Optimizing Neuro-Oncology Imaging: A Review of Deep Learning Approaches for Glioma Imaging

Abstract

Radiographic assessment with magnetic resonance imaging (MRI) is widely used to characterize gliomas, which represent 80% of all primary malignant brain tumors. Unfortunately, glioma biology is marked by heterogeneous angiogenesis, cellular proliferation, cellular invasion, and apoptosis. This translates into varying degrees of enhancement, edema, and necrosis, making reliable imaging assessment challenging. Deep learning, a subset of machine learning artificial intelligence, has gained traction as a method, which has seen effective employment in solving image-based problems, including those in medical imaging. This review seeks to summarize current deep learning applications used in the field of glioma detection and outcome prediction and will focus on (1) pre- and post-operative tumor segmentation, (2) genetic characterization of tissue, and (3) prognostication. We demonstrate that deep learning methods of segmenting, characterizing, grading, and predicting survival in gliomas are promising opportunities that may enhance both research and clinical activities.

Keywords: artificial intelligence; deep learning; glioblastoma; glioma; machine learning; neural network.

Figure 1

Adapted from Goodfellow et al. [7]. Flowchart of the varying machine learning components across different disciplines, increasing in sophistication from left to right. Orange boxes denote trainable components.

Figure 2

Comparison of linear 1D measurements (A) and machine learning volumetric analysis (B) in a 64-year-old man with GBM, 11 weeks following resection. Chow et al. [35] found volumetric analysis preferable given the irregularity of recurrence. Panel A indicates the challenges of selecting greatest dimensions in 2D, while panel B shows how a semi-automated volumetric approach can accurately capture greatest dimensions.

Figure 3

Prototypical imaging features associated with IDH mutation status [59]. Our CNN demonstrated that T1 post-contrast features predict IDH1 mutation status. Specifically, IDH wild types are characterized by thick and irregular enhancement (A) or thin, irregular, poorly-margined, peripheral enhancement (B). In contrast, patients with IDH mutations show minimal enhancement (C) and well-defined tumor margins (D).