A Combined Deep-Learning and Lattice Boltzmann Model for Segmentation of the Hippocampus in MRI.

Yingqian Liu,Zhuangzhi Yan

doi:10.3390/s20133628

Abstract

Segmentation of the hippocampus (HC) in magnetic resonance imaging (MRI) is an essential step for diagnosis and monitoring of several clinical situations such as Alzheimer’s disease (AD), schizophrenia and epilepsy. Automatic segmentation of HC structures is challenging due to their small volume, complex shape, low contrast and discontinuous boundaries. The active contour model (ACM) with a statistical shape prior is robust. However, it is difficult to build a shape prior that is general enough to cover all possible shapes of the HC and that suffers the problems of complicated registration of the shape prior and the target object and of low efficiency. In this paper, we propose a semi-automatic model that combines a deep belief network (DBN) and the lattice Boltzmann (LB) method for the segmentation of HC. The training process of DBN consists of unsupervised bottom-up training and supervised training of a top restricted Boltzmann machine (RBM). Given an input image, the trained DBN is utilized to infer the patient-specific shape prior of the HC. The specific shape prior is not only used to determine the initial contour, but is also introduced into the LB model as part of the external force to refine the segmentation. We used a subset of OASIS-1 as the training set and the preliminary release of EADC-ADNI as the testing set. The segmentation results of our method have good correlation and consistency with the manual segmentation results.

Highlights

The shape and volume of the hippocampus (HC) is altered in cases of Alzheimer’s disease (AD), schizophrenia and epilepsy, among other conditions [1]
We propose a deep belief network (DBN) driven lattice Boltzmann (LB)
We proposed a DBN-driven LB model for HC segmentation

Summary

Introduction

The shape and volume of the hippocampus (HC) is altered in cases of Alzheimer’s disease (AD), schizophrenia and epilepsy, among other conditions [1]. Hippocampal segmentation methods include but are not limited to image-based methods, active contour models (ACM) [4], active appearance and shape models [5], atlas models [6] and deep learning methods [7]. Model-based methods such as active appearance and shape models can overcome the problems with previous methods and reduce user interaction at the expense of a large training set to build a general model. Especially multi-atlas based methods, have the advantage of enabling segmentation in individuals with great anatomical variability. The disadvantage of this kind of method is that it requires many registration operations, which increases its computational

Methods

Results

Discussion

Conclusion