Automatic Brain Tumor Grading from MRI Data Using Convolutional Neural Networks and Quality Assessment

Abstract

Glioblastoma Multiforme is a high grade, very aggressive, brain tumor, with patients having a poor prognosis. Lower grade gliomas are less aggressive, but they can evolve into higher grade tumors over time. Patient management and treatment can vary considerably with tumor grade, ranging from tumor resection followed by a combined radio-and chemotherapy to a "wait and see" approach. Hence, tumor grading is important for adequate treatment planning and monitoring. The gold standard for tumor grading relies on histopathological diagnosis of biopsy specimens. However, this procedure is invasive, time consuming, and prone to sampling error. Given these disadvantages, automatic tumor grading from widely used MRI protocols would be clinically important, as a way to expedite treatment planning and assessment of tumor evolution. In this paper, we propose to use Convolutional Neural Networks for predicting tumor grade directly from imaging data. In this way, we overcome the need for expert annotations of regions of interest. We evaluate two prediction approaches: from the whole brain, and from an automatically defined tumor region. Finally, we employ interpretability methodologies as a quality assurance stage to check if the method is using image regions indicative of tumor grade for classification.

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI

“…Chexpert [6] uses GradCAM for visualization of pleural effusion in a radiograph. CAM is also used for interpretability in brain tumor grading [153]. Tang et al [68] uses guided Grad-CAM and feature occlusion, providing complementary heatmaps for the classification of Alzheimer's disease pathologies.…”

Classification of Brain Tumors from MRI Images Using a Convolutional Neural Network

“…The image databases used in BRATS are made publicly available after the competition is finished. Different classification algorithms designed using these image databases can be found in many papers [10][11][12][13][14]. However, the databases are usually small, on average about 285 images, and they often contain images showing two tumor levels, low and high level of glioma tumor, acquired in the axial plane [10].…”

On the Interpretability of Artificial Intelligence in Radiology: Challenges and Opportunities

“…Interpretability methods are approaches designed to explicitly enhance the interpretability of a machine learning algorithm, despite its complexity. Figure 1 (6,7) shows examples of popular interpretability techniques applied on medical images, such as guided backpropagation (8), gradient-weighted class activation mapping (Grad-CAM) (9), and regression concept vectors (6), which are described in detail below. (A web-based demonstration of interpretability approaches is available at https://www.…”