PURPOSE: To provide early and localized glioblastoma (GBM) recurrence prediction, we introduce a novel postsurgery multiparametric magnetic resonance-based support vector machine (SVM) method coupling with stem cell niche (SCN) proximity estimation. METHODS AND MATERIALS: This study used postsurgery magnetic resonance imaging (MRI) scans from 50 patients with recurrent GBM, obtained approximately 2 months before clinically diagnosed recurrence. The main prediction pipeline consisted of a proximity-based estimator to identify regions with high risk of recurrence (HRRs) and an SVM classifier to provide voxelwise prediction in HRRs. The HRRs were estimated using the weighted sum of inverse distances to 2 possible origins of recurrence-the SCN and the tumor cavity. Subsequently, multiparametric voxels (from T1, T1 contrast-enhanced, fluid-attenuated inversion recovery, T2, and apparent diffusion coefficient) within the HRR were grouped into recurrent (warped from the clinical diagnosis) and nonrecurrent subregions and fed into the proximity estimation-coupled SVM classifier (SVMPE). The cohort was randomly divided into 40% and 60% for training and testing, respectively. The trained SVMPE was then extrapolated to an earlier time point for earlier recurrence prediction. As an exploratory analysis, the SVMPE predictive cluster sizes and the image intensities from the 5 magnetic resonance sequences were compared across time to assess the progressive subclinical traces. RESULTS: On 2-month prerecurrence MRI scans from 30 test cohort patients, the SVMPE classifier achieved a recall of 0.80, a precision of 0.69, an F1-score of 0.73, and a mean boundary distance of 7.49 mm. Exploratory analysis at early time points showed spatially consistent but significantly smaller subclinical clusters and significantly increased T1 contrast-enhanced and apparent diffusion coefficient values over time. CONCLUSIONS: We demonstrated a novel voxelwise early prediction method, SVMPE, for GBM recurrence based on clinical follow-up MR scans. The SVMPE is promising in localizing subclinical traces of recurrence 2 months ahead of clinical diagnosis and may be used to guide more effective personalized early salvage therapy.
PURPOSE: To provide early and localized glioblastoma (GBM) recurrence prediction, we introduce a novel postsurgery multiparametric magnetic resonance-based support vector machine (SVM) method coupling with stem cell niche (SCN) proximity estimation. METHODS AND MATERIALS: This study used postsurgery magnetic resonance imaging (MRI) scans from 50 patients with recurrent GBM, obtained approximately 2 months before clinically diagnosed recurrence. The main prediction pipeline consisted of a proximity-based estimator to identify regions with high risk of recurrence (HRRs) and an SVM classifier to provide voxelwise prediction in HRRs. The HRRs were estimated using the weighted sum of inverse distances to 2 possible origins of recurrence-the SCN and the tumor cavity. Subsequently, multiparametric voxels (from T1, T1 contrast-enhanced, fluid-attenuated inversion recovery, T2, and apparent diffusion coefficient) within the HRR were grouped into recurrent (warped from the clinical diagnosis) and nonrecurrent subregions and fed into the proximity estimation-coupled SVM classifier (SVMPE). The cohort was randomly divided into 40% and 60% for training and testing, respectively. The trained SVMPE was then extrapolated to an earlier time point for earlier recurrence prediction. As an exploratory analysis, the SVMPE predictive cluster sizes and the image intensities from the 5 magnetic resonance sequences were compared across time to assess the progressive subclinical traces. RESULTS: On 2-month prerecurrence MRI scans from 30 test cohort patients, the SVMPE classifier achieved a recall of 0.80, a precision of 0.69, an F1-score of 0.73, and a mean boundary distance of 7.49 mm. Exploratory analysis at early time points showed spatially consistent but significantly smaller subclinical clusters and significantly increased T1 contrast-enhanced and apparent diffusion coefficient values over time. CONCLUSIONS: We demonstrated a novel voxelwise early prediction method, SVMPE, for GBM recurrence based on clinical follow-up MR scans. The SVMPE is promising in localizing subclinical traces of recurrence 2 months ahead of clinical diagnosis and may be used to guide more effective personalized early salvage therapy.
Authors: Günther Grabner; Andrew L Janke; Marc M Budge; David Smith; Jens Pruessner; D Louis Collins Journal: Med Image Comput Comput Assist Interv Date: 2006
Authors: James S Cordova; Hui-Kuo G Shu; Zhongxing Liang; Saumya S Gurbani; Lee A D Cooper; Chad A Holder; Jeffrey J Olson; Brad Kairdolf; Eduard Schreibmann; Stewart G Neill; Constantinos G Hadjipanayis; Hyunsuk Shim Journal: Neuro Oncol Date: 2016-03-15 Impact factor: 12.300
Authors: Nicholas J Tustison; Brian B Avants; Philip A Cook; Yuanjie Zheng; Alexander Egan; Paul A Yushkevich; James C Gee Journal: IEEE Trans Med Imaging Date: 2010-04-08 Impact factor: 10.048
Authors: Patrick Evers; Percy P Lee; John DeMarco; Nzhde Agazaryan; James W Sayre; Michael Selch; Frank Pajonk Journal: BMC Cancer Date: 2010-07-21 Impact factor: 4.430
Authors: Russell T Shinohara; Elizabeth M Sweeney; Jeff Goldsmith; Navid Shiee; Farrah J Mateen; Peter A Calabresi; Samson Jarso; Dzung L Pham; Daniel S Reich; Ciprian M Crainiceanu Journal: Neuroimage Clin Date: 2014-08-15 Impact factor: 4.881
Authors: Akshitkumar M Mistry; Nishit Mummareddy; Sanjana Salwi; Larry T Davis; Rebecca A Ihrie Journal: Front Oncol Date: 2020-12-11 Impact factor: 6.244
Authors: Md Yousuf Ali; Claudia R Oliva; Abu Shadat M Noman; Bryan G Allen; Prabhat C Goswami; Yousef Zakharia; Varun Monga; Douglas R Spitz; John M Buatti; Corinne E Griguer Journal: Cancers (Basel) Date: 2020-09-03 Impact factor: 6.639