CASIA OpenIR  > 中国科学院分子影像重点实验室
Deep learning radiomics of dual-modality ultrasound images for hierarchical diagnosis of unexplained cervical lymphadenopathy
Zhu,Yangyang1,2; Meng,Zheling2,3; Fan,Xiao1; Duan,Yin4; Jia,Yingying5; Dong,Tiantian1; Wang,Yanfang1; Song,Juan5; Tian,Jie2,3,6; Wang,Kun2,3; Nie,Fang1,7,8
Source PublicationBMC Medicine
2022-08-26
Volume20Issue:1
Corresponding AuthorWang,Kun(kun.wang@ia.ac.cn) ; Nie,Fang(ery_nief@lzu.edu.cn)
AbstractAbstractBackgroundAccurate diagnosis of unexplained cervical lymphadenopathy (CLA) using medical images heavily relies on the experience of radiologists, which is even worse for CLA patients in underdeveloped countries and regions, because of lack of expertise and reliable medical history. This study aimed to develop a deep learning (DL) radiomics model based on B-mode and color Doppler ultrasound images for assisting radiologists to improve their diagnoses of the etiology of unexplained CLA.MethodsPatients with unexplained CLA who received ultrasound examinations from three hospitals located in underdeveloped areas of China were retrospectively enrolled. They were all pathologically confirmed with reactive hyperplasia, tuberculous lymphadenitis, lymphoma, or metastatic carcinoma. By mimicking the diagnosis logic of radiologists, three DL sub-models were developed to achieve the primary diagnosis of benign and malignant, the secondary diagnosis of reactive hyperplasia and tuberculous lymphadenitis in benign candidates, and of lymphoma and metastatic carcinoma in malignant candidates, respectively. Then, a CLA hierarchical diagnostic model (CLA-HDM) integrating all sub-models was proposed to classify the specific etiology of each unexplained CLA. The assistant effectiveness of CLA-HDM was assessed by comparing six radiologists between without and with using the DL-based classification and heatmap guidance.ResultsA total of 763 patients with unexplained CLA were enrolled and were split into the training cohort (n=395), internal testing cohort (n=171), and external testing cohorts 1 (n=105) and 2 (n=92). The CLA-HDM for diagnosing four common etiologies of unexplained CLA achieved AUCs of 0.873 (95% CI: 0.838–0.908), 0.837 (95% CI: 0.789–0.889), and 0.840 (95% CI: 0.789–0.898) in the three testing cohorts, respectively, which was systematically more accurate than all the participating radiologists. With its assistance, the accuracy, sensitivity, and specificity of six radiologists with different levels of experience were generally improved, reducing the false-negative rate of 2.2–10% and the false-positive rate of 0.7–3.1%.ConclusionsMulti-cohort testing demonstrated our DL model integrating dual-modality ultrasound images achieved accurate diagnosis of unexplained CLA. With its assistance, the gap between radiologists with different levels of experience was narrowed, which is potentially of great significance for benefiting CLA patients in underdeveloped countries and regions worldwide.
KeywordDeep learning Cervical lymphadenopathy Ultrasound Reactive hyperplasia Tuberculous lymphadenitis Lymphoma Metastatic carcinoma
DOI10.1186/s12916-022-02469-z
Language英语
WOS IDBMC:10.1186/s12916-022-02469-z
PublisherBioMed Central
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/49853
Collection中国科学院分子影像重点实验室
Corresponding AuthorWang,Kun; Nie,Fang
Affiliation1.Lanzhou University Second Hospital, Lanzhou University; Ultrasound Medical Center
2.CAS Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences
3.University of Chinese Academy of Sciences; School of Artificial Intelligence
4.Gansu Provincial Cancer Hospital; Department of Ultrasound
5.People’s Hospital of Ningxia Hui Autonomous Region; Department of Ultrasound
6.Beihang University; Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering
7.Gansu Province Clinical Research Center for Ultrasonography
8.Gansu Province Medical Engineering Research Center for Intelligence Ultrasound
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhu,Yangyang,Meng,Zheling,Fan,Xiao,et al. Deep learning radiomics of dual-modality ultrasound images for hierarchical diagnosis of unexplained cervical lymphadenopathy[J]. BMC Medicine,2022,20(1).
APA Zhu,Yangyang.,Meng,Zheling.,Fan,Xiao.,Duan,Yin.,Jia,Yingying.,...&Nie,Fang.(2022).Deep learning radiomics of dual-modality ultrasound images for hierarchical diagnosis of unexplained cervical lymphadenopathy.BMC Medicine,20(1).
MLA Zhu,Yangyang,et al."Deep learning radiomics of dual-modality ultrasound images for hierarchical diagnosis of unexplained cervical lymphadenopathy".BMC Medicine 20.1(2022).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhu,Yangyang]'s Articles
[Meng,Zheling]'s Articles
[Fan,Xiao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu,Yangyang]'s Articles
[Meng,Zheling]'s Articles
[Fan,Xiao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu,Yangyang]'s Articles
[Meng,Zheling]'s Articles
[Fan,Xiao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.