Automatic segmentation of esophageal gross tumor volume in 18F-FDG PET/CT images via GloD-LoATUNet. (February 2023)

• Record Type: Journal Article
• Authors: Yue, Yaoting; Li, Nan; Zhang, Gaobo; Zhu, Zhibin; Liu, Xin; Song, Shaoli; Ta, Dean
• Is Part Of: Computer methods and programs in biomedicine. Volume 229(2023)
• Publication Date: 2023-02
• Subjects: Esophageal gross tumor volume -- Segmentation -- Transformer -- PET/CT; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107266
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: For two-dimensional esophageal gross tumor volume segmentation, we first introduce the attention transformer-based idea to design an effective model GloD-LoATUNet. GloD-LoATUNet has a remarkable representation learning capability to model localized information and long-range dependencies, excelling at the prediction of small and variable esophageal tumors. GloD-LoATUNet achieves superior performance than the convolution, attention-based convolution, and transformer-based comparative networks, opening a new trial for the three-dimensional segmentation of esophageal gross tumor volume in the future. Abstract: Background and objective: For esophageal squamous cell carcinoma, radiotherapy is one of the primary treatments. During the planning before radiotherapy, the intractable task is to precisely delineate the esophageal gross tumor volume (GTV) on medical images. In current clinical practice, the manual delineation suffers from high intra- and inter-rater variability, while also exhausting the oncologists on a treadmill. There is an urgent demand for effective computer-aided automatic segmentation methods. To this end, we designed a novel deep network, dubbed as GloD-LoATUNet. Methods: GloD-LoATUNet follows the effective U-shape structure. On the contractile path, the global deformable dense attention transformer (GloDAT), local attention transformer (LoAT), and convolution blocks are integrated to model long-range dependencies and localized information. On the center bridge and the expanding path, convolution blocks are adopted to upsample the extracted representations for pixel-wise semantic prediction. Between the peer-to-peer counterparts, enhanced skip connections are built to compensate for the lost spatial information and dependencies. By exploiting complementary strengths of the GloDAT, LoAT, and convolution, GloD-LoATUNet has remarkable representation learning capabilities, performing well in the prediction of the small and variable esophageal GTV. Results: The proposed approach was validated in the clinical positron emission tomography/computed tomography (PET/CT) cohort. For 4 different data partitions, we report the Dice similarity coefficient (DSC), Hausdorff distance (HD), and Mean surface distance (MSD) as: 0.83±0.13, 4.88±9.16 mm, and 1.40±4.11 mm ; 0.84±0.12, 6.89±12.04 mm, and 1.18±3.02 mm ; 0.84±0.13, 3.89±7.64 mm, and 1.28±3.68 mm ; 0.86±0.09, 3.71±4.79 mm, and 0.90±0.37 mm ; respectively. The predicted contours present a desirable consistency with the ground truth. Conclusions: The inspiring results confirm the accuracy and generalizability of the proposed model, demonstrating the potential for automatic segmentation of esophageal GTV in clinical practice.