DataVXAdvanced SciencePaper
journal article·2025-12Open access

Cytological Classification Diagnosis for Thyroid Nodules via Multimodal Model Deep Learning

Yuanzheng Lou, Yongjian Su, Haoda Lu, Wencai Li, Weihua Yin, Shengnan Li, Huobiao Zhu, Kok Haur Ong, Gang Chen, Yong Jiang, Yifei Liu, Shenglei Li, Manchun Yang, Zhengyu Zhang, Xiaoyan Wang, Xiaohui Zhu, Xinmi Huo, Longjie Li, Chao Wang, Nanyan Zhang, Weijun Pan, Bin Shang, Xudan Yang, Yongqiang Zhu, Xiaolin Liu, Weimiao Yu, Xiuwu Bian, Yanqing Ding

Advanced Science· Volume 12· Issue 48
Publisher pageOpen full text
Source abstract

Abstract

Abstract The rising prevalence of thyroid nodules is straining limited cytopathology resources, resulting in excessive overdiagnosis and overtreatment with significant patient and healthcare consequences. To address this, AI‐TFNA is developed, a robust artificial intelligence platform leveraging extensive clinical data to enhance diagnostic accuracy and clinical efficiency. A total of 20,803 thyroid samples are collected from seven medical centers across different regions in China. Of these, 4,421 thyroid fine‐needle aspiration (TFNA) samples from three hospitals are used to train AI‐TFNA, ensuring strong generalizability across diverse clinical settings. For the internal validation, AI‐TFNA demonstrates exceptional performance: the overall accuracy of TBS I is 93.27%, the sensitivity of TBS V and TBS VI reaches 85.37% and 83.78%, while the specificity of TBS II is 97.13%. Consistent results are observed in an external cohort of 2,153 samples, demonstrating robust generalizability. The incorporation of BRAF mutation data into AI‐TFNA and the development of a multi‐modal model further improve precision by significantly improving the differentiation between benign and malignant thyroid nodules. Image Appearance Migration (IAM) is an innovative technique that substantially improves cross‐institutional model generalizability, increasing AI‐TFNA sensitivity by 1.90% and specificity by 8.12%. AI‐TFNA offers rapid, reliable decision support, advancing thyroid nodule diagnostics.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: AI in cancer detection · Thyroid Cancer Diagnosis and Treatment · Radiomics and Machine Learning in Medical Imaging

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Pathology Nanfang Hospital and School of Basic Medical Sciences Southern Medical University Guangzhou 510515 China

College of Bioengineering Chongqing University Chongqing 400030 China

Institute of Pathology & Southwest Cancer Center the First Affiliated Hospital (Southwest Hospital) and School of Basic Medical Sciences Army Medical University (Third Military Medical University), and the Key Laboratory of Tumor Immunopathology the Ministry of Education (Third Military Medical University) Chongqing 400038 China

Chongqing Institute of Advanced Pathology Jinfeng Laboratory Chongqing 400041 China

Guangzhou F.Q. PATHOTECH Co., Ltd Guangzhou 510515 China

Guangzhou Huayin Health Medical Group Co., Ltd Guangzhou 510663 China

Intelligent Digital and Molecular Pathology (IDMP) Lab Bioinformatics Institute (BII) Agency of Science Technology and Research (A*STAR) Singapore 138671 Singapore

Department of Pathology The First Affiliated Hospital of Zhengzhou University No. 1 Jian She Dong Avenue Zhengzhou 450002 China

Department of Pathology Peking University Shenzhen Hospital Shenzhen 518036 China

Department of Pathology Clinical Oncology School of Fujian Medical University Fujian Cancer Hospital Fuzhou Fujian 35000 China

Department of Pathology West China Hospital of Sichuan University Chengdu 610044 China

Department of Pathology Affiliated Hospital of Nantong University and Medical School of Nantong University Nantong 226007 China

Guangdong Province Key Laboratory of Molecular Tumor Pathology Guangzhou 510515 China

Department of Pathology Sichuan Provincial People's Hospital School of Medicine University of Electronic Science and Technology of China Chengdu 610072 China

Computational & Molecular Pathology Lab (CMPL) Institute of Molecule and Cell Biology (IMCB) Agency of Science Technology and Research (A*STAR) Singapore 138673 Singapore

Funding

National Natural Science Foundation of China

References (50)

Show source-provided references
1. 10.1016/S2213-8587(22)00035-310.1016/S2213-8587(22)00035-3 ↗
2. 10.1038/s41598-024-77663-510.1038/s41598-024-77663-5 ↗
3. 10.1089/thy.2014.050210.1089/thy.2014.0502 ↗
4. 10.1001/jama.2023.2634810.1001/jama.2023.26348 ↗
5. 10.1097/CM9.000000000000210810.1097/CM9.0000000000002108 ↗
6. 10.3322/caac.2183410.3322/caac.21834 ↗
7. 10.1016/S2214-109X(18)30127-X10.1016/S2214-109X(18)30127-X ↗
8. 10.1016/S0140-6736(23)00020-X10.1016/S0140-6736(23)00020-X ↗
9. 10.1016/S2213-8587(24)00223-710.1016/S2213-8587(24)00223-7 ↗
10. 10.21037/gs.2017.11.1710.21037/gs.2017.11.17 ↗
11. 10.1016/S2213-8587(22)00139-510.1016/S2213-8587(22)00139-5 ↗
12. 10.1097/MED.000000000000081410.1097/MED.0000000000000814 ↗
13. 10.1056/NEJMp140984110.1056/NEJMp1409841 ↗
14. 10.1007/s11427-022-2240-610.1007/s11427-022-2240-6 ↗
15. 10.7189/jogh.14.0413110.7189/jogh.14.04131 ↗
16. 10.1016/j.eprac.2021.09.00610.1016/j.eprac.2021.09.006 ↗
17. 10.2991/jegh.k.191008.00110.2991/jegh.k.191008.001 ↗
18. 10.1089/thy.2015.002010.1089/thy.2015.0020 ↗
19. 10.1017/S002221511600057810.1017/S0022215116000578 ↗
20. Ali S. Z. · Thyroid · 2023 · 33 · 1039
21. 10.1530/ETJ-23-006710.1530/ETJ-23-0067 ↗
22. 10.1001/jamanetworkopen.2019.430810.1001/jamanetworkopen.2019.4308 ↗
23. 10.1038/s41467-023-43749-310.1038/s41467-023-43749-3 ↗
24. 10.1038/s41591-022-02134-110.1038/s41591-022-02134-1 ↗
25. 10.1016/j.ccell.2023.08.00210.1016/j.ccell.2023.08.002 ↗
26. 10.1001/jama.2017.1458510.1001/jama.2017.14585 ↗
27. 10.1016/j.modpat.2023.10021610.1016/j.modpat.2023.100216 ↗
28. 10.1038/s41467-021-23913-310.1038/s41467-021-23913-3 ↗
29. 10.1016/S2589-7500(21)00041-810.1016/S2589-7500(21)00041-8 ↗
30. 10.1002/cncy.2266910.1002/cncy.22669 ↗
31. 10.4103/jpi.jpi_43_1810.4103/jpi.jpi_43_18 ↗
32. 10.1016/j.media.2020.10181410.1016/j.media.2020.101814 ↗
33. 10.3390/cancers1315389110.3390/cancers13153891 ↗
34. 10.1016/S2589-7500(24)00085-210.1016/S2589-7500(24)00085-2 ↗
35. 10.1007/978-3-642-15948-0_810.1007/978-3-642-15948-0_8 ↗
36. 10.1038/s43856-024-00502-110.1038/s43856-024-00502-1 ↗
37. M.Macenko M.Niethammer J. S.Marron D.Borland N. E.Thomas presented at2009 IEEE Int. Symp. on Biomedical Imaging: From Nano to Macro Boston MA USA June 2009.
38. 10.1109/38.94662910.1109/38.946629 ↗
39. Z.Liu Y.Lin Y.Cao H.Hu Y.Wei Z.Zhang S.Lin B.Guo presented atIEEE/CVF Int. Conf. on Computer Vision (ICCV) Montreal Canada October 2021.
40. K.He X.Zhang S.Ren J.Sun presented at2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) Las Vegas NV USA June 2016.
41. 10.1159/00054539110.1159/000545391 ↗
42. 10.3390/bioengineering1203029310.3390/bioengineering12030293 ↗
43. 10.1016/j.compmedimag.2025.10249910.1016/j.compmedimag.2025.102499 ↗
44. 10.1038/s41551-020-00682-w10.1038/s41551-020-00682-w ↗
45. 10.1038/s41591-024-02857-310.1038/s41591-024-02857-3 ↗
46. 10.1038/s41591-024-02856-410.1038/s41591-024-02856-4 ↗
47. 10.1038/s41586-024-07894-z10.1038/s41586-024-07894-z ↗
48. Vaswani A. · Adv. Neural Inf. Proces. Syst. · 2017 · 30
49. 10.1007/s41095-023-0364-210.1007/s41095-023-0364-2 ↗
50. 10.1145/2939672.293978510.1145/2939672.2939785 ↗