates of perfusion parameters than the SVD algorithm, however CBF estimates from bSVD and rSVD still remain influenced by other artifacts Keywords: PWI = perfusion weighted imaging, CBF= cerebral blood flow, MTT = mean transit time, CBV= cerebral blood volume, SVD = singular value decomposition algorithm.