AUTHOR=Liu Yajing , Chen Jifan , Zhang Chao , Li Qunying , Zhou Hang , Zeng Yiqing , Zhang Ying , Li Jia , Xv Wen , Li Wencun , Zhu Jianing , Zhao Yanan , Chen Qin , Huang Yi , Li Hongming , Huang Ying , Yang Gaoyi , Huang Pintong 

TITLE=Ultrasound-Based Radiomics Can Classify the Etiology of Cervical Lymphadenopathy: A Multi-Center Retrospective Study

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.856605

DOI=10.3389/fonc.2022.856605

ISSN=2234-943X

ABSTRACT=Medical diagnostic imaging is essential for the differential diagnosis of cervical lymphadenopathy. Here, we develop an ultrasonic radiomics method for accurately differentiating cervical lymph nodes tuberculosis (LNTB), cervical lymphoma, reactive lymph nodes hyperplasia, and metastatic lymph nodes especially in the multi-operator, cross-machine, multicenter context. The inter-observer and intra-observer consistency of radiomics parameters from region of interest were 0.8245 and 0.9228, respectively. The radiomics model showed good and repeatable diagnostic performance for multiple classification diagnosis of cervical lymphadenopathy, especially in LNTB (AUC: 0.673, 0.662, and 0.626) and cervical lymphoma (AUC: 0.623, 0.644, and 0.602); in the whole set, training set, and test set, respectively. However, the diagnostic performance of lymphadenopathy among skilled radiologists was varied (Kappa coefficient: 0.108, p < 0.001*). The diagnostic performance of radiomics is comparable and more reproducible compared with skilled radiologists. Our study offers a more comprehensive method for differentiating LNTB, cervical lymphoma, reactive lymph nodes hyperplasia, and metastatic LN.