Institution
Beaumont Health
Nonprofit•Royal Oak, Michigan, United States•
About: Beaumont Health is a nonprofit organization based out in Royal Oak, Michigan, United States. It is known for research contribution in the topics: Medicine & Population. The organization has 1483 authors who have published 1448 publications receiving 15407 citations. The organization is also known as: William Beaumont Health System & Beaumont Hospitals.
Topics: Medicine, Population, Cancer, Breast cancer, Arthroplasty
Papers published on a yearly basis
Papers
More filters
••
TL;DR: It is demonstrated that deep learning models, utilizing 3D convolutional neural networks, can accurately delineate the hippocampus using only high-resolution non-contrast CT images alone, comparable to those obtained by participating physicians from the RTOG 0933 Phase II clinical trial.
Abstract: Purpose Accurate segmentation of the hippocampus for hippocampal avoidance whole-brain radiotherapy currently requires high-resolution magnetic resonance imaging (MRI) in addition to neuroanatomic expertise for manual segmentation. Removing the need for MR images to identify the hippocampus would reduce planning complexity, the need for a treatment planning MR imaging session, potential uncertainties associated with MRI-computed tomography (CT) image registration, and cost. Three-dimensional (3D) deep convolutional network models have the potential to automate hippocampal segmentation. In this study, we investigate the accuracy and reliability of hippocampal segmentation by automated deep learning models from CT alone and compare the accuracy to experts using MRI fusion. Methods Retrospectively, 390 Gamma Knife patients with high-resolution CT and MR images were collected. Following the RTOG 0933 guidelines, images were rigidly fused, and a neuroanatomic expert contoured the hippocampus on the MR, then transferred the contours to CT. Using a calculated cranial centroid, the image volumes were cropped to 200 × 200 × 35 voxels, which were used to train four models, including our proposed Attention-Gated 3D ResNet (AG-3D ResNet). These models were then compared with results from a nested tenfold validation. From the predicted test set volumes, we calculated the 100% Hausdorff distance (HD). Acceptability was assessed using the RTOG 0933 protocol criteria, and contours were considered passing with HD ≤ 7 mm. Results The bilateral hippocampus passing rate across all 90 models trained in the nested cross-fold validation was 80.2% for AG-3D ResNet, which performs with a comparable pass rate (P = 0.3345) to physicians during centralized review for the RTOG 0933 Phase II clinical trial. Conclusions Our proposed AG-3D ResNet's segmentation of the hippocampus from noncontrast CT images alone are comparable to those obtained by participating physicians from the RTOG 0933 Phase II clinical trial.
8 citations
••
TL;DR: In this paper, the optimal approach to screening and risk stratification for non-alcoholic fatty liver disease is challenging given disease burden and variable progression, and the aim of this study was...
Abstract: Introduction:The optimal approach to screening and risk stratification for non-alcoholic fatty liver disease is challenging given disease burden and variable progression. The aim of this study was ...
8 citations
••
TL;DR: New regularity results for the solution in a class of weighted Sobolev spaces are established and finite element algorithms that approximate the singular solution at the optimal convergence rate are proposed.
8 citations
••
TL;DR: Both agents enable biochemical and morphological quantification of the IVD via contrast‐enhanced μCT and are effective tools for preclinical characterization.
8 citations
••
TL;DR: Care of anticoagulated patients in the acute care setting is inconsistent, reflecting the diversity of presentation, and further study and targeted educational efforts are needed to drive more evidence-based care of these patients.
Abstract: Objective The Safety of Oral Anticoagulants Registry (SOAR) was designed to describe the evaluation and management of patients with oral anticoagulant (OAC)-related major bleeding or bleeding concerns who present to the emergency department (ED) with acute illness or injury. Patients in the ED are increasingly taking anticoagulants, which can cause bleeding-related complications as well as impact the acute management of related or unrelated clinical issues that prompt presentation. Modifications of emergency evaluation and management due to anticoagulation have not previously been studied. Methods This was a multicenter observational in-hospital study of patients who were judged to be experiencing an active OAC effect and had (a) an obvious bleeding event or (b) were deemed at risk for serious bleeding spontaneously, after injury, or during an indicated invasive procedure. Diagnostic testing, therapies employed, and clinical outcomes were collected. Results Thirty-one US hospitals contributed data to SOAR. Of 1513 subjects, acute hemorrhage (AH) qualified 78%, while 22% had a bleeding concern (BC). Warfarin was the index OAC in 37.3%, dabigatran in 13.3%, and an anti-Factor Xa in 49.4%. The most common sites of AH were gastrointestinal (51.0%) and intracranial (26.8%). In warfarin-treated patients, the mean (IQR) presenting INR was 3.1 (2.2, 4.8) in AH patients and 3.9 (2.4, 7.2) in BC patients. Three-fifths of SOAR patients were treated with factor repletion or specific reversal agents, and those patients had a longer length of stay. In addition, seven (0.76%) of the treated patients experienced an in-hospital thrombotic complication; two of these seven died on the index admission, both of fatal pulmonary embolism. Vitamin K was used and dosed inconsistently in both warfarin and NOAC cohorts. Conclusion Care of anticoagulated patients in the acute care setting is inconsistent, reflecting the diversity of presentation. As the prevalence of OAC use increases with the aging of the US population, further study and targeted educational efforts are needed to drive more evidence-based care of these patients.
8 citations
Authors
Showing all 1494 results
Name | H-index | Papers | Citations |
---|---|---|---|
Barry P. Rosen | 102 | 529 | 36258 |
Praveen Kumar | 88 | 1339 | 35718 |
George S. Wilson | 88 | 716 | 33034 |
Ahmed Ali | 61 | 728 | 15197 |
Di Yan | 61 | 295 | 11437 |
David P. Wood | 59 | 243 | 12154 |
Brian D. Kavanagh | 58 | 322 | 15865 |
James A. Goldstein | 49 | 193 | 12312 |
Kenneth M. Peters | 46 | 197 | 6513 |
James M. Robbins | 45 | 157 | 8489 |
Bin Nan | 44 | 139 | 5321 |
Inga S. Grills | 43 | 217 | 6343 |
Sachin Kheterpal | 43 | 169 | 8545 |
Craig W. Stevens | 42 | 164 | 6598 |
Thomas Guerrero | 41 | 93 | 5018 |