PItcHPERFeCT: Primary Intracranial Hemorrhage Probability Estimation using Random Forests on CT

Introduction Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10–15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans. Methods The Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test. Results All results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic (p < 0.001), LASSO (p < 0.001), or GAM (p < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package (https://github.com/muschellij2/ichseg) and a Shiny R application online (http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach.

[1]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[2]  Eric E. Smith,et al.  Imaging of hemorrhagic stroke. , 2006, Magnetic resonance imaging clinics of North America.

[3]  John Muschelli,et al.  fslr: Connecting the FSL Software with R , 2015, R J..

[4]  S. Wood Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models , 2011 .

[5]  Eric E. Smith,et al.  Prediction of Functional Outcome in Patients With Primary Intracerebral Hemorrhage: The FUNC Score , 2008, Stroke.

[6]  S. Mayer,et al.  Recombinant Activated Factor VII for Acute Intracerebral Hemorrhage , 2007, Stroke.

[7]  M. Y. Rathor,et al.  Prediction of functional outcome in patients with primary intracerebral hemorrhage by clinical-computed tomographic correlations , 2012, Journal of research in medical sciences : the official journal of Isfahan University of Medical Sciences.

[8]  K. Lee Effects of Early Intensive Blood Pressure-Lowering Treatment on the Growth of Hematoma and Perihematomal Edema in Acute Intracerebral Hemorrhage: The Intensive Blood Pressure Reduction in Acute Cerebral Haemorrhage Trial (INTERACT) , 2011 .

[9]  Chris Rorden,et al.  Age-specific CT and MRI templates for spatial normalization , 2012, NeuroImage.

[10]  S. Wood,et al.  Generalized additive models for large data sets , 2015 .

[11]  S. Tuhrim,et al.  Volume of ventricular blood is an important determinant of outcome in supratentorial intracerebral hemorrhage. , 1999, Critical care medicine.

[12]  Jitendra Malik,et al.  Anisotropic Diffusion , 1994, Geometry-Driven Diffusion in Computer Vision.

[13]  Arno Klein,et al.  A reproducible evaluation of ANTs similarity metric performance in brain image registration , 2011, NeuroImage.

[14]  Sven Loncaric,et al.  Hierarchical segmentation of CT head images , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  C. Crainiceanu,et al.  Quantitative Intracerebral Hemorrhage Localization , 2015, Stroke.

[16]  D. Hanley,et al.  Preliminary findings of the minimally-invasive surgery plus rtPA for intracerebral hemorrhage evacuation (MISTIE) clinical trial. , 2008, Acta neurochirurgica. Supplement.

[17]  M. Banerjee,et al.  Brain Edema After Human Cerebral Hemorrhage A Magnetic Resonance Imaging Volumetric Analysis , 2003, Journal of neurosurgical anesthesiology.

[18]  Ciprian M. Crainiceanu,et al.  Validated automatic brain extraction of head CT images , 2015, NeuroImage.

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  D. Hanley,et al.  Minimally Invasive Surgery Plus Recombinant Tissue-type Plasminogen Activator for Intracerebral Hemorrhage Evacuation Decreases Perihematomal Edema , 2013, Stroke.

[21]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[22]  A. Hillis,et al.  Intracerebral hemorrhage volume predicts poor neurologic outcome in children. , 2009, Stroke.

[23]  T Brott,et al.  The ABCs of measuring intracerebral hemorrhage volumes. , 1996, Stroke.

[24]  Glyn W. Humphreys,et al.  NeuroImage: Clinical Automated delineation of stroke lesions using brain CT images , 2022 .

[25]  Brian B. Avants,et al.  Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain , 2008, Medical Image Anal..

[26]  R. Tibshirani,et al.  Generalized Additive Models , 1986 .

[27]  John Muschelli,et al.  Accuracy of the ABC/2 Score for Intracerebral Hemorrhage: Systematic Review and Analysis of MISTIE, CLEAR-IVH, and CLEAR III , 2015, Stroke.

[28]  Wieslaw Lucjan Nowinski,et al.  Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique , 2012, International Journal of Computer Assisted Radiology and Surgery.

[29]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[30]  Brian B. Avants,et al.  An Open Source Multivariate Framework for n-Tissue Segmentation with Evaluation on Public Data , 2011, Neuroinformatics.

[31]  C. Anderson,et al.  Effects of Early Intensive Blood Pressure-Lowering Treatment on the Growth of Hematoma and Perihematomal Edema in Acute Intracerebral Hemorrhage: The Intensive Blood Pressure Reduction in Acute Cerebral Haemorrhage Trial (INTERACT) , 2010, Stroke.

[32]  Jie Zhang,et al.  The ABCs of Accurate Volumetric Measurement of Cerebral Hematoma , 2011, Stroke.

[33]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[34]  Yuko Y Palesch,et al.  Reliability of Hematoma Volume Measurement at Local Sites in a Multicenter Acute Intracerebral Hemorrhage Clinical Trial , 2013, Stroke.

[35]  J. Goldstein,et al.  Association of Serum Glucose Concentrations During Acute Hospitalization with Hematoma Expansion, Perihematomal Edema, and Three Month Outcome Among Patients with Intracerebral Hemorrhage , 2011, Neurocritical care.

[36]  A. Dávalos,et al.  Predictors of good outcome in medium to large spontaneous supratentorial intracerebral haemorrhages , 2005, Journal of Neurology, Neurosurgery & Psychiatry.

[37]  Sven Loncaric,et al.  Quantitative intracerebral brain hemorrhage analysis , 1999, Medical Imaging.

[38]  C. Anderson,et al.  Intensive blood pressure reduction in acute cerebral haemorrhage trial (INTERACT): a randomised pilot trial , 2008, The Lancet Neurology.

[39]  L. R. Dice Measures of the Amount of Ecologic Association Between Species , 1945 .

[40]  D. Hanley,et al.  Preliminary report of the clot lysis evaluating accelerated resolution of intraventricular hemorrhage (CLEAR-IVH) clinical trial. , 2008, Acta neurochirurgica. Supplement.

[41]  C. Rorden,et al.  Stereotaxic display of brain lesions. , 2000, Behavioural neurology.

[42]  M. Bergström,et al.  Variation with Time of the Attenuation Values of Intracranial Hematomas , 1977, Journal of computer assisted tomography.

[43]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[44]  G. Manley,et al.  The ICH score: a simple, reliable grading scale for intracerebral hemorrhage. , 2001, Stroke.

[45]  J. Weinberger,et al.  Management of intracerebral hemorrhage , 2007, Vascular health and risk management.

[46]  Bart M. ter Haar Romeny,et al.  Geometry-Driven Diffusion in Computer Vision , 1994, Computational Imaging and Vision.

[47]  Jj Allaire,et al.  Web Application Framework for R , 2016 .

[48]  Min Lou,et al.  Hematoma Volume Measurement in Gradient Echo MRI Using Quantitative Susceptibility Mapping , 2013, Stroke.

[49]  S. Pedraza,et al.  Reliability of the ABC/2 Method in Determining Acute Infarct Volume , 2012, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[50]  Miguel Ángel Guevara-López,et al.  Set of Methods for Spontaneous ICH Segmentation and Tracking from CT Head Images , 2007, CIARP.

[51]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[52]  J. Broderick,et al.  Volume of Intracerebral Hemorrhage: A Powerful and Easy‐to‐Use Predictor of 30‐Day Mortality , 1993, Stroke.