Segmentation of Lymph Nodes in Ultrasound Images Using U-Net Convolutional Neural Networks and Gabor-Based Anisotropic Diffusion

Purpose The automated segmentation of lymph nodes (LNs) in ultrasound images is challenging, largely because of speckle noise and echogenic hila. This paper proposes a fully automatic and accurate method for LN segmentation in ultrasound that overcomes these issues. Methods The proposed segmentation...

Full description

Saved in:
Bibliographic Details
Published in:Journal of medical and biological engineering 2021-12, Vol.41 (6), p.942-952
Main Authors: Chen, Haobo, Wang, Yuqun, Shi, Jie, Xiong, Jingyu, Jiang, Jianwei, Chang, Wanying, Chen, Man, Zhang, Qi
Format: Article
Language:English
Subjects:
Anisotropy
Artificial intelligence
Artificial neural networks
Biological Techniques
Biomedical and Life Sciences
Biomedical Engineering and Bioengineering
Biomedical Engineering/Biotechnology
Biomedicine
Diffusion
Image enhancement
Image processing
Image segmentation
Lymph nodes
Lymphatic system
Medical imaging
Morphology
Neural networks
Original Article
Regenerative Medicine/Tissue Engineering
Ultrasonic imaging
Ultrasound
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose The automated segmentation of lymph nodes (LNs) in ultrasound images is challenging, largely because of speckle noise and echogenic hila. This paper proposes a fully automatic and accurate method for LN segmentation in ultrasound that overcomes these issues. Methods The proposed segmentation method integrates diffusion-based despeckling, U-Net convolutional neural networks and morphological operations. First, the speckle noise is suppressed and the lymph node edges are enhanced using Gabor-based anisotropic diffusion (GAD). Then, a modified U-Net model is used to segment the LNs excluding any echogenic hila. Finally, morphological operations are undertaken to segment the entire LNs by filling in any regions occupied by echogenic hila. Results A total of 531 lymph nodes from 526 patients were segmented using the proposed method. Its segmentation performance was evaluated in terms of its accuracy, sensitivity, specificity, Jaccard similarity and Dice coefficient, for which it achieved values of 0.934, 0.939, 0.937, 0.763 and 0.865, respectively. Conclusion The proposed method automatically and accurately segments LNs in ultrasound images, enhancing the prospects of being able to undertake artificial intelligence (AI)-based diagnosis of lymph node diseases.
ISSN:1609-0985
2199-4757
DOI:10.1007/s40846-021-00670-8