A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules
Abstract Recognizing the limitations of computer-assisted tools for thyroid nodule diagnosis using static ultrasound images, this study developed a diagnostic tool utilizing dynamic ultrasound video, namely Thyroid Nodules Visualization (TNVis), by leveraging a two-stage deep learning framework that...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01455-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850029112683397120 |
|---|---|
| author | Yahan Zhou Chen Chen Jincao Yao Jiabin Yu Bojian Feng Lin Sui Yuqi Yan Xiayi Chen Yuanzhen Liu Xiao Zhang Hui Wang Qianmeng Pan Weijie Zou Qi Zhang Lu Lin Chenke Xu Shengxing Yuan Qingquan He Xiaofan Ding Ping Liang Vicky Yang Wang Dong Xu |
| author_facet | Yahan Zhou Chen Chen Jincao Yao Jiabin Yu Bojian Feng Lin Sui Yuqi Yan Xiayi Chen Yuanzhen Liu Xiao Zhang Hui Wang Qianmeng Pan Weijie Zou Qi Zhang Lu Lin Chenke Xu Shengxing Yuan Qingquan He Xiaofan Ding Ping Liang Vicky Yang Wang Dong Xu |
| author_sort | Yahan Zhou |
| collection | DOAJ |
| description | Abstract Recognizing the limitations of computer-assisted tools for thyroid nodule diagnosis using static ultrasound images, this study developed a diagnostic tool utilizing dynamic ultrasound video, namely Thyroid Nodules Visualization (TNVis), by leveraging a two-stage deep learning framework that involved three-dimensional (3D) visualization. In this multicenter study, 4569 cases were included for framework development, and data from seven hospitals were employed for diagnostic validation. TNVis achieved a Dice similarity coefficient of 0.90 after internal testing. For the external validation, TNVis significantly improved radiologists’ performance, reaching an AUC of 0.79, compared to their diagnostic performance without the use of TNVis (AUC: 0.66; p < 0.001) and those with partial assistance (AUC: 0.72; p < 0.001). In conclusion, the TNVis-assisted diagnostic strategy not only significantly improves the diagnostic ability of radiologists but also closely imitates their clinical diagnostic procedures and provides them with an objective 3D representation of the nodules for precise and personalized diagnosis and treatment planning. |
| format | Article |
| id | doaj-art-ddbe86d60ca74d7fb68f721805e8fdcd |
| institution | DOAJ |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-ddbe86d60ca74d7fb68f721805e8fdcd2025-08-20T02:59:37ZengNature Portfolionpj Digital Medicine2398-63522025-02-018111110.1038/s41746-025-01455-yA deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodulesYahan Zhou0Chen Chen1Jincao Yao2Jiabin Yu3Bojian Feng4Lin Sui5Yuqi Yan6Xiayi Chen7Yuanzhen Liu8Xiao Zhang9Hui Wang10Qianmeng Pan11Weijie Zou12Qi Zhang13Lu Lin14Chenke Xu15Shengxing Yuan16Qingquan He17Xiaofan Ding18Ping Liang19Vicky Yang Wang20Dong Xu21Center of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesDepartment of Biomedical Sciences, Faculty of Health Sciences, University of MacauDepartment of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesCollege of Information Engineering, China Jiliang UniversityCenter of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesCenter of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesCenter of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesCenter of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesCenter of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesThe First People’s Hospital of Hangzhou Lin’an DistrictDepartment of Ultrasound, Taizhou Campus of Zhejiang Cancer Hospital (Taizhou Cancer Hospital)Department of Ultrasound, Taizhou Campus of Zhejiang Cancer Hospital (Taizhou Cancer Hospital)Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesShaoxing People’s HospitalZhoushan Hospital of Traditional Chinese MedicineAffiliated Hangzhou First People’s Hospital, School of Medicine, Westlake UniversityDepartment of Ultrasonography, Qujing No.1 Hospital, Affiliated Hospital of Kunming Medical UniversityTaizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence, Taizhou Campus of Zhejiang Cancer Hospital (Taizhou Cancer Hospital)Department of Biomedical Sciences, Faculty of Health Sciences, University of MacauDepartment of Ultrasound, Chinese PLA General Hospital, Chinese PLA Medical SchoolCenter of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesCenter of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesAbstract Recognizing the limitations of computer-assisted tools for thyroid nodule diagnosis using static ultrasound images, this study developed a diagnostic tool utilizing dynamic ultrasound video, namely Thyroid Nodules Visualization (TNVis), by leveraging a two-stage deep learning framework that involved three-dimensional (3D) visualization. In this multicenter study, 4569 cases were included for framework development, and data from seven hospitals were employed for diagnostic validation. TNVis achieved a Dice similarity coefficient of 0.90 after internal testing. For the external validation, TNVis significantly improved radiologists’ performance, reaching an AUC of 0.79, compared to their diagnostic performance without the use of TNVis (AUC: 0.66; p < 0.001) and those with partial assistance (AUC: 0.72; p < 0.001). In conclusion, the TNVis-assisted diagnostic strategy not only significantly improves the diagnostic ability of radiologists but also closely imitates their clinical diagnostic procedures and provides them with an objective 3D representation of the nodules for precise and personalized diagnosis and treatment planning.https://doi.org/10.1038/s41746-025-01455-y |
| spellingShingle | Yahan Zhou Chen Chen Jincao Yao Jiabin Yu Bojian Feng Lin Sui Yuqi Yan Xiayi Chen Yuanzhen Liu Xiao Zhang Hui Wang Qianmeng Pan Weijie Zou Qi Zhang Lu Lin Chenke Xu Shengxing Yuan Qingquan He Xiaofan Ding Ping Liang Vicky Yang Wang Dong Xu A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules npj Digital Medicine |
| title | A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules |
| title_full | A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules |
| title_fullStr | A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules |
| title_full_unstemmed | A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules |
| title_short | A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules |
| title_sort | deep learning based ultrasound diagnostic tool driven by 3d visualization of thyroid nodules |
| url | https://doi.org/10.1038/s41746-025-01455-y |
| work_keys_str_mv | AT yahanzhou adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT chenchen adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT jincaoyao adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT jiabinyu adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT bojianfeng adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT linsui adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT yuqiyan adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT xiayichen adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT yuanzhenliu adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT xiaozhang adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT huiwang adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT qianmengpan adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT weijiezou adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT qizhang adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT lulin adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT chenkexu adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT shengxingyuan adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT qingquanhe adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT xiaofanding adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT pingliang adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT vickyyangwang adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT dongxu adeeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT yahanzhou deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT chenchen deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT jincaoyao deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT jiabinyu deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT bojianfeng deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT linsui deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT yuqiyan deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT xiayichen deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT yuanzhenliu deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT xiaozhang deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT huiwang deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT qianmengpan deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT weijiezou deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT qizhang deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT lulin deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT chenkexu deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT shengxingyuan deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT qingquanhe deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT xiaofanding deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT pingliang deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT vickyyangwang deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules AT dongxu deeplearningbasedultrasounddiagnostictooldrivenby3dvisualizationofthyroidnodules |