Journal article
Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation
Academic radiology, Vol.31(5), pp.2041-2049
05/2024
DOI: 10.1016/j.acra.2023.10.044
PMID: 37977889
Abstract
RATIONALE AND OBJECTIVES Imaging-based differentiation between glioblastoma (GB) and brain metastases (BM) remains challenging. Our aim was to evaluate the performance of 3D-convolutional neural networks (CNN) to address this binary classification problem. MATERIALS AND METHODS T1-CE, T2WI, and FLAIR 3D-segmented masks of 307 patients (157 GB and 150 BM) were generated post resampling, co-registration normalization and semi-automated 3D-segmentation and used for internal model development. Subsequent external validation was performed on 59 cases (27 GB and 32 BM) from another institution. Four different mask-sequence combinations were evaluated using area under the curve (AUC), precision, recall and F1-scores. Diagnostic performance of a neuroradiologist and a general radiologist, both without and with the model output available, was also assessed.RESULTS3D-model using the T1-CE tumor mask (TM) showed the highest performance [AUC 0.93 (95% CI 0.858-0.995)] on the external test set, followed closely by the model using T1-CE TM and FLAIR mask of peri-tumoral region (PTR) [AUC of 0.91 (95% CI 0.834-0.986)]. Models using T2WI masks showed robust performance on the internal dataset but lower performance on the external set. Both neuroradiologist and general radiologist showed improved performance with model output provided [AUC increased from 0.89 to 0.968 (p = 0.06) and from 0.78 to 0.965 (p = 0.007) respectively], the latter being statistically significant.CONCLUSION3D-CNNs showed robust performance for differentiating GB from BMs, with T1-CE TM, either alone or combined with FLAIR-PTR masks. Availability of model output significantly improved the accuracy of the general radiologist.
Details
- Title: Subtitle
- Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation
- Creators
- Girish Bathla - University of Iowa Hospitals and ClinicsDurjoy Deb Dhruba - University of IowaYanan Liu - University of IowaNam H Le - University of IowaNeetu Soni - University of IowaHonghai Zhang - University of IowaSuyash Mohan - University of PennsylvaniaDouglas Roberts-Wolfe - University of PennsylvaniaSaima RathoreMilan Sonka - University of IowaSarv Priya - University of IowaAmit Agarwal - Mayo Clinic in Florida
- Resource Type
- Journal article
- Publication Details
- Academic radiology, Vol.31(5), pp.2041-2049
- DOI
- 10.1016/j.acra.2023.10.044
- PMID
- 37977889
- NLM abbreviation
- Acad Radiol
- eISSN
- 1878-4046
- Language
- English
- Electronic publication date
- 11/15/2023
- Date published
- 05/2024
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Engineering Administration; Radiation Oncology; The Iowa Institute for Biomedical Imaging; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Ophthalmology and Visual Sciences
- Record Identifier
- 9984513302902771
Metrics
43 Record Views