Attention LinkNet-152: a novel encoder-decoder based deep learning network for automated spine segmentation

被引:0
|
作者
Aqsa Dastgir [1 ]
Wang Bin [1 ]
Muhammad Usman Saeed [1 ]
Jinfang Sheng [1 ]
Luo Site [2 ]
Haseeb Hassan [2 ]
机构
[1] Central South University,School of Computer Science and Engineering
[2] Shenzhen Technology University,College of Health Science and Environmental Engineering
关键词
D O I
10.1038/s41598-025-95243-z
中图分类号
学科分类号
摘要
Segmenting the spine from CT images is crucial for diagnosing and treating spine-related conditions but remains challenging due to the spine’s complex anatomy and imaging artifacts. This study introduces a novel encoder-decoder-based deep learning approach, named LinkNet-152, tailored for automated spine segmentation. The model integrates a modified EfficientNetB7 encoder with attention modules to enhance feature extraction by focusing on regions of interest. The decoder leverages a modified LinkNet architecture, replacing ResNet34 with the deeper ResNet152 to improve feature extraction and segmentation accuracy. Additionally, gradient sensitivity-based pruning is applied to optimize the model’s complexity and computational efficiency. Evaluated on the VerSe 2019 and VerSe 2020 datasets, the proposed model achieves superior performance, with a Dice coefficient of 96.85% and a Jaccard index of 95.37%, outperforming state-of-the-art methods. These results highlight the model’s effectiveness in addressing the challenges of spine segmentation and its potential to advance clinical applications.
引用
收藏
相关论文
共 50 条
  • [21] Roadway Crack Segmentation Based on an Encoder-decoder Deep Network with Multi-scale Convolutional Blocks
    Sun, Mengyuan
    Guo, Runhua
    Zhu, Jinhui
    Fan, Wenhui
    2020 10TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2020, : 869 - 874
  • [22] Blur kernel estimation method based on deep encoder-decoder network
    Yu X.-Y.
    Xie W.
    Kongzhi Lilun Yu Yingyong/Control Theory and Applications, 2020, 37 (04): : 731 - 738
  • [23] Robust Boundary Segmentation in Medical Images Using a Consecutive Deep Encoder-Decoder Network
    Ngoc-Quang Nguyen
    Lee, Sang-Woong
    IEEE ACCESS, 2019, 7 : 33795 - 33808
  • [24] Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network
    Shahzad, Muhammad
    Umar, Arif Iqbal
    Shirazi, Syed Hamad
    Shaikh, Israr Ahmed
    IEEE ACCESS, 2021, 9 : 161326 - 161341
  • [25] DCNet: Densely Connected Deep Convolutional Encoder-Decoder Network for Nasopharyngeal Carcinoma Segmentation
    Li, Yang
    Han, Guanghui
    Liu, Xiujian
    SENSORS, 2021, 21 (23)
  • [26] Optimized encoder-decoder cascaded deep convolutional network for leaf disease image segmentation
    Femi, David
    Mukunthan, Manapakkam Anandan
    NETWORK-COMPUTATION IN NEURAL SYSTEMS, 2024,
  • [27] Effectiveness of encoder-decoder deep learning approach for colorectal polyp segmentation in colonoscopy images
    Hamza, Ameer
    Bilal, Muhammad
    Ramzan, Muhammad
    Malik, Nadia
    APPLIED INTELLIGENCE, 2025, 55 (04)
  • [28] Manipulating Retinal OCT data for Image Segmentation based on Encoder-Decoder Network
    Song, Mingue
    Kim, Yanggon
    PROCEEDINGS OF THE 2021 15TH INTERNATIONAL CONFERENCE ON UBIQUITOUS INFORMATION MANAGEMENT AND COMMUNICATION (IMCOM 2021), 2021,
  • [29] A DWT-based encoder-decoder network for Specularity segmentation in colonoscopy images
    Sharma, Vanshali
    Bhuyan, M. K.
    Das, Pradip K.
    Bora, Kangkana
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (26) : 40065 - 40084
  • [30] CA-SegNet: A channel-attention encoder-decoder network for histopathological image segmentation
    He, Feng
    Wang, Weibo
    Ren, Lijuan
    Zhao, Yixuan
    Liu, Zhengjun
    Zhu, Yuemin
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 96