0 72

Cited 0 times in

Development and Validation of a Deep Learning-Based Model to Distinguish Glioblastoma from Solitary Brain Metastasis Using Conventional MR Images

Authors
 I Shin  ;  H Kim  ;  S S Ahn  ;  B Sohn  ;  S Bae  ;  J E Park  ;  H S Kim  ;  S-K Lee 
Citation
 AMERICAN JOURNAL OF NEURORADIOLOGY, Vol.42(5) : 838-844, 2021-05 
Journal Title
AMERICAN JOURNAL OF NEURORADIOLOGY
ISSN
 0195-6108 
Issue Date
2021-05
MeSH
Adult ; Aged ; Area Under Curve ; Brain Neoplasms / diagnostic imaging* ; Brain Neoplasms / secondary* ; Deep Learning* ; Diagnosis, Differential ; Female ; Glioblastoma / diagnostic imaging* ; Humans ; Image Enhancement ; Image Processing, Computer-Assisted / methods* ; Magnetic Resonance Imaging / methods* ; Male ; Middle Aged ; Reproducibility of Results ; Retrospective Studies
Abstract
Background and purpose: Differentiating glioblastoma from solitary brain metastasis preoperatively using conventional MR images is challenging. Deep learning models have shown promise in performing classification tasks. The diagnostic performance of a deep learning-based model in discriminating glioblastoma from solitary brain metastasis using preoperative conventional MR images was evaluated.

Materials and methods: Records of 598 patients with histologically confirmed glioblastoma or solitary brain metastasis at our institution between February 2006 and December 2017 were retrospectively reviewed. Preoperative contrast-enhanced T1WI and T2WI were preprocessed and roughly segmented with rectangular regions of interest. A deep neural network was trained and validated using MR images from 498 patients. The MR images of the remaining 100 were used as an internal test set. An additional 143 patients from another tertiary hospital were used as an external test set. The classifications of ResNet-50 and 2 neuroradiologists were compared for their accuracy, precision, recall, F1 score, and area under the curve.

Results: The areas under the curve of ResNet-50 were 0.889 and 0.835 in the internal and external test sets, respectively. The area under the curve of neuroradiologists 1 and 2 were 0.889 and 0.768 in the internal test set and 0.857 and 0.708 in the external test set, respectively.

Conclusions: A deep learning-based model may be a supportive tool for preoperative discrimination between glioblastoma and solitary brain metastasis using conventional MR images.
Full Text
http://www.ajnr.org/content/42/5/838.long
DOI
10.3174/ajnr.A7003
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Biomedical Systems Informatics (의생명시스템정보학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Radiology (영상의학교실) > 1. Journal Papers
Yonsei Authors
Kim, Hwiyoung(김휘영)
Sohn, Beomseok(손범석) ORCID logo https://orcid.org/0000-0002-6765-8056
Shin, Ilah(신일아)
Ahn, Sung Soo(안성수) ORCID logo https://orcid.org/0000-0002-0503-5558
Lee, Seung Koo(이승구) ORCID logo https://orcid.org/0000-0001-5646-4072
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/184852
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links