Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec;46(4):1643-1658.
doi: 10.1007/s13246-023-01327-3. Epub 2023 Nov 1.

Condition control training-based ConVMLP-ResU-Net for semantic segmentation of esophageal cancer in 18F-FDG PET/CT images

Affiliations

Condition control training-based ConVMLP-ResU-Net for semantic segmentation of esophageal cancer in 18F-FDG PET/CT images

Yaoting Yue et al. Phys Eng Sci Med. 2023 Dec.

Abstract

The precise delineation of esophageal gross tumor volume (GTV) on medical images can promote the radiotherapy effect of esophagus cancer. This work is intended to explore effective learning-based methods to tackle the challenging auto-segmentation problem of esophageal GTV. By employing the progressive hierarchical reasoning mechanism (PHRM), we devised a simple yet effective two-stage deep framework, ConVMLP-ResU-Net. Thereinto, the front-end ConVMLP integrates convolution (ConV) and multi-layer perceptrons (MLP) to capture localized and long-range spatial information, thus making ConVMLP excel in the location and coarse shape prediction of esophageal GTV. According to the PHRM, the front-end ConVMLP should have a strong generalization ability to ensure that the back-end ResU-Net has correct and valid reasoning. Therefore, a condition control training algorithm was proposed to control the training process of ConVMLP for a robust front end. Afterward, the back-end ResU-Net benefits from the yielded mask by ConVMLP to conduct a finer expansive segmentation to output the final result. Extensive experiments were carried out on a clinical cohort, which included 1138 pairs of 18F-FDG positron emission tomography/computed tomography (PET/CT) images. We report the Dice similarity coefficient, Hausdorff distance, and Mean surface distance as 0.82 ± 0.13, 4.31 ± 7.91 mm, and 1.42 ± 3.69 mm, respectively. The predicted contours visually have good agreements with the ground truths. The devised ConVMLP is apt at locating the esophageal GTV with correct initial shape prediction and hence facilitates the finer segmentation of the back-end ResU-Net. Both the qualitative and quantitative results validate the effectiveness of the proposed method.

Keywords: Automatic segmentation; ConVMLP-ResU-Net; Condition control training algorithm; Esophageal gross tumor volume; PET/CT.

PubMed Disclaimer

References

    1. Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, Bray F (2021) Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71(2021):209–249 - DOI - PubMed
    1. Jin D, Guo D, Ho TY, Harrison AP, Xiao J, Tseng CK, Lu L (2021) DeepTarget: gross tumor and clinical target volume segmentation in esophageal cancer radiotherapy. Med Image Anal 68:101909 - DOI - PubMed
    1. Lu J, Sun XD, Yang X, Tang XY, Qin Q, Zhu HC, Cheng HY, Sun XC (2016) Impact of PET/CT on radiation treatment in patients with esophageal cancer: a systematic review. Crit Rev Oncol Hemat 107:128–137 - DOI
    1. Lei T, Wang R, Wan Y, Zhang B, Meng H, Nandi AK (2020) Medical image segmentation using deep learning a survey, arXiv:2009.13120
    1. Du X, Xu X, Liu H, Li S (2021) TSU-net: two-stage multi-scale cascade and multi-field fusion U-net for right ventricular segmentation. Comput Med Imaging Graph 93:101971 - DOI - PubMed

MeSH terms

Substances

LinkOut - more resources