A general skull stripping of multiparametric brain MRIs using 3D convolutional neural network.

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 .

COVID-19-related state-wise racial and ethnic disparities across the USA: an observational study based on publicly available data from The COVID Tracking Project.

OBJECTIVE: To evaluate COVID-19 infection and mortality disparities in ethnic and racial subgroups in a state-wise manner across the USA. METHODS: Publicly available data from The COVID Tracking Project at The Atlantic were accessed between 9 September 2020 and 14 September 2020. For each state and the District of Columbia, % infection, % death, and % population proportion for subgroups of race (African American/black (AA/black), Asian, American Indian or Alaska Native (AI/AN), and white) and ethnicity (Hispanic/Latino, non-Hispanic) were recorded. Crude and normalised disparity estimates were generated for COVID-19 infection (CDI and NDI) and mortality (CDM and NDM), computed as absolute and relative difference between % infection or % mortality and % population proportion per state. Choropleth map display was created as thematic representation proportionate to CDI, NDI, CDM and NDM. RESULTS: The Hispanic population had a median of 158% higher COVID-19 infection relative to their % population proportion (median 158%, IQR 100%-200%). This was followed by AA, with 50% higher COVID-19 infection relative to their % population proportion (median 50%, IQR 25%-100%). The AA population had the most disproportionate mortality, with a median of 46% higher mortality than the % population proportion (median 46%, IQR 18%-66%). Disproportionate impact of COVID-19 was also seen in AI/AN and Asian populations, with 100% excess infections than the % population proportion seen in nine states for AI/AN and seven states for Asian populations. There was no disproportionate impact in the white population in any state. CONCLUSIONS: There are racial/ethnic disparities in COVID-19 infection/mortality, with distinct state-wise patterns across the USA based on racial/ethnic composition. There were missing and inconsistently reported racial/ethnic data in many states. This underscores the need for standardised reporting, attention to specific regional patterns, adequate resource allocation and addressing the underlying social determinants of health adversely affecting chronically marginalised groups.