Segmenting Brain Tissues from Chinese Visible Human Dataset by Deep-Learned Features with Stacked Autoencoder

Abstract

Cryosection brain images in Chinese Visible Human (CVH) dataset contain rich anatomical structure information of tissues because of its high resolution (e.g., 0.167 mm per pixel). Fast and accurate segmentation of these images into white matter, gray matter, and cerebrospinal fluid plays a critical role in analyzing and measuring the anatomical structures of human brain. However, most existing automated segmentation methods are designed for computed tomography or magnetic resonance imaging data, and they may not be applicable for cryosection images due to the imaging difference. In this paper, we propose a supervised learning-based CVH brain tissues segmentation method that uses stacked autoencoder (SAE) to automatically learn the deep feature representations. Specifically, our model includes two successive parts where two three-layer SAEs take image patches as input to learn the complex anatomical feature representation, and then these features are sent to Softmax classifier for inferring the labels. Experimental results validated the effectiveness of our method and showed that it outperformed four other classical brain tissue detection strategies. Furthermore, we reconstructed three-dimensional surfaces of these tissues, which show their potential in exploring the high-resolution anatomical structures of human brain.

Myocardium Detection by Deep SSAE Feature and Within-Class Neighborhood Preserved Support Vector Classifier and Regressor

“…SSAE is a deep neural network composed of multiple stacked sparse auto-encoders (SAEs) [37], and it has been applied in tissue segmentation in late gadolinium-enhanced cardiac MRI images (such as atrial scarring segmentation [38], atrial fibrosis segmentation [39], left atrium segmentation [40]), nuclei patch classification on breast cancer histopathology images [41], brain tissue segmentation in visible human images [42], or other applications (such as hyperspectral imagery classification [43] and building extraction from LiDAR and optical images [44]). Figure 3 shows a SSAE network with three hidden layers, where a SAE aims to learn features that form a good sparse representation of its input.…”

Gross Anatomy Education in China during the Covid‐19 Pandemic: A National Survey

“…Web‐based anatomy education has used various technologies, such as three‐dimensional (3D) computer models (Kancherla et al, 1995; Codd and Choudhury, 2011; Williams and George, 2013; Fellner et al, 2017), but the educational worth and efficacy of these technologies remains controversial (Nicholson et al, 2006). In mainland China, Chinese Visible Humans have been used in regional anatomy education (Liu et al, 2013; Wu et al, 2015; Zhao et al, 2016). Virtual reality modeling language (VRML) techniques and 3D animation software have been used by Chinese anatomists to reconstruct 3D models of human tissues and organs for teaching practice (Lifeng and Weimin, 2011; Li et al, 2012).…”

Automatic Vertebrae Localization and Identification by Combining Deep SSAE Contextual Features and Structured Regression Forest

“…performance in some specific tasks [24], which motivates us to investigate the SSAE-based feature learning for vertebrae localization and identification. SSAE essentially is a neural network consisting of multiple layers of sparse autoencoders (AEs) in which the outputs of each layer are connected to the inputs of the successive layer [24,25]. AE is an unsupervised learning algorithm that implements feature encoding by setting the target values to be equal to the inputs.…”