A5017506914- Machine Learning in Materials Science
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Advanced Electron Microscopy Techniques and Applications
- Computational Drug Discovery Methods
- Glioma Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Pleural and Pulmonary Diseases
- Advanced X-ray and CT Imaging
- Cerebrovascular and Carotid Artery Diseases
- Head and Neck Cancer Studies
- Acute Ischemic Stroke Management
- Vascular Malformations Diagnosis and Treatment
- Ferroelectric and Negative Capacitance Devices
- Medical Imaging and Pathology Studies
- Myasthenia Gravis and Thymoma
- Cardiac Imaging and Diagnostics
Yuhuangding Hospital
2021-2024
Affiliated Hospital of Qingdao University
2021-2024
Qingdao University
2021-2024
Abstract Purpose: We aimed to develop and validate a deep learning (DL) model automatically segment posterior fossa ependymoma (PF-EPN) predict its molecular subtypes [Group A (PFA) Group B (PFB)] from preoperative MR images. Experimental Design: retrospectively identified 227 PF-EPNs (development internal test sets) with available T2-weighted (T2w) images status 3D nnU-Net (referred as T2-nnU-Net) for tumor segmentation subtype prediction. The network was externally tested using an external...
To investigate the value of fluid-attenuated inversion recovery vascular hyperintensity (FVH) within asymmetrical prominent veins sign (APVS) on susceptibility-weighted imaging predicting collateral circulation and prognosis in patients with acute anterior ischemic stroke.Patients severe stenosis or occlusion ICA MCA M1, who underwent MRI 72 h from stroke onset were reviewed. The Alberta Stroke Program Early CT Score was used to evaluate volume infarction DWI, degree FVH APVS. Spearman...
This study aimed to distinguish preoperatively anterior mediastinal thymic cysts from epithelial tumors via a computed tomography (CT)-based radiomics nomogram.This analyzed 74 samples of and 116 as confirmed by pathology examination that were collected January 2014 December 2020. Among the patients, 151 cases (scanned at CT 1) selected training cohort, 39 2 3) served validation cohort. Radiomics features extracted pre-contrast images. Key SelectKBest least absolute shrinkage selection...
<div>AbstractPurpose:<p>We aimed to develop and validate a deep learning (DL) model automatically segment posterior fossa ependymoma (PF-EPN) predict its molecular subtypes [Group A (PFA) Group B (PFB)] from preoperative MR images.</p>Experimental Design:<p>We retrospectively identified 227 PF-EPNs (development internal test sets) with available T2-weighted (T2w) images status 3D nnU-Net (referred as T2-nnU-Net) for tumor segmentation subtype prediction. The network...
<p>Next-generation sequencing</p>
<p>DNA methylation profiling</p>
<p>Next-generation sequencing</p>
<div>AbstractPurpose:<p>We aimed to develop and validate a deep learning (DL) model automatically segment posterior fossa ependymoma (PF-EPN) predict its molecular subtypes [Group A (PFA) Group B (PFB)] from preoperative MR images.</p>Experimental Design:<p>We retrospectively identified 227 PF-EPNs (development internal test sets) with available T2-weighted (T2w) images status 3D nnU-Net (referred as T2-nnU-Net) for tumor segmentation subtype prediction. The network...
<p>DNA methylation profiling</p>
This study aimed to explore the value of radiomics nomogram based on computed tomography (CT) diagnosis benign and malignant solitary indeterminate smoothly marginated solid pulmonary nodules (SMSPNs).