Automated Brain Metastases Detection Framework for T1-Weighted Contrast-Enhanced 3D MRI

Autor: Barbaros S. Erdal, Mutlu Demirer, Richard D. White, Luciano M. Prevedello, Matthew T. Bigelow, Wayne Slone, Engin Dikici, John L. Ryu
Jazyk: angličtina
Rok vydání: 2019
Předmět:
media_common.quotation_subject
Blob detection
Convolutional neural network
Sensitivity and Specificity
Standard deviation
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
Deep Learning
Imaging
Three-Dimensional
Health Information Management
Image Interpretation
Computer-Assisted
FOS: Electrical engineering
electronic engineering
information engineering
medicine
T1 weighted
Contrast (vision)
Humans
Electrical and Electronic Engineering
Stage (cooking)
media_common
medicine.diagnostic_test
business.industry
Brain Neoplasms
Image and Video Processing (eess.IV)
Brain
Magnetic resonance imaging
Electrical Engineering and Systems Science - Image and Video Processing
Magnetic Resonance Imaging
Computer Science Applications
Intensity (physics)
Neural Networks
Computer
Nuclear medicine
business
030217 neurology & neurosurgery
Algorithms
Biotechnology
Popis: Brain Metastases (BM) complicate 20–40% of cancer cases. BM lesions can present as punctate (1 mm) foci, requiring high-precision Magnetic Resonance Imaging (MRI) in order to prevent inadequate or delayed BM treatment. However, BM lesion detection remains challenging partly due to their structural similarities to normal structures (e.g., vasculature). We propose a BM-detection framework using a single-sequence gadolinium-enhanced T1-weighted 3D MRI dataset. The framework focuses on the detection of smaller (
Databáze: OpenAIRE
Externí odkaz: