Accurate skull stripping facilitates following neuro-image analysis. For computer-aided methods, the presence of brain skull in structural magnetic resonance imaging (MRI) impacts brain tissue identification, which could result in serious misjudgments, specifically for patients with brain tumors. Though there are several existing works on skull stripping in literature, most of them either focus on healthy brain MRIs or only apply for a single image modality. These methods may be not optimal for multiparametric MRI scans. In the paper, we propose an ensemble neural network (EnNet), a 3D convolutional neural network (3DCNN) based method, for brain extraction on multiparametric MRI scans (mpMRIs). We comprehensively investigate the skull stripping performance by using the proposed method on a total of 15 image modality combinations. The comparison shows that utilizing all modalities provides the best performance on skull stripping. We have collected a retrospective dataset of 815 cases with/without glioblastoma multiforme (GBM) at the University of Pittsburgh Medical Center (UPMC) and The Cancer Imaging Archive (TCIA). The ground truths of the skull stripping are verified by at least one qualified radiologist. The quantitative evaluation gives an average dice score coefficient and Hausdorff distance at the 95th percentile, respectively. We also compare the performance to the state-of-the-art methods/tools. The proposed method offers the best performance.The contributions of the work have five folds: first, the proposed method is a fully automatic end-to-end for skull stripping using a 3D deep learning method. Second, it is applicable for mpMRIs and is also easy to customize for any MRI modality combination. Third, the proposed method not only works for healthy brain mpMRIs but also pre-/post-operative brain mpMRIs with GBM. Fourth, the proposed method handles multicenter data. Finally, to the best of our knowledge, we are the first group to quantitatively compare the skull stripping performance using different modalities. All code and pre-trained model are available at: https://github.com/plmoer/skull_stripping_code_SR.

Accurate skull stripping helps following neuro-image analysis. For computer-aided methods, the presentence of the brain skull in structural MRI impacts brain tissue identification, which could result in serious misjudgment, especially for patients with brain tumors. Though there are some existing works on skull stripping in literature, most of them either focus on healthy brain MRI or only apply for a single image modality. These methods may be not optimal for multiparametric MRI scans. In the paper, we propose an ensemble neural network (EnNet), a 3D convolutional neural network (3DCNN) based method, for brain extraction of multiparametric brain MRI scans. We comprehensively investigate the skull stripping performance by using the proposed method on a total of 15 image modality combinations. The comparison shows that using all modalities provides the best performance on skull stripping. We have collected a retrospective dataset of 815 cases with glioblastoma at the University of Pittsburgh Medical Center (UPMC) and The Cancer Imaging Archive (TCIA). The ground truths of the skull stripping are verified by at least one qualified radiologist. The quantitative evaluation gives an average dice score coefficient and Hausdorff distance at 95th percentile, respectively. We also compare the performance to the state-of-the-art methods/tools. The proposed method offers the best performance.The contributions of the work have five folds: First, the proposed method is a fully automatic end-to-end for skull stripping using a 3D deep learning method. Second, it is applicable for multiparametric MRI (mpMRIs) and is also easy to customize for a single MRI modality. Third, the proposed method not only works for healthy brain mpMRIs but also pre-/post-operative brain mpMRIs with GBM. Fourth, the proposed method is capable to handle multicenter data. Last, to the best of our knowledge, we are the first group to quantitatively compare the skull stripping performance using different modalities.

Introduction: Heart failure is a common clinical syndrome that leads to high volumes of hospitalizations and in hospital mortality. Previous studies have attempted to characterize the various reasons for the high rates of morbidity and mortality associated with heart failure. Our study aimed to utilize large database information to identify the most common indicators for and cause of death in patients with heart failure. Methods: Using the National Inpatient Sample database, we analyzed heart failure hospitalizations during the years 2016-2019 and categorized reasons for hospitalization and in-patient mortality using the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10). Results: We identified a total of 5,281,210 hospitalizations with heart failure as the principal or secondary diagnosis ICD-10 code. The leading cause for admission was heart failure (65%), followed by sepsis (8.5%), non ST elevation myocardial infarction (NSTEMI) (6.0%), acute chronic obstructive pulmonary disease (COPD) exacerbation (2.5%) and pneumonia (2.2%). There were a total of 161,417 cases of in-hospital mortality in patients with heart failure during this period. The most common reason for mortality was heart failure itself (49.8%), followed by sepsis (41.2%), NSTEMI (12.8%), acute hypoxic respiratory failure (7.8%) and acute-on-chronic hypoxic respiratory failure (5.9%). Conclusion: This study represents the most recent nationwide data on causes for hospitalization and mortality in patients with heart failure across the United States, with the most common cause of both being heart failure itself followed by sepsis and NSTEMI. A better understanding of why patients are hospitalized may lead to changes in practice to prevent admissions as well as in-hospital management to ultimately prevent death.