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
Randomized Controlled Trial
. 2022 Oct;148(10):2773-2780.
doi: 10.1007/s00432-022-04047-5. Epub 2022 May 13.

Deep learning combined with radiomics for the classification of enlarged cervical lymph nodes

Wentao Zhang #  1 , Jian Peng #  2 , Shan Zhao  1 , Wenli Wu  1 , Junjun Yang  3 , Junyong Ye  3 , Shengsheng Xu  4
Affiliations
Randomized Controlled Trial

Deep learning combined with radiomics for the classification of enlarged cervical lymph nodes

Wentao Zhang et al. J Cancer Res Clin Oncol. 2022 Oct.

Abstract

Purpose: To investigate the application of deep learning combined with traditional radiomics methods for classifying enlarged cervical lymph nodes.

Methods: The clinical and computed tomography (CT) imaging data of 276 patients with enlarged cervical lymph nodes (150 with lymph-node metastasis, 65 with lymphoma, and 61 with benign lymphadenopathy) who were treated at the hospital from January 2015 to January 2021 were retrospectively analysed. The patients were randomly divided into a training group and a test group at a ratio of 8:2. The radiomics features were extracted using one-by-one convolution and neural network activation, filtered with the least absolute shrinkage and selection operator (LASSO) model, and used to construct a discrimination model with PyTorch. Then, the performance of the model was compared with the radiologists' diagnostic performance. The neural network model was evaluated using the area under the receiver-operator characteristic curve (AUC), and the accuracy, sensitivity, and specificity were analysed.

Results: A total of 102 features, comprising five traditional radiomic features and 97 deep learning features, were selected with LASSO and used to construct a discrimination model, which achieved a total accuracy of 87.50%. The AUC value, specificity, and sensitivity were, respectively, 0.92, 92.30%, and 90.00% for metastatic lymph nodes, 0.87, 95.45%, and 83.33% for benign lymphadenopathy, and 0.88, 90.47%, and 85.71% for lymphoma. The accuracies of the radiologists' diagnoses were 62.68% and 62.68%. The diagnostic performance of the model was significantly different from that of the radiologists (p < 0.05).

Conclusion: CT-based deep learning combined with the traditional radiomics methods has a high diagnostic value for the classification of cervical enlarged lymph nodes.

Keywords: Cervical lymph nodes; Classification; Deep learning; Diagnosis; Radiomics; Tomography; X-ray computed.

PubMed Disclaimer

Conflict of interest statement

No authors have any conflicts of interest to disclose.

Figures

Fig. 1
Fig. 1
①–③ Respective ROIs of lymphoma (axial image), metastatic lymph nodes (from papillary thyroid carcinoma, sagittal image) and benign lymph nodes (reactive hyperplasia, coronal image) in the left neck. Note that images were obtained in all three planes for each type of lymph node, but only one plane is shown for each. Ⓐ–Ⓒ Respective three-dimensional images after fusion of the ROIs corresponding to the lesions in ①–③
Fig. 2
Fig. 2
ROC curves of the established prediction model for diagnosing metastatic lymph nodes, benign lymph nodes, and lymphoma
Fig. 3
Fig. 3
Predictive confidence of the classification model
See this image and copyright information in PMC

References

    1. Bayanati H, Thornhill RE, Souza CA et al (2015) Quantitative CT texture and shape analysis: can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer? Eur Radiol 25(2):480–487. 10.1007/s00330-014-3420-6 - PubMed
    1. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563–577. 10.1148/radiol.2015151169 - PMC - PubMed
    1. Kann BH, Hicks DF, Payabvash S et al (2020) Multi-institutional validation of deep learning for pretreatment identification of extranodal extension in head and neck squamous cell carcinoma. J Clin Oncol 38(12):1304–1311. 10.1200/JCO.19.02031 - PubMed
    1. Kuno H, Garg N, Qureshi MM et al (2019) CT texture analysis of cervical lymph nodes on contrast-enhanced [(18)F] FDG-PET/CT images to differentiate nodal metastases from reactive lymphadenopathy in HIV-positive patients with head and neck squamous cell carcinoma. AJNR Am J Neuroradiol 40(3):543–550. 10.3174/ajnr.A5974 - PMC - PubMed
    1. Le WT, Maleki F, Romero FP et al (2020) Overview of machine learning: part 2 deep learning for medical image analysis. Neuroimaging Clin North Am 30(4):417. 10.1016/j.nic.2020.06.003 - PubMed

Publication types

MeSH terms