Next Article in Journal
The Effect of Different Deep Network Architectures upon CNN-Based Gaze Tracking
Next Article in Special Issue
Metric Embedding Learning on Multi-Directional Projections
Previous Article in Journal
A Novel Method for Inference of Chemical Compounds of Cycle Index Two with Desired Properties Based on Artificial Neural Networks and Integer Programming
Previous Article in Special Issue
Oil Spill Monitoring of Shipborne Radar Image Features Using SVM and Local Adaptive Threshold
Open AccessArticle

PUB-SalNet: A Pre-Trained Unsupervised Self-Aware Backpropagation Network for Biomedical Salient Segmentation

by Feiyang Chen 1,†, Ying Jiang 1,†, Xiangrui Zeng 1, Jing Zhang 2, Xin Gao 3 and Min Xu 1,*
Compututational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Department of Computer Science, University of California Irvine, Irvine, CA 92697, USA
Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Algorithms 2020, 13(5), 126;
Received: 19 April 2020 / Revised: 12 May 2020 / Accepted: 15 May 2020 / Published: 19 May 2020
(This article belongs to the Special Issue Bio-Inspired Algorithms for Image Processing)
Salient segmentation is a critical step in biomedical image analysis, aiming to cut out regions that are most interesting to humans. Recently, supervised methods have achieved promising results in biomedical areas, but they depend on annotated training data sets, which requires labor and proficiency in related background knowledge. In contrast, unsupervised learning makes data-driven decisions by obtaining insights directly from the data themselves. In this paper, we propose a completely unsupervised self-aware network based on pre-training and attentional backpropagation for biomedical salient segmentation, named as PUB-SalNet. Firstly, we aggregate a new biomedical data set from several simulated Cellular Electron Cryo-Tomography (CECT) data sets featuring rich salient objects, different SNR settings, and various resolutions, which is called SalSeg-CECT. Based on the SalSeg-CECT data set, we then pre-train a model specially designed for biomedical tasks as a backbone module to initialize network parameters. Next, we present a U-SalNet network to learn to selectively attend to salient objects. It includes two types of attention modules to facilitate learning saliency through global contrast and local similarity. Lastly, we jointly refine the salient regions together with feature representations from U-SalNet, with the parameters updated by self-aware attentional backpropagation. We apply PUB-SalNet for analysis of 2D simulated and real images and achieve state-of-the-art performance on simulated biomedical data sets. Furthermore, our proposed PUB-SalNet can be easily extended to 3D images. The experimental results on the 2d and 3d data sets also demonstrate the generalization ability and robustness of our method. View Full-Text
Keywords: unsupervised learning; saliency segmentation; biomedical image processing; pre-trained methods unsupervised learning; saliency segmentation; biomedical image processing; pre-trained methods
Show Figures

Figure 1

MDPI and ACS Style

Chen, F.; Jiang, Y.; Zeng, X.; Zhang, J.; Gao, X.; Xu, M. PUB-SalNet: A Pre-Trained Unsupervised Self-Aware Backpropagation Network for Biomedical Salient Segmentation. Algorithms 2020, 13, 126.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Search more from Scilit
Back to TopTop