Abstract #0893

Classification of Dense Tumor, Tumor Necrosis and Tumor Infiltration in Glioma: Machine Learning and Diffusion MRI

Zezhong Ye¹, Xiran Liu², Joshua Lin¹, Liang Wang², Richard Price³, Peng Sun¹, Jeff Viox¹, Sonika Dahiya^4,5, Albert Kim³, Jr-Shin Li², and Sheng-Kwei Song¹

¹Radiology, Washington University School of Medicine, St. Louis, MO, United States, ²Electrical & System Engineering, Washington University in St. Louis, St. Louis, MO, United States, ³Neurological Surgery, Washington University School of Medicine, St. Louis, MO, United States, ⁴Pathology and Immunology, Washington University School of Medicine, St. Louis, MO, United States, ⁵Immunology and Pathology, Washington University School of Medicine, St. Louis, MO, United States

Here we introduce a diffusion MR-based imaging technique - Diffusion MRI Histology (D-Histo), to detect and differentiate various co-existing tumor pathologies including high-cellularity tumor (tumor), tumor necrosis (necrosis) and tumor infiltration (infiltration) within high grade glioma. We incorporated a support vector machine algorithm to generate an automation framework to predict locations of tumor lesion, necrosis and infiltration. The mean predictive accuracy of the D-Histo SVM classifier for tumor lesion, necrosis and infiltration were 91.9%, 93.7% and 87.8%. DTI-based prediction under the same framework resulted in 44.4%, 56.0% and 43.0% accuracy for the three pathologies.

This abstract and the presentation materials are available to members only; a login is required.

Join Here