Objective To systematically review the research progress of artificial intelligence (AI) combined with multimodal data in the field of malignant risk assessment for thyroid nodules (TN), analyze current technological application bottlenecks and future development directions. Methods Relevant literatures on the application of AI combined with multimodal data in TN risk assessment in recent years were retrieved and reviewed. Results AI, by integrating multimodal data such as ultrasound, cytopathology, and molecular markers, can effectively address the limitations of subjectivity in traditional ultrasound evaluation, uncertainty results of fine needle aspiration biopsy and diagnostic blind spots associated with single molecular markers. However, current research still faces challenges including insufficient generalization ability of small sample, lack of clinical interpretability in black-box algorithms, and insufficient standardization of multimodal data. To tackle these challenges, strategies such as promoting federated learning for multi-center data sharing, establishing interpretable AI integrated with clinical diagnostic pathways, and optimizing deep integration of liquid biopsy with AI provide new directions for overcoming existing obstacles. Conclusion AI combined with multimodal data offers an innovative technical pathway for TN malignancy risk assessment, which is expected to address inherent limitations of traditional diagnostic models and facilitate comprehensive precision management from risk stratification to prognostic monitoring.
Citation：
JIN Ling, MU Yongwei, ZHAO Chengboya, WANG Xiaoxuan, YANG Xiaokun. Research progress on artificial intelligence combined with multimodal data in malignancy risk assessment of thyroid nodules. CHINESE JOURNAL OF BASES AND CLINICS IN GENERAL SURGERY, 2026, 33(6): 830-837. doi: 10.7507/1007-9424.202603074
Copy
Copyright ? the editorial department of CHINESE JOURNAL OF BASES AND CLINICS IN GENERAL SURGERY of West China Medical Publisher. All rights reserved
| 1. |
|
| 2. |
|
| 3. |
|
| 4. |
|
| 5. |
|
| 6. |
|
| 7. |
|
| 8. |
|
| 9. |
Shen H, Huang Y, Yan W, et al. Noninvasive deep learning system for preoperative diagnosis of follicular-like thyroid neoplasms using ultrasound images: a multicenter, retrospective study. Ann Surg, 2025. doi: 10.1097/SLA.0000000000006841.
|
| 10. |
|
| 11. |
|
| 12. |
|
| 13. |
|
| 14. |
|
| 15. |
|
| 16. |
|
| 17. |
|
| 18. |
|
| 19. |
|
| 20. |
|
| 21. |
|
| 22. |
Ferraz C. Molecular testing for thyroid nodules: where are we now? Rev Endocr Metab Disord, 2024, 25(1): 149-159.
|
| 23. |
|
| 24. |
|
| 25. |
|
| 26. |
|
| 27. |
|
| 28. |
|
| 29. |
|
| 30. |
|
| 31. |
|
| 32. |
|
| 33. |
Keatmanee C, Songsaeng D, Klabwong S, et al. Enhancing weakly supervised data augmentation networks for thyroid nodule assessment using traditional and doppler ultrasound images. Comput Biol Med, 2025, 196(Pt A): 110553. doi: 10.1016/j.compbiomed.2025.110553.
|
| 34. |
|
| 35. |
|
| 36. |
|
| 37. |
|
| 38. |
|
| 39. |
|
| 40. |
|
| 41. |
|
| 42. |
|
| 43. |
|
| 44. |
|
| 45. |
|
| 46. |
|
| 47. |
|
| 48. |
|
| 49. |
|
| 50. |
|
| 51. |
|
| 52. |
|
| 53. |
|
| 54. |
|
| 55. |
|
| 56. |
|
| 57. |
Radhachandran A, Kinzel A, Chen J, et al. A multitask approach for automated detection and segmentation of thyroid nodules in ultrasound images. Comput Biol Med, 2024, 170: 107974. doi: 10.1016/j.compbiomed.2024.107974.
|
| 58. |
|
| 59. |
|
| 60. |
|
| 61. |
|
| 62. |
|
| 63. |
|
| 64. |
|
| 65. |
|
| 66. |
|
| 67. |
|
| 68. |
|
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9. Shen H, Huang Y, Yan W, et al. Noninvasive deep learning system for preoperative diagnosis of follicular-like thyroid neoplasms using ultrasound images: a multicenter, retrospective study. Ann Surg, 2025. doi: 10.1097/SLA.0000000000006841.
- 10.
- 11.
- 12.
- 13.
- 14.
- 15.
- 16.
- 17.
- 18.
- 19.
- 20.
- 21.
- 22. Ferraz C. Molecular testing for thyroid nodules: where are we now? Rev Endocr Metab Disord, 2024, 25(1): 149-159.
- 23.
- 24.
- 25.
- 26.
- 27.
- 28.
- 29.
- 30.
- 31.
- 32.
- 33. Keatmanee C, Songsaeng D, Klabwong S, et al. Enhancing weakly supervised data augmentation networks for thyroid nodule assessment using traditional and doppler ultrasound images. Comput Biol Med, 2025, 196(Pt A): 110553. doi: 10.1016/j.compbiomed.2025.110553.
- 34.
- 35.
- 36.
- 37.
- 38.
- 39.
- 40.
- 41.
- 42.
- 43.
- 44.
- 45.
- 46.
- 47.
- 48.
- 49.
- 50.
- 51.
- 52.
- 53.
- 54.
- 55.
- 56.
- 57. Radhachandran A, Kinzel A, Chen J, et al. A multitask approach for automated detection and segmentation of thyroid nodules in ultrasound images. Comput Biol Med, 2024, 170: 107974. doi: 10.1016/j.compbiomed.2024.107974.
- 58.
- 59.
- 60.
- 61.
- 62.
- 63.
- 64.
- 65.
- 66.
- 67.
- 68.
1/5
WeChat