Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation
Academic Radiology · 2024
DOI: 10.1016/j.acra.2023.10.044 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Academic Radiology, 2024. Verfasst von Girish Bathla und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, Iowa, USA (G.B., N.S., S.P.); Department of Radiology, Mayo Clinic, Roc…. Hauptthemen laut MEDLINE: Glioblastoma, Brain Neoplasms, Magnetic Resonance Imaging, Neural Networks, Computer. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: NIBIB NIH HHS.
Abstract (Originalsprache)
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. RESULTS: 3D-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. CONCLUSION: 3D-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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, Iowa, USA (G.B., N.S., S.P.); Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA (G.B.).
- Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa, USA (D.D.D.). Electronic address: durjoy-dhruba@uiowa.edu.
- College of Engineering, University of Iowa, Iowa City, Iowa, USA (Y.L., N.H.L., H.Z., M.S.).
- Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, Iowa, USA (G.B., N.S., S.P.); Department of Radiology, Mayo Clinic, Jacksonville, Florida, USA (N.S., A.A.).
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Pennsylvania, USA (S.M., D.R.W.).
- Senior research scientist, Avid Radiopharmaceuticals, Philadelphia, Pennsylvania, USA (S.R.).
Förderung
- NIBIB NIH HHS
Zitieren
APA
Bathla, G., Dhruba, D. D., Liu, Y., Le, N. H., Soni, N., Zhang, H., Mohan, S., Roberts-Wolfe, D., Rathore, S., Sonka, M., Priya, S., & Agarwal, A. (2024). Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation. Academic Radiology. https://doi.org/10.1016/j.acra.2023.10.044
Vancouver
Bathla G, Dhruba DD, Liu Y, Le NH, Soni N, Zhang H, et al. Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation. Academic Radiology. 2024. doi:10.1016/j.acra.2023.10.044
BibTeX
@article{Bathla2024,
author = {Bathla, Girish and Dhruba, Durjoy Deb and Liu, Yanan and Le, Nam H and Soni, Neetu and Zhang, Honghai and Mohan, Suyash and Roberts-Wolfe, Douglas and Rathore, Saima and Sonka, Milan and Priya, Sarv and Agarwal, Amit},
title = {Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation},
journal = {Academic Radiology},
year = {2024},
doi = {10.1016/j.acra.2023.10.044}
}
EUVIMED