Masataka Nakagawa1, Takeshi Nakaura2, Tomohiro Namimoto3, Mika Kitajima4, Hiroyuki Uetani5, Machiko Tateishi6, Seitaro Oda7, Daisuke Utsunomiya8, Keishi Makino9, Hideo Nakamura10, Akitake Mukasa11, Toshinori Hirai12, Yasuyuki Yamashita13. 1. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: mstknkgw.a.you.1@gmail.com. 2. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: kff00712@nifty.com. 3. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: namimottoo@yahoo.co.jp. 4. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: mkitaji@kumamoto-u.ac.jp. 5. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: hama-moto@hotmail.co.jp. 6. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: mtateishi_kennnobe@yahoo.co.jp. 7. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: seisei1979@yahoo.co.jp. 8. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: d.utsunomiya@gmail.com. 9. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: kmakino@kuh.kumamoto-u.ac.jp. 10. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: hnakamur@kuh.kumamoto-u.ac.jp. 11. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: mukasa@kumamoto-u.ac.jp. 12. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: toshinorh@gmail.com. 13. Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuoku, Kumamoto, 860-8556, Japan. Electronic address: yama@kumamoto-u.ac.jp.
Abstract
PURPOSE: To evaluate the performance of a machine learning method based on texture features in multi-parametric magnetic resonance imaging (MRI) to differentiate a glioblastoma multiforme (GBM) from a primary cerebral nervous system lymphoma (PCNSL). MATERIALS AND METHODS: We included 70 patients who underwent contrast enhanced brain MRI at 3 T with brain tumors diagnosed as GBM (n = 45) and PCNSL (n = 25) in this retrospective study. Twelve histograms and texture parameters were assessed on T2-weighted images (T2WIs), apparent diffusion coefficient maps, relative cerebral blood volume (rCBV) map, and contrast-enhanced T1-weighted images (CE-T1WIs). A prediction model was developed using a machine learning method (univariate logistic regression and multivariate eXtreme gradient boosting-XGBoost) and the area under the receiver operating characteristic curve of this model was calculated via 10-fold cross validation. In addition, the performance of the machine learning method was compared with the judgments of two board certified radiologists. RESULTS: With the univariate logistic regression model, the standard deviation of rCBV offered the highest AUC (0.86), followed by mean value of rCBV (0.83), skewness of CE-T1WI (0.78), mean value of CET1 (0.78), and max value of rCBV (0.77). The AUC of the XGBoost was significantly higher than the two radiologists (0.98 vs. 0.84; p < 0.01 and 0.98 vs. 0.79; p < 0.01, respectively). CONCLUSION: The performance of machine learning based on histogram and texture features in multi-parametric MRI was superior to that of conventional cut-off method and the board certified radiologists to differentiate a GBM from a PCNSL.
PURPOSE: To evaluate the performance of a machine learning method based on texture features in multi-parametric magnetic resonance imaging (MRI) to differentiate a glioblastoma multiforme (GBM) from a primary cerebral nervous system lymphoma (PCNSL). MATERIALS AND METHODS: We included 70 patients who underwent contrast enhanced brain MRI at 3 T with brain tumors diagnosed as GBM (n = 45) and PCNSL (n = 25) in this retrospective study. Twelve histograms and texture parameters were assessed on T2-weighted images (T2WIs), apparent diffusion coefficient maps, relative cerebral blood volume (rCBV) map, and contrast-enhanced T1-weighted images (CE-T1WIs). A prediction model was developed using a machine learning method (univariate logistic regression and multivariate eXtreme gradient boosting-XGBoost) and the area under the receiver operating characteristic curve of this model was calculated via 10-fold cross validation. In addition, the performance of the machine learning method was compared with the judgments of two board certified radiologists. RESULTS: With the univariate logistic regression model, the standard deviation of rCBV offered the highest AUC (0.86), followed by mean value of rCBV (0.83), skewness of CE-T1WI (0.78), mean value of CET1 (0.78), and max value of rCBV (0.77). The AUC of the XGBoost was significantly higher than the two radiologists (0.98 vs. 0.84; p < 0.01 and 0.98 vs. 0.79; p < 0.01, respectively). CONCLUSION: The performance of machine learning based on histogram and texture features in multi-parametric MRI was superior to that of conventional cut-off method and the board certified radiologists to differentiate a GBM from a PCNSL.
Authors: G I Cassinelli Petersen; J Shatalov; T Verma; W R Brim; H Subramanian; A Brackett; R C Bahar; S Merkaj; T Zeevi; L H Staib; J Cui; A Omuro; R A Bronen; A Malhotra; M S Aboian Journal: AJNR Am J Neuroradiol Date: 2022-03-31 Impact factor: 3.825
Authors: Peter A Noseworthy; Zachi I Attia; LaPrincess C Brewer; Sharonne N Hayes; Xiaoxi Yao; Suraj Kapa; Paul A Friedman; Francisco Lopez-Jimenez Journal: Circ Arrhythm Electrophysiol Date: 2020-02-16