Literature DB >> 34058628

Lung computed tomography image segmentation based on U-Net network fused with dilated convolution.

Kuan-Bing Chen1, Ying Xuan2, Ai-Jun Lin3, Shao-Hua Guo4.   

Abstract

PURPOSE: In order to solve the problem of accurate and effective segmentation of the patient's lung computed tomography (CT) images, so as to improve the efficiency of treating lung cancer.
METHOD: We propose a U-Net network (DC-U-Net) fused with dilated convolution, and compare the results of segmented lung CT with DC-U-Net, Otsu and region growth. We use Intersection over Union (IOU), Dice coefficient, Precision and Recall to evaluate the performance of the three algorithms.
RESULTS: Compared with the common segmentation algorithm Otsu and region growing, the segmented image of DC-U-Net is closer to the Ground truth. The IOU of DC-U-Net is 0.9627, and the Dice coefficient is 0.9743, which is close to 1 and much higher than the other two algorithms.
CONCLUSION: We propose that the model can directly segment the original image automatically, and the segmentation effect is good. This model speeds up the segmentation, simplifies the steps of medical image segmentation, and provides better segmentation for subsequent lung blood vessels, trachea and other tissues.
Copyright © 2021 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Dilated convolution; Ground truth; Image segmentation; Lung CT; U-Net network

Year:  2021        PMID: 34058628     DOI: 10.1016/j.cmpb.2021.106170

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  2 in total

1.  A bi-directional deep learning architecture for lung nodule semantic segmentation.

Authors:  Debnath Bhattacharyya; N Thirupathi Rao; Eali Stephen Neal Joshua; Yu-Chen Hu
Journal:  Vis Comput       Date:  2022-09-08       Impact factor: 2.835

Review 2.  Research on CT Lung Segmentation Method of Preschool Children based on Traditional Image Processing and ResUnet.

Authors:  Zheming Li; Li Yang; Liqi Shu; Zhuo Yu; Jian Huang; Jing Li; Lingdong Chen; Shasha Hu; Ting Shu; Gang Yu
Journal:  Comput Math Methods Med       Date:  2022-10-10       Impact factor: 2.809

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.