Diffusion Histology Imaging Combining Diffusion Basis Spectrum Imaging (DBSI) and Machine Learning Improves Detection and Classification of Glioblastoma Pathology

Abstract

Purpose: Glioblastoma (GBM) is one of the deadliest cancers with no cure. While conventional MRI has been widely adopted to examine GBM clinically, accurate neuroimaging assessment of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation remains an unmet need in the clinical management of GBMs.Experimental Design: We employ a novel diffusion histology imaging (DHI) approach, combining diffusion basis spectrum imaging (DBSI) and machine learning, to detect, differentiate, and quantify areas of high cellularity, tumor necrosis, and tumor infiltration in GBM.Results: Gadolinium-enhanced T1-weighted or hyperintense fluid-attenuated inversion recovery failed to reflect the morphologic complexity underlying tumor in patients with GBM. Contrary to the conventional wisdom that apparent diffusion coefficient (ADC) negatively correlates with increased tumor cellularity, we demonstrate disagreement between ADC and histologically confirmed tumor cellularity in GBM specimens, whereas DBSI-derived restricted isotropic diffusion fraction positively correlated with tumor cellularity in the same specimens. By incorporating DBSI metrics as classifiers for a supervised machine learning algorithm, we accurately predicted high tumor cellularity, tumor necrosis, and tumor infiltration with 87.5%, 89.0%, and 93.4% accuracy, respectively.Conclusions: Our results suggest that DHI could serve as a favorable alternative to current neuroimaging techniques in guiding biopsy or surgery as well as monitoring therapeutic response in the treatment of GBM.

Applications of Radiomics and Radiogenomics in High-Grade Gliomas in the Era of Precision Medicine

“…Another study discovered a radiomic subtype of GBM with poor prognosis which might respond better to immunotherapy [ 79 ]. These findings might help answer critical clinical concerns, including determining the difference between TP and PsP or radiation necrosis [ 80 ]. Given the importance of tumor microenvironment, this is an emerging field in radiomics, and many studies are currently underway.…”

Deep neural network analysis employing diffusion basis spectrum imaging metrics as classifiers improves prostate cancer detection and grading

“…Two-dimensional (2D) thin plate spline (TPS) registration was performed using MIPAV Version 10.0.0 (NIH, Bethda, MD) as described previously (28) to co-register ex vivo MR images with histology images. We first ensure the plane of histology section of the prostate specimens matched closely with the slice plane of the corresponding T2W images.…”

“…We previously developed diffusion basis spectrum imaging (DBSI), which utilizes a data-driven multiple-tensor modeling approach to deconvolute cellular and structural profiles within an image voxel (24). DBSI-derived structural metrics distinguish and quantify various pathologies in an array of central nervous system (CNS) disorders (25)(26)(27)(28)(29). In this study, we examine whether DBSI-derived metrics reflect structural and cellular changes associated with PCa.…”

Glioma Classification Using Multimodal Radiology and Histology Data

“…grading and sub-typing) and for high-grade cases histopathology examination is often required [6]. In histopathology, gliomas are classified based on the morphological features of the glial cells including increased cellularity, vascular proliferation, necrosis, and infiltration into normal brain parenchyma [11,17]. Oncologists examine patients' medical history, radiology scans, pathology slides and reports to provide suitable medical care for a person diagnosed with cancer.…”