Generative Adversarial Networks to Synthesize Missing T1 and FLAIR MRI Sequences for Use in a Multisequence Brain Tumor Segmentation Model
Authors:
- Gian Marco ConteGCGian Marco Conte
- Alexander D. WestonAWAlexander D. Weston
- David C. VogelsangDVDavid C. Vogelsang
- Kenneth A. PhilbrickKPKenneth A. Philbrick
- Jason C. CaiJCJason C. Cai
- Maurizio BarberaMBMaurizio Barbera
- Francesco SanvitoFSFrancesco Sanvito
- Daniel H. LachanceDLDaniel H. Lachance
- Robert B. JenkinsRJRobert B. Jenkins
- W. Oliver TobinWTW. Oliver Tobin
- Jeanette E. Eckel-PassowJEJeanette E. Eckel-Passow
- Bradley J. EricksonBEBradley J. Erickson
- 9 March 2021
- journal article
- research article
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 299 (2) , 313-323
Abstract
Brain MRI scans synthesized using generative adversarial networks can be used as inputs in an existing deep learning model, thus allowing for their application in case MRI data are missing. Background Missing MRI sequences represent an obstacle in the development and use of deep learning (DL) models that require multiple inputs. Purpose To determine if synthesizing brain MRI scans usi...Keywords
Funding Information
- National Institute of Neurological Disorders and Stroke (R01NS113803)
This publication has 26 references indexed in Scilit:
- DeepInfer: open-source deep learning deployment toolkit for image-guided therapy2017
- Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentationMedical Image Analysis, 2017
- Brain tumor segmentation with Deep Neural NetworksMedical Image Analysis, 2017
- Brain Tumor Segmentation Using Convolutional Neural Networks in MRI ImagesIEEE Transactions on Medical Imaging, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)IEEE Transactions on Medical Imaging, 2015
- scikit-image: image processing in PythonPeerJ, 2014
- Mean squared error: Love it or leave it? A new look at Signal Fidelity MeasuresIEEE Signal Processing Magazine, 2009
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Interobserver variations in gross tumor volume delineation of brain tumors on computed tomography and impact of magnetic resonance imagingRadiotherapy and Oncology, 2001