Improving AI models for rare thyroid cancer subtype by text guided diffusion models
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...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-59478-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849326658694152192 |
|---|---|
| author | 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 Hui Lu |
| author_facet | 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 Hui Lu |
| author_sort | Fang Dai |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-fb34ee94385242a6b84a610b451c2cf2 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-fb34ee94385242a6b84a610b451c2cf22025-08-20T03:48:06ZengNature PortfolioNature Communications2041-17232025-05-0116111610.1038/s41467-025-59478-8Improving AI models for rare thyroid cancer subtype by text guided diffusion modelsFang Dai0Siqiong Yao1Min Wang2Yicheng Zhu3Xiangjun Qiu4Peng Sun5Cheng Qiu6Jisheng Yin7Guangtai Shen8Jingjing Sun9Maofeng Wang10Yun Wang11Zheyu Yang12Jianfeng Sang13Xiaolei Wang14Fenyong Sun15Wei Cai16Xingcai Zhang17Hui Lu18Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong UniversitySJTU-Yale Joint Center of Biostatistics and Data Science, Technical Center for Digital Medicine, National Center for Translational Medicine, Shanghai Jiao Tong UniversityDepartment of Critical Care Medicine, Jiuquan Hospital of Shanghai General Hospital, Shanghai Jiaotong University School of MedicineDepartment of Ultrasound, Pudong New Area People’s Hospital Affiliated to Shanghai University of Medicine and Health SciencesDepartment of Automation, Tsinghua UniversityDepartment of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong UniversityMedical college, Nantong UniversityShcool of Artificial Intelligence, University of Chinese Academy of sciencesXin’an League People’s HospitalDepartment of Ultrasound, Shanghai Fourth People’s Hospital Affiliated to Tongji UniversityDepartment of Biomedical Sciences Laboratory, Affiliated Dongyang Hospital of Wenzhou Medical UniversityDepartment of Hepatobiliary pancreatic center, Xuzhou City Central HospitalDepartment of General Surgery, Ruijin Hospital, Shanghai Jiaotong University School of medicineNanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical SchoolDepartment of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong UniversityDepartment of Clinical Laboratory Medicine, Shanghai Tenth People’s Hospital, School of Medicine, Tongji UniversityDepartment of General Surgery, Ruijin Hospital, Shanghai Jiaotong University School of medicineWorld Tea OrganizationDepartment of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong UniversityAbstract 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.https://doi.org/10.1038/s41467-025-59478-8 |
| spellingShingle | 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 Hui Lu Improving AI models for rare thyroid cancer subtype by text guided diffusion models Nature Communications |
| title | Improving AI models for rare thyroid cancer subtype by text guided diffusion models |
| title_full | Improving AI models for rare thyroid cancer subtype by text guided diffusion models |
| title_fullStr | Improving AI models for rare thyroid cancer subtype by text guided diffusion models |
| title_full_unstemmed | Improving AI models for rare thyroid cancer subtype by text guided diffusion models |
| title_short | Improving AI models for rare thyroid cancer subtype by text guided diffusion models |
| title_sort | improving ai models for rare thyroid cancer subtype by text guided diffusion models |
| url | https://doi.org/10.1038/s41467-025-59478-8 |
| work_keys_str_mv | AT fangdai improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT siqiongyao improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT minwang improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT yichengzhu improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT xiangjunqiu improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT pengsun improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT chengqiu improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT jishengyin improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT guangtaishen improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT jingjingsun improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT maofengwang improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT yunwang improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT zheyuyang improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT jianfengsang improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT xiaoleiwang improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT fenyongsun improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT weicai improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT xingcaizhang improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels AT huilu improvingaimodelsforrarethyroidcancersubtypebytextguideddiffusionmodels |