Abstract-We present a new method for automatic segmentation of heterogeneous image data that takes a step toward bridging the gap between bottom-up affinity-based segmentation methods and top-down generative model based approaches. The main contribution of the paper is a Bayesian formulation for incorporating soft model assignments into the calculation of affinities, which are conventionally model free. We integrate the resulting model-aware affinities into the multilevel segmentation by weighted aggregation algorithm, and apply the technique to the task of detecting and segmenting brain tumor and edema in multichannel MR volumes. The computationally efficient method runs orders of magnitude faster than current state-ofthe-art techniques giving comparable or improved results. Our quantitative results indicate the benefit of incorporating modelaware affinities into the segmentation process for the difficult case of brain tumor.

Elevation in PIs as measured by TCD shows strong correlation with MRI evidence of small-vessel disease. TCD may be a useful physiologic index of the presence and severity of diffuse small-vessel disease.

No abstract

Assuming US is the initial imaging examination, when occlusion is diagnosed, MR angiography can depict it. If occlusion is confirmed, no further imaging is necessary. US performed well in helping to differentiate vessels with focal severe stenosis from those with diffuse disease. MR angiography added little in this group. Catheter angiography remains beneficial for vessels with diffuse nonfocal narrowing.

Current clinical practice relies on clinical history to determine the time since stroke onset (TSS). Imaging-based determination of acute stroke onset time could provide critical information to clinicians in deciding stroke treatment options such as thrombolysis. Patients with unknown or unwitnessed TSS are usually excluded from thrombolysis, even if their symptoms began within the therapeutic window. In this work, 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 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