Automated Brain Tumor Segmentation Based on Multi-Planar Superpixel Level Features Extracted From 3D MR Images

Abstract

Brain tumor segmentation from Magnetic Resonance Imaging (MRI) is of great importance for better tumor diagnosis, growth rate prediction and radiotherapy planning. But this task is extremely challenging due to intrinsically heterogeneous tumor appearance, the presence of severe partial volume effect and ambiguous tumor boundaries. In this work, a unique approach of tumor segmentation is introduced based on superpixel level features extracted from all three planes (x-y, y-z, and z-x) of 3D volumetric MR images. In order to avoid the pixel randomness and to account for precise inhomogeneous boundaries of brain tumor, each of the images belonging to a particular plane is partitioned into irregular patches (superpixels) based on their intensity and spatial similarity. Next, various statistical and textural features are extracted from each superpixel where all three planes are considered separately in order to obtain better labeling on superpixels in tumor edges. A feature selection scheme is proposed based on their performance on histogram based consistency analysis and local descriptor pattern analysis, which offers a significant reduction in feature dimension without sacrificing classification performance. For the purpose of supervised classification, Extremely Randomized Trees is used to classify these superpixels into a tumor or a non-tumor class. Finally, pixel level decision is taken based on corresponding decisions obtained in each plane. Extensive simulations are carried out on publicly available dataset and it is found that the proposed method offers better tumor segmentation performance in comparison to that obtained by some state of the art methods.

Selecting critical features for data classification based on machine learning methods

“…Meanwhile, some unique characteristics of big data also bring about new possibilities for feature selection research [111]. The latest advances in feature selection are a combination of feature selection with deep learning especially the Convolutional Neural Networks (CNN) for classification tasks, such as applications in bioinformatics neurodegenerative disorders classification using the Principal Components Analysis (PCA) algorithm [112,113], brain tumor segmentation [114] using three planar super pixel based statistical and textural features extraction. Next, remote sensing imagery classification using a fusion of CNN and RF [115], and software fault prediction [116] using enhanced binary moth flame optimization as a feature selection, and text classification based on independent feature space search [117].…”

Brain MR image tumor detection and classification using neuro fuzzy with binary cuckoo search technique

“…Imtiaz et al 15 have proposed tumor division models, which refer to the properties of the superpixel level and come from each of the three levels (x-y, y-z and z-x) of 3D volumetric images in MRI. In order to move away from the randomness of the pixels and show uneven limits specific to a brain tumor, each image was divided into separate points (superpixels) due to its strength and the spatial environment.…”

Anatomical Landmarks and DAG Network Learning for Alzheimer’s Disease Diagnosis

“…MRI is usually destroyed by a smooth and slowly changing bias field, resulting in inhomogeneous image intensity, thus affecting the accuracy of image automatic processing. Generally, there are two kinds of methods to measure and correct the intensity nonuniformity, including the methods that use parametric representations of image intensity distributions [42] and the methods that use non-parametric representations [43], [44]. In our method, an automatic bias field correction method [42] is used to measure and correct the inhomogeneous intensity in which the Mixture of Gaussians model with extra parameters that account for smooth intensity variations is applied.…”