Samantha E Seymour1,2, Ryan A Rava1,2, Dennis J Swetz1,2, Andre Monteiro3,4, Ammad Baig3,4, Kurt Schultz5, Kenneth V Snyder2,3,4, Muhammad Waqas2,4, Jason M Davies2,3,4,6, Elad I Levy2,3,4, Adnan H Siddiqui2,3,4, Ciprian N Ionita1,2,3,4. 1. Department of Biomedical Engineering, University at Buffalo, Buffalo, NY 14260, US. 2. Canon Stroke and Vascular Research Center, Buffalo, NY, 14203, US. 3. Jacobs School of Medicine and Biomedical Sciences, Buffalo, NY, 14203, US. 4. Department of Neurosurgery, University at Buffalo, Buffalo, NY 14203, US. 5. Canon Medical Research USA, Vernon Hills, IL 60061, US. 6. Department of Bioinformatics, University at Buffalo, Buffalo, NY 14214, US.
Abstract
Purpose: Intracranial hemorrhage (ICH) is characterized as bleeding into the brain tissue, intracranial space, and ventricles and is the second most disabling form of stroke. Hematoma expansion (HE) following ICH has been correlated with significant neurological decline and death. For early detection of patients at risk, deep learning prediction models were developed to predict whether hematoma due to ICH will expand. This study aimed to explore the feasibility of HE prediction using a radiomic approach to help clinicians better stratify HE patients and tailor intensive therapies timely and effectively. Materials and Methods: Two hundred ICH patients with known hematoma evolution, were enrolled in this study. An open-source python package was utilized for the extraction of radiomic features from both non-contrast computed tomography (NCCT) and magnetic resonance imaging (MRI) scans through characterization algorithms. A total of 99 radiomic features were extracted and different features were selected for network inputs for the NCCT and MR models. Seven supervised classifiers: Support Vector Machine, Naïve Bayes, Decision Tree, Random Forest, Logistic Regression, K-Nearest Neighbor and Multilayer Perceptron were used to build the models. A training:testing split of 80:20 and 20 iterations of Monte Carlo cross validation were performed to prevent overfitting and assess the variability of the networks, respectively. The models were fed training datasets from which they learned to classify the data based on pre-determined radiomic categories. Results: The highest sensitivity among the NCCT classifier models was seen with the support vector machine (SVM) and logistic regression (LR) of 72 ± 0.3% and 73 ± 0.5%, respectively. The MRI classifier models had the highest sensitivity of 68 ± 0.5% and 72 ± 0.5% for the SVM and LR models, respectively. Conclusions: This study indicates that the NCCT radiomics model is a better predictor of HE and that SVM and LR classifiers are better predictors of HE due to their more cautious approach indicated by a higher sensitivity metric.
Purpose: Intracranial hemorrhage (ICH) is characterized as bleeding into the brain tissue, intracranial space, and ventricles and is the second most disabling form of stroke. Hematoma expansion (HE) following ICH has been correlated with significant neurological decline and death. For early detection of patients at risk, deep learning prediction models were developed to predict whether hematoma due to ICH will expand. This study aimed to explore the feasibility of HE prediction using a radiomic approach to help clinicians better stratify HE patients and tailor intensive therapies timely and effectively. Materials and Methods: Two hundred ICH patients with known hematoma evolution, were enrolled in this study. An open-source python package was utilized for the extraction of radiomic features from both non-contrast computed tomography (NCCT) and magnetic resonance imaging (MRI) scans through characterization algorithms. A total of 99 radiomic features were extracted and different features were selected for network inputs for the NCCT and MR models. Seven supervised classifiers: Support Vector Machine, Naïve Bayes, Decision Tree, Random Forest, Logistic Regression, K-Nearest Neighbor and Multilayer Perceptron were used to build the models. A training:testing split of 80:20 and 20 iterations of Monte Carlo cross validation were performed to prevent overfitting and assess the variability of the networks, respectively. The models were fed training datasets from which they learned to classify the data based on pre-determined radiomic categories. Results: The highest sensitivity among the NCCT classifier models was seen with the support vector machine (SVM) and logistic regression (LR) of 72 ± 0.3% and 73 ± 0.5%, respectively. The MRI classifier models had the highest sensitivity of 68 ± 0.5% and 72 ± 0.5% for the SVM and LR models, respectively. Conclusions: This study indicates that the NCCT radiomics model is a better predictor of HE and that SVM and LR classifiers are better predictors of HE due to their more cautious approach indicated by a higher sensitivity metric.
Authors: Stephan A Mayer; Nikolai C Brun; Joseph Broderick; Stephen M Davis; Michael N Diringer; Brett E Skolnick; Thorsten Steiner Journal: Neurocrit Care Date: 2006 Impact factor: 3.210
Authors: Alexander R Podgorsak; Ryan A Rava; Mohammad Mahdi Shiraz Bhurwani; Anusha R Chandra; Jason M Davies; Adnan H Siddiqui; Ciprian N Ionita Journal: J Neurointerv Surg Date: 2019-08-23 Impact factor: 5.836
Authors: Ryan A Rava; Samantha E Seymour; Meredith E LaQue; Blake A Peterson; Kenneth V Snyder; Maxim Mokin; Muhammad Waqas; Yiemeng Hoi; Jason M Davies; Elad I Levy; Adnan H Siddiqui; Ciprian N Ionita Journal: World Neurosurg Date: 2021-03-05 Impact factor: 2.104
Authors: Joost J M van Griethuysen; Andriy Fedorov; Chintan Parmar; Ahmed Hosny; Nicole Aucoin; Vivek Narayan; Regina G H Beets-Tan; Jean-Christophe Fillion-Robin; Steve Pieper; Hugo J W L Aerts Journal: Cancer Res Date: 2017-11-01 Impact factor: 12.701