Brain MR Image Classification Using Superpixel-Based Deep Transfer Learning.

Researchers

Journal

Modalities

Models

Abstract

Nowadays, brain MR (Magnetic Resonance) images are widely used by clinicians to examine the brain’s anatomy to look into various pathological conditions like cerebrovascular incidents and neuro-degenerative diseases. Generally, these diseases can be identified with the MR images as “normal” and “abnormal” brains in a two-class classification problem or as disease-specific classes in a multi-class problem. This article presents an ensemble transfer learning deep architecture that uses the simple linear iterative clustering (SLIC)-based superpixel algorithm along with CNN to classify the MR images into normal or abnormal. Superpixel algorithm is applied across the input MR images to segment into clusters of regions defined by similarity measures using perceptual feature space. These superpixel images are beneficial as they can provide a compact and meaningful image that plays a crucial role in computationally demanding applications. The superpixel images are then fed to the deep convolutional neural network (CNN) to classify the images. Three brain MR image datasets, NITR-DHH, DS-75, and DS-160, were used to conduct the experimentation. Through the use of deep transfer learning, the model managed to achieve the highest evaluated performance accuracy of 88.15% (NITR-DHH), 98.15% (DS-160), and 98.33% (DS-75) even with the small-scale medical image dataset. The experimentally obtained results demonstrate that our proposed method is promising and efficient for clinical applications for the diagnosis of different brain diseases via MR images.