Weaving attention U-net: A novel hybrid CNN and attention-based method for organs-at-risk segmentation in head and neck CT images

Zhuangzhuang Zhang, Tianyu Zhao, Hiram Gay, Weixiong Zhang, Baozhou Sun

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Purpose: In radiotherapy planning, manual contouring is labor-intensive and time-consuming. Accurate and robust automated segmentation models improve the efficiency and treatment outcome. We aim to develop a novel hybrid deep learning approach, combining convolutional neural networks (CNNs) and the self-attention mechanism, for rapid and accurate multi-organ segmentation on head and neck computed tomography (CT) images. Methods: Head and neck CT images with manual contours of 115 patients were retrospectively collected and used. We set the training/validation/testing ratio to 81/9/25 and used the 10-fold cross-validation strategy to select the best model parameters. The proposed hybrid model segmented 10 organs-at-risk (OARs) altogether for each case. The performance of the model was evaluated by three metrics, that is, the Dice Similarity Coefficient (DSC), Hausdorff distance 95% (HD95), and mean surface distance (MSD). We also tested the performance of the model on the head and neck 2015 challenge dataset and compared it against several state-of-the-art automated segmentation algorithms. Results: The proposed method generated contours that closely resemble the ground truth for 10 OARs. On the head and neck 2015 challenge dataset, the DSC scores of these OARs were 0.91 (Formula presented.) 0.02, 0.73 (Formula presented.) 0.10, 0.95 (Formula presented.) 0.03, 0.76 (Formula presented.) 0.08, 0.79 (Formula presented.) 0.05, 0.87 (Formula presented.) 0.05, 0.86 (Formula presented.) 0.08, 0.87 (Formula presented.) 0.03, and 0.87 (Formula presented.) 0.07 for brain stem, chiasm, mandible, left/right optic nerve, left/right submandibular, and left/right parotid, respectively. Our results of the new weaving attention U-net (WAU-net) demonstrate superior or similar performance on the segmentation of head and neck CT images. Conclusions: We developed a deep learning approach that integrates the merits of CNNs and the self-attention mechanism. The proposed WAU-net can efficiently capture local and global dependencies and achieves state-of-the-art performance on the head and neck multi-organ segmentation task.

Original languageEnglish
Pages (from-to)7052-7062
Number of pages11
JournalMedical physics
Volume48
Issue number11
DOIs
StatePublished - Nov 2021

Keywords

  • attention mechanism
  • convolutional neural networks
  • deep learning
  • head and neck radiotherapy
  • multi-organ segmentation

Fingerprint

Dive into the research topics of 'Weaving attention U-net: A novel hybrid CNN and attention-based method for organs-at-risk segmentation in head and neck CT images'. Together they form a unique fingerprint.

Cite this