ASMCNN: An Efficient Brain Extraction Using Active Shape Model and Convolutional Neural Networks

TL;DR

This paper introduces ASMCNN, a novel brain extraction method combining Active Shape Model and CNNs, processing 2D MRI slices to improve segmentation accuracy over existing algorithms.

Contribution

The paper presents a new hybrid approach that leverages ASM and CNNs with group-based shape modeling and post-processing for enhanced brain extraction in MRI scans.

Findings

Outperforms state-of-the-art algorithms in accuracy

Effective in handling variability in MRI data

Utilizes group-based shape detection and advanced post-processing

Abstract

Brain extraction (skull stripping) is a challenging problem in neuroimaging. It is due to the variability in conditions from data acquisition or abnormalities in images, making brain morphology and intensity characteristics changeable and complicated. In this paper, we propose an algorithm for skull stripping in Magnetic Resonance Imaging (MRI) scans, namely ASMCNN, by combining the Active Shape Model (ASM) and Convolutional Neural Network (CNN) for taking full of their advantages to achieve remarkable results. Instead of working with 3D structures, we process 2D image sequences in the sagittal plane. First, we divide images into different groups such that, in each group, shapes and structures of brain boundaries have similar appearances. Second, a modified version of ASM is used to detect brain boundaries by utilizing prior knowledge of each group. Finally, CNN and post-processing methods, including Conditional Random Field (CRF), Gaussian processes, and several special rules are applied to refine the segmentation contours. Experimental results show that our proposed method outperforms current state-of-the-art algorithms by a significant margin in all experiments.