Large-scale long-tailed disease diagnosis on radiology images

Qiaoyu Zheng, Weike Zhao, Chaoyi Wu, Xiaoman Zhang, Lisong Dai, Hengyu Guan, Yuehua Li, Ya Zhang, Yanfeng Wang () and Weidi Xie ()
Additional contact information
Qiaoyu Zheng: Shanghai Jiao Tong University
Weike Zhao: Shanghai Jiao Tong University
Chaoyi Wu: Shanghai Jiao Tong University
Xiaoman Zhang: Shanghai Jiao Tong University
Lisong Dai: Shanghai Jiao Tong University
Hengyu Guan: Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine
Yuehua Li: Shanghai Jiao Tong University
Ya Zhang: Shanghai Jiao Tong University
Yanfeng Wang: Shanghai Jiao Tong University
Weidi Xie: Shanghai Jiao Tong University

Nature Communications, 2024, vol. 15, issue 1, 1-16

Abstract: Abstract Developing a generalist radiology diagnosis system can greatly enhance clinical diagnostics. In this paper, we introduce RadDiag, a foundational model supporting 2D and 3D inputs across various modalities and anatomies, using a transformer-based fusion module for comprehensive disease diagnosis. Due to patient privacy concerns and the lack of large-scale radiology diagnosis datasets, we utilize high-quality, clinician-reviewed radiological images available online with diagnosis labels. Our dataset, RP3D-DiagDS, contains 40,936 cases with 195,010 scans covering 5568 disorders (930 unique ICD-10-CM codes). Experimentally, our RadDiag achieves 95.14% AUC on internal evaluation with the knowledge-enhancement strategy. Additionally, RadDiag can be zero-shot applied or fine-tuned to external diagnosis datasets sourced from various medical centers, demonstrating state-of-the-art results. In conclusion, we show that publicly shared medical data on the Internet is a tremendous and valuable resource that can potentially support building strong models for image understanding in healthcare.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-54424-6 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:15:y:2024:i:1:d:10.1038_s41467-024-54424-6

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

DOI: 10.1038/s41467-024-54424-6

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 ().