Improving AI models for rare thyroid cancer subtype by text guided diffusion models

Fang Dai, Siqiong Yao (), Min Wang, Yicheng Zhu, Xiangjun Qiu, Peng Sun, Cheng Qiu, Jisheng Yin, Guangtai Shen, Jingjing Sun, Maofeng Wang, Yun Wang, Zheyu Yang, Jianfeng Sang, Xiaolei Wang, Fenyong Sun (), Wei Cai (), Xingcai Zhang () and Hui Lu ()
Additional contact information
Fang Dai: Shanghai Jiao Tong University
Siqiong Yao: Shanghai Jiao Tong University
Min Wang: Shanghai Jiaotong University School of Medicine
Yicheng Zhu: Pudong New Area People’s Hospital Affiliated to Shanghai University of Medicine and Health Sciences
Xiangjun Qiu: Tsinghua University
Peng Sun: Shanghai Jiao Tong University
Cheng Qiu: Nantong University
Jisheng Yin: University of Chinese Academy of sciences
Guangtai Shen: Xin’an League People’s Hospital
Jingjing Sun: Shanghai Fourth People’s Hospital Affiliated to Tongji University
Maofeng Wang: Affiliated Dongyang Hospital of Wenzhou Medical University
Yun Wang: Xuzhou City Central Hospital
Zheyu Yang: Shanghai Jiaotong University School of medicine
Jianfeng Sang: The Affiliated Hospital of Nanjing University Medical School
Xiaolei Wang: Shanghai Jiao Tong University
Fenyong Sun: Tongji University
Wei Cai: Shanghai Jiaotong University School of medicine
Xingcai Zhang: World Tea Organization
Hui Lu: Shanghai Jiao Tong University

Nature Communications, 2025, vol. 16, issue 1, 1-16

Abstract: Abstract Artificial intelligence applications in oncology imaging often struggle with diagnosing rare tumors. We identify significant gaps in detecting uncommon thyroid cancer types with ultrasound, where scarce data leads to frequent misdiagnosis. Traditional augmentation strategies do not capture the unique disease variations, hindering model training and performance. To overcome this, we propose a text-driven generative method that fuses clinical insights with image generation, producing synthetic samples that realistically reflect rare subtypes. In rigorous evaluations, our approach achieves substantial gains in diagnostic metrics, surpasses existing methods in authenticity and diversity measures, and generalizes effectively to other private and public datasets with various rare cancers. In this work, we demonstrate that text-guided image augmentation substantially enhances model accuracy and robustness for rare tumor detection, offering a promising avenue for more reliable and widespread clinical adoption.

Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-59478-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-59478-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-59478-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().