Deep learning-based automatic scoring models for the disease activity of rheumatoid arthritis based on multimodal ultrasound images

doi:10.1093/rheumatology/kead366

	Deep learning-based automatic scoring models for the disease activity of rheumatoid arthritis based on multimodal ultrasound images
	He, Xuelei 1,2,3; Wang, Ming 1; Zhao, Chenyang 1; Wang, Qian4 ; Zhang, Rui1 ; Liu, Jian5 ; Zhang, Yixiu 1; Qi, Zhenhong 1; Su, Na 1; Wei, Yao 1; Gui, Yang 1; Li, Jianchu 1; Tian, Xinping 4; Zeng, Xiaofeng 4; Jiang, Yuxin 1; Wang, Kun3,7 ; Yang, Meng1,6
发表期刊	RHEUMATOLOGY
ISSN	1462-0324
	2023-07-20
页码	8
通讯作者	Wang, Kun(kun.wang@ia.ac.cn) ; Yang, Meng(yangmeng_pumch@126.com)
摘要	Objectives We aimed to investigate the value of deep learning (DL) models based on multimodal ultrasonographic (US) images to quantify RA activity. Methods Static greyscale (SGS), dynamic greyscale (DGS), static power Doppler (SPD) and dynamic power Doppler (DPD) US images were collected and evaluated by two expert radiologists according to the EULAR-OMERACT Synovitis Scoring system. Four DL models were developed based on the ResNet-type structure, evaluated on two separate test cohorts, and finally compared with the performance of 12 radiologists with different levels of experience. Results In total, 1244 images were used for the model training, and 152 and 354 for testing (cohort 1 and 2, respectively). The best-performing models for the scores of 0/1/2/3 were the DPD, SGS, DGS and SPD models, respectively (Area Under the receiver operating characteristic Curve [AUC] = 0.87/0.95/0.74/0.95; no significant differences). All the DL models provided results comparable to the experienced radiologists on a per-image basis (intraclass correlation coefficient: 0.239-0.756, P < 0.05). The SPD model performed better than the SGS one on test cohort 1 (score of 0/2/3: AUC = 0.82/0.67/0.95 vs 0.66/0.66/0.75, respectively) and test cohort 2 (score of 0: AUC = 0.89 vs 0.81). The dynamic DL models performed better than the static ones in most of the scoring processes and were more accurate than the most of senior radiologists, especially the DPD model. Conclusion DL models based on multimodal US images allow a quantitative and objective assessment of RA activity. Dynamic DL models in particular have potential value in assisting radiologists to improve the accuracy of RA US-based grading.
关键词	deep learning RA activity scoring multimodal ultrasonography
DOI	10.1093/rheumatology/kead366
关键词[WOS]	EULAR RECOMMENDATIONS ; CLINICAL MANAGEMENT ; RELIABILITY ; INTRA ; ULTRASONOGRAPHY ; SYNOVITIS
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[U22A2023] ; National Natural Science Foundation of China[61971447] ; National Natural Science Foundation of China[81421004] ; National Natural Science Foundation of China[81301268] ; Beijing Natural Science Foundation[JQ18023] ; Fundamental Research Funds for the Central Public-interest Scientific Institution of Chinese Academy of Medical Sciences[2021-PT320-002] ; CAMS Innovation Fund for Medical Sciences (CIFMS)[2021-I2M-1005] ; National High Level Hospital Clinical Research Funding[2022-PUMCH-D-002] ; National High Level Hospital Clinical Research Funding[2022-PUMCH-C-009] ; National High Level Hospital Clinical Research Funding[2022-PUMCH-A-225] ; National High Level Hospital Clinical Research Funding[2022-PUMCH-B-064]
项目资助者	National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Fundamental Research Funds for the Central Public-interest Scientific Institution of Chinese Academy of Medical Sciences ; CAMS Innovation Fund for Medical Sciences (CIFMS) ; National High Level Hospital Clinical Research Funding
WOS研究方向	Rheumatology
WOS类目	Rheumatology
WOS记录号	WOS:001051223500001
出版者	OXFORD UNIV PRESS
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/54057
专题	中国科学院分子影像重点实验室
通讯作者	Wang, Kun; Yang, Meng
作者单位	1.Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Dept Ultrasound, State Key Lab Complex Severe & Rare Dis, Beijing, Peoples R China 2.Northwest Univ, Sch Informat Sci & Technol, Xian, Shaanxi, Peoples R China 3.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 4.Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Dept Rheumatol, State Key Lab Complex Severe & Rare Dis, Beijing, Peoples R China 5.Peking Univ Aerosp, Aerosp Ctr Hosp, Sch Clin Med, Dept Rheumatol & Immunol, Beijing, Peoples R China 6.Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Dept Ultrasound, State Key Lab Complex Severe & Rare Dis, Shuaifuyuan 1, Beijing 100730, Peoples R China 7.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, State Key Lab Management & Control Complex Syst, Zhongguancun East Rd 95, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	He, Xuelei,Wang, Ming,Zhao, Chenyang,et al. Deep learning-based automatic scoring models for the disease activity of rheumatoid arthritis based on multimodal ultrasound images[J]. RHEUMATOLOGY,2023:8.
APA	He, Xuelei.,Wang, Ming.,Zhao, Chenyang.,Wang, Qian.,Zhang, Rui.,...&Yang, Meng.(2023).Deep learning-based automatic scoring models for the disease activity of rheumatoid arthritis based on multimodal ultrasound images.RHEUMATOLOGY,8.
MLA	He, Xuelei,et al."Deep learning-based automatic scoring models for the disease activity of rheumatoid arthritis based on multimodal ultrasound images".RHEUMATOLOGY (2023):8.