Accurate Patient-Specific Machine Learning Models of Glioblastoma Invasion Using Transfer Learning.

Leland Hu ,Leslie C Baxter ,J Ross Mitchell ,Ashley Nespodzany ,Jennifer Eschbacher ,Maciej M Mrugala ,P E Koulemberis ,Mithun G Sattur ,Peter Nakaji ,Kyle Singleton ,Amylou C Dueck ,Joseph M Hoxworth ,Yanzhe Xu ,Kris A Smith ,Lujia Wang ,C Chad Quarles ,Nhan L Tran ,John P Karis ,Andrea Hawkins-Daarud ,Richard S Zimmerman ,Hyunsoo Yoon ,Bernard R Bendok ,A B Porter-Umphrey ,Barrett J Anderies ,Chandan Krishna ,Pamela Jackson ,Anand Sharma ,Teresa Wu ,Nader Sanai ,Kristin R Swanson ,Jing Li

doi:10.3174/ajnr.a5981

Abstract

MR imaging-based modeling of tumor cell density can substantially improve targeted treatment of glioblastoma. Unfortunately, interpatient variability limits the predictive ability of many modeling approaches. We present a transfer learning method that generates individualized patient models, grounded in the wealth of population data, while also detecting and adjusting for interpatient variabilities based on each patient's own histologic data. We recruited patients with primary glioblastoma undergoing image-guided biopsies and preoperative imaging, including contrast-enhanced MR imaging, dynamic susceptibility contrast MR imaging, and diffusion tensor imaging. We calculated relative cerebral blood volume from DSC-MR imaging and mean diffusivity and fractional anisotropy from DTI. Following image coregistration, we assessed tumor cell density for each biopsy and identified corresponding localized MR imaging measurements. We then explored a range of univariate and multivariate predictive models of tumor cell density based on MR imaging measurements in a generalized one-model-fits-all approach. We then implemented both univariate and multivariate individualized transfer learning predictive models, which harness the available population-level data but allow individual variability in their predictions. Finally, we compared Pearson correlation coefficients and mean absolute error between the individualized transfer learning and generalized one-model-fits-all models. Tumor cell density significantly correlated with relative CBV (r = 0.33, P < .001), and T1-weighted postcontrast (r = 0.36, P < .001) on univariate analysis after correcting for multiple comparisons. With single-variable modeling (using relative CBV), transfer learning increased predictive performance (r = 0.53, mean absolute error = 15.19%) compared with one-model-fits-all (r = 0.27, mean absolute error = 17.79%). With multivariate modeling, transfer learning further improved performance (r = 0.88, mean absolute error = 5.66%) compared with one-model-fits-all (r = 0.39, mean absolute error = 16.55%). Transfer learning significantly improves predictive modeling performance for quantifying tumor cell density in glioblastoma.

Highlights

BACKGROUND AND PURPOSEMR imaging– based modeling of tumor cell density can substantially improve targeted treatment of glioblastoma
We evaluated a range of combined MR imaging contrasts to create various linear regression OMFA models
We address any potential risks of overfitting by performing leave-one-out cross-validation (LOOCV) to estimate the predictive performance of relative cerebral blood volume (rCBV) for quantifying tissue cell density (TCD)

Summary

Methods

We recruited patients with primary glioblastoma undergoing image-guided biopsies and preoperative imaging, including contrast-enhanced MR imaging, dynamic susceptibility contrast MR imaging, and diffusion tensor imaging. We explored a range of univariate and multivariate predictive models of tumor cell density based on MR imaging measurements in a generalized one-model-fits-all approach We implemented both univariate and multivariate individualized transfer learning predictive models, which harness the available population-level data but allow individual variability in their predictions. We recruited patients with clinically suspected primary GBM undergoing preoperative stereotactic MR imaging for first-line surgical resection before any treatment, as per our institutional review board protocol at Barrow Neurological Institute. We acquired preoperative 3T MR imaging (Sigma HDx; GE Healthcare, Milwaukee, Wisconsin) within 1 day of stereotactic surgery, including T2-weighted, T1-weighted precontrast, and T1-weighted postcontrast (T1 ϩ C) sequences.[3,6,14] T1 ϩ C images were acquired after completion of dynamic susceptibility contrast perfusion MR imaging following a total Gd-DTPA dosage of 0.15 mmol/kg.[3,6,14] In brief, for the DSC protocol, we administered an IV preload dose (0.1 mmol/kg of Gd-DTPA) to minimize T1weighted leakage errors, after which we administered a second IV bolus injection (0.05 mmol/kg of Gd-DTPA) during the 3-minute DSC acquisition (gradient-echo echo-planar imaging: TR/TE/flip angle ϭ 1500/20 ms/60°, matrix ϭ 128 ϫ 128, thickness ϭ 5 mm).[3,6,14] We derived postcontrast T2*WI (EPIϩC) from the initial-source DSC volume.[3,23] DTI acquisition consisted of spinecho EPI (TR/TE ϭ 10,000/85.2 ms, matrix ϭ 256 ϫ 256, FOV ϭ 30 cm, thickness ϭ 3 mm, 30 directions, array spatial sensitivity encoding technique, bϭ0, 1000).[3,6]

Results

Discussion

Conclusion