Localized prediction of tissue outcome in acute ischemic stroke patients using diffusion- and perfusion-weighted MRI datasets.

BACKGROUND: An accurate prediction of tissue outcome in acute ischemic stroke patients is of high interest for treatment decision making. To date, various machine learning models have been proposed that combine multi-parametric imaging data for this purpose. However, most of these machine learning models were trained using voxel information extracted from the whole brain, without taking differences in susceptibility to ischemia into account that exist between brain regions. The aim of this study was to develop and evaluate a local tissue outcome prediction approach, which makes predictions using locally trained machine learning models and thus accounts for regional differences. MATERIAL AND METHODS: Multi-parametric MRI data from 99 acute ischemic stroke patients were used for the development and evaluation of the local tissue outcome prediction approach. Diffusion (ADC) and perfusion parameter maps (CBF, CBV, MTT, Tmax) and corresponding follow-up lesion masks for each patient were registered to the MNI brain atlas. Logistic regression (LR) and random forest (RF) models were trained employing a local approach, which makes predictions using models individually trained for each specific voxel position using the corresponding local data. A global approach, which uses a single model trained using all voxels of the brain, was used for comparison. Tissue outcome predictions resulting from the global and local RF and LR models, as well as a combined (hybrid) approach were quantitatively evaluated and compared using the area under the receiver operating characteristic curve (ROC AUC), the Dice coefficient, and the sensitivity and specificity metrics. RESULTS: Statistical analysis revealed the highest ROC AUC and Dice values for the hybrid approach. With 0.872 (ROC AUC; LR) and 0.353 (Dice; RF), these values were significantly higher (p < 0.01) than the values of the two other approaches. In addition, the local approach achieved the highest sensitivity of 0.448 (LR). Overall, the hybrid approach was only outperformed in sensitivity (LR) by the local approach and in specificity by both other approaches. However, in these cases the effect sizes were comparatively small. CONCLUSION: The results of this study suggest that using locally trained machine learning models can lead to better lesion outcome prediction results compared to a single global machine learning model trained using all voxel information independent of the location in the brain.

Correction: Improved multi-parametric prediction of tissue outcome in acute ischemic stroke patients using spatial features.

[This corrects the article DOI: 10.1371/journal.pone.0228113.].

Improved multi-parametric prediction of tissue outcome in acute ischemic stroke patients using spatial features.

INTRODUCTION: In recent years, numerous methods have been proposed to predict tissue outcome in acute stroke patients using machine learning methods incorporating multiparametric imaging data. Most methods include diffusion and perfusion parameters as image-based parameters but do not include any spatial information although these parameters are spatially dependent, e.g. different perfusion properties in white and gray brain matter. This study aims to investigate if including spatial features improves the accuracy of multi-parametric tissue outcome prediction. MATERIALS AND METHODS: Acute and follow-up multi-center MRI datasets of 99 patients were available for this study. Logistic regression, random forest, and XGBoost machine learning models were trained and tested using acute MR diffusion and perfusion features and known follow-up lesions. Different combinations of atlas coordinates and lesion probability maps were included as spatial information. The stroke lesion predictions were compared to the true tissue outcomes using the area under the receiver operating characteristic curve (ROC AUC) and the Dice metric. RESULTS: The statistical analysis revealed that including spatial features significantly improves the tissue outcome prediction. Overall, the XGBoost and random forest models performed best in every setting and achieved state-of-the-art results regarding both metrics with similar improvements achieved including Montreal Neurological Institute (MNI) reference space coordinates or voxel-wise lesion probabilities. CONCLUSION: Spatial features should be integrated to improve lesion outcome prediction using machine learning models.

CT-perfusion stroke imaging: a threshold free probabilistic approach to predict infarct volume compared to traditional ischemic thresholds.

The aim was to evaluate a novel method of threshold-free prediction of brain infarct from computed tomography perfusion (CTP) imaging in comparison to conventional ischemic thresholds. In a multicenter cohort of 161 patients with acute large vessel occlusion who received endovascular therapy, brain infarction was predicted by CTP using (1) optimized parameter cut-off values determined by ROC curve analysis and (2) probabilistic logistic regression threshold-free analysis. Predicted infarct volumes and prediction errors based on four perfusion parameter maps were compared against observed infarcts. In 93 patients with successful recanalization, the mean observed infarct volume was 35.7 ± 61.9 ml (the reference for core infarct not savable by reperfusion). Optimal parameter thresholds predicted mean infarct volumes between 53.2 ± 44.4 and 125.0 ± 95.4 ml whereas threshold-free analysis predicted mean volumes between 35.9 ± 28.5 and 36.1 ± 29.0 ml. In 68 patients with persistent occlusion, the mean observed infarct volume was 113.4 ± 138.3 ml (the reference to define penumbral infarct savable by reperfusion). Predicted mean infarct volumes by parameter thresholds ranged from 91.4 ± 81.5 to 163.8 ± 135.7 ml, by threshold-free analysis from 113.2 ± 89.9 to 113.5 ± 89.0 ml. Threshold-free prediction of infarct volumes had a higher precision and lower patient-specific prediction error than conventional thresholding. Penumbra to core lesion mismatch estimate may therefore benefit from threshold-free CTP analysis.

Edema is not a reliable diagnostic sign to exclude small brain metastases.

No prior systematic study on the extent of vasogenic edema (VE) in patients with brain metastases (BM) exists. Here, we aim to determine 1) the general volumetric relationship between BM and VE, 2) a threshold diameter above which a BM shows VE, and 3) the influence of the primary tumor and location of the BM in order to improve diagnostic processes and understanding of edema formation. This single center, retrospective study includes 173 untreated patients with histologically proven BM. Semi-manual segmentation of 1416 BM on contrast-enhanced T1-weighted images and of 865 VE on fluid-attenuated inversion recovery/T2-weighted images was conducted. Statistical analyses were performed using a paired-samples t-test, linear regression/generalized mixed-effects model, and receiver-operating characteristic (ROC) curve controlling for the possible effect of non-uniformly distributed metastases among patients. For BM with non-confluent edema (n = 545), there was a statistically significant positive correlation between the volumes of the BM and the VE (P < 0.001). The optimal threshold for edema formation was a diameter of 9.4 mm for all BM. The primary tumors as interaction term in multivariate analysis had a significant influence on VE formation whereas location had not. Hence VE development is dependent on the volume of the underlying BM and the site of the primary neoplasm, but not from the location of the BM.

Heterogeneity of Multiple Sclerosis Lesions in Multislice Myelin Water Imaging.

PURPOSE: To assess neuroprotection and remyelination in Multiple Sclerosis (MS), we applied a more robust myelin water imaging (MWI) processing technique, including spatial priors into image reconstruction, which allows for lower SNR, less averages and shorter acquisition times. We sought to evaluate this technique in MS-patients and healthy controls (HC). MATERIALS AND METHODS: Seventeen MS-patients and 14 age-matched HCs received a 3T Magnetic Resonance Imaging (MRI) examination including MWI (8 slices, 12 minutes acquisition time), T2w and T1mprage pre and post gadolinium (GD) administration. Black holes (BH), contrast enhancing lesions (CEL) and T2 lesions were marked and registered to MWI. Additionally, regions of interest (ROI) were defined in the frontal, parietal and occipital normal appearing white matter (NAWM)/white matter (WM), the corticospinal tract (CST), the splenium (SCC) and genu (GCC) of the corpus callosum in patients and HCs. Mean values of myelin water fraction (MWF) were determined for each ROI. RESULTS: Significant differences (p≤0.05) of the MWF were found in all three different MS-lesion types (BH, CEL, T2 lesions), compared to the WM of HCs. The mean MWF values among the different lesion types were significantly differing from each other. Comparing MS-patients vs. HCs, we found a significant (p≤0.05) difference of the MWF in all measured ROIs except of GCC and SCC. The mean reduction of MWF in the NAWM of MS-patients compared to HCs was 37%. No age, sex, disability score and disease duration dependency was found for the NAWM MWF. CONCLUSION: MWF measures were in line with previous studies and lesions were clearly visible in MWI. MWI allows for quantitative assessment of NAWM and lesions in MS, which could be used as an additional sensitive imaging endpoint for larger MS studies. Measurements of the MWF also differ between patients and healthy controls.