Radio-pathomic estimates of cellular growth kinetics predict survival in recurrent glioblastoma
Sonoko Oshima,
Jingwen Yao,
Samuel Bobholz,
Raksha Nagaraj,
Catalina Raymond,
Ashley Teraishi,
Anna-Marie Guenther,
Asher Kim,
Francesco Sanvito,
Nicholas S Cho,
Blaine S C Eldred,
Jennifer M Connelly,
Phioanh L Nghiemphu,
Albert Lai,
Noriko Salamon,
Timothy F Cloughesy,
Peter S LaViolette,
Benjamin M Ellingson
Affiliations
Sonoko Oshima
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Jingwen Yao
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Samuel Bobholz
Department of Radiology, Medical College of Wisconsin, Milwaukee, WI 53226, USA
Raksha Nagaraj
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Catalina Raymond
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Ashley Teraishi
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Anna-Marie Guenther
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Asher Kim
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Francesco Sanvito
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Nicholas S Cho
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Blaine S C Eldred
UCLA Neuro-Oncology Program, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USA
Jennifer M Connelly
Department of Neurology, Medical College of Wisconsin, Milwaukee, WI 53226, USA
Phioanh L Nghiemphu
UCLA Neuro-Oncology Program, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USA
Albert Lai
UCLA Neuro-Oncology Program, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USA
Noriko Salamon
Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USA
Timothy F Cloughesy
UCLA Neuro-Oncology Program, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USA
Peter S LaViolette
Department of Radiology, Medical College of Wisconsin, Milwaukee, WI 53226, USA
Benjamin M Ellingson
UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision & Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA 90024, USA
Aim: A radio-pathomic machine learning (ML) model has been developed to estimate tumor cell density, cytoplasm density (Cyt) and extracellular fluid density (ECF) from multimodal MR images and autopsy pathology. In this multicenter study, we implemented this model to test its ability to predict survival in patients with recurrent glioblastoma (rGBM) treated with chemotherapy.Methods: Pre- and post-contrast T1-weighted, FLAIR and ADC images were used to generate radio-pathomic maps for 51 patients with longitudinal pre- and post-treatment scans. Univariate and multivariate Cox regression analyses were used to test the influence of contrast-enhancing tumor volume, total cellularity, mean Cyt and mean ECF at baseline, immediately post-treatment and the pre- and post-treatment rate of change in volume and cellularity on overall survival (OS).Results: Smaller Cyt and larger ECF after treatment were significant predictors of OS, independent of tumor volume and other clinical prognostic factors (HR = 3.23 × 10-6, p < 0.001 and HR = 2.39 × 105, p < 0.001, respectively). Both post-treatment volumetric growth rate and the rate of change in cellularity were significantly correlated with OS (HR = 1.17, p = 0.003 and HR = 1.14, p = 0.01, respectively).Conclusion: Changes in histological characteristics estimated from a radio-pathomic ML model are a promising tool for evaluating treatment response and predicting outcome in rGBM.
