A deep learning classification of metacarpophalangeal joints synovial proliferation in rheumatoid arthritis by ultrasound images

Wu, Min1; Wu, Huaiuy2,3; Wu, Lili4; Cui, Chen2,3; Shi, Siyuan2,3; Xu, Jinfeng2,3; Liu, Yan5,6,7; Dong, Fajin2,3

2022

10.1002/jcu.23143

JOURNAL OF CLINICAL ULTRASOUND   影响因子和分区

0091-2751

1097-0096

Objective To evaluate if an automatic classification of rheumatoid arthritis (RA) metacarpophalangeal joint conditions in ultrasound images is feasible by deep learning (DL) method, to provide a more objective, automated, and fast way of RA diagnosis in clinical setting. Materials and Methods DenseNet-based DL model was used and both training and testing are implemented in TensorFlow 1.13.1 with Keras DL libraries. The area under curve (AUC), accuracy, sensitivity, and specificity values with 95% CIs were reported. The statistical analysis was performed by using scikit-learn libraries in Python 3.7. Results A total of 1337 RA ultrasound images were acquired from 208 patients, the number of images is 313, 657, 178, and 189 in OESS Grade L0, L1, L2, and L3, respectively. In Classification Scenario 1 SP-no versus SP-yes, three experiments with region of interest of size 192 x 448 (Group 1), 96 x 224 (Group 2), and 96 x 224 stacked with pre-segmented annotated mask of SP area (Group 3) as input achieve an AUC of 0.863 (95% CI: 0.809, 0.917), 0.861 (95% CI: 0.805, 0.916), and 0.886 (95% CI: 0.836, 0.936), respectively. In Classification Scenario 2 Healthy versus Diseased, experiments in Group 1, Group 2 and Group 3 achieve an AUC of 0.848 (95% CI: 0.799, 0.896), 0.864 (95% CI: 0.819, 0.909), and 0.916 (95% CI: 0.883, 0.952), respectively. Conclusion We combined DenseNet model with ultrasound images for RA condition assessment. The feasibility of using DL to create an automatic RA condition classification system was also demonstrated. The proposed method can be an alternative to the initial screening of RA patients.

artificial intelligence deep learning rheumatoid arthritis synovitis ultrasonography

SCI

英语

通讯

Commission of Scientific and Technology of Shenzhen[JCYJ20190806151807192]

Acoustics ; Radiology, Nuclear Medicine & Medical Imaging

Acoustics ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000743211600001

WILEY

CLINICAL MEDICINE

Web of Science

1.Xintai Peoples Hosp, Phys Examinat, Tai An, Shandong, Peoples R China
2.Jinan Univ, Clin Med Coll 2, Dept Ultrasound, Jinan, Guangdong, Peoples R China
3.Southern Univ Sci & Technol, Shenzhen Peoples Hosp, Affiliated Hosp 1, Shenzhen 518020, Guangdong, Peoples R China
4.Xintai Matern & Child Hlth Hosp, Dept Ultrasound, Tai An, Shandong, Peoples R China
5.Shandong Univ, Chinese Minist Educ, Key Lab Cardiovasc Remodeling & Funct Res, Qilu Hosp, 107 Wenhuaxi Rd, Jinan 250012, Puerto Rico, Peoples R China
6.Shandong Univ, Chinese Minist Hlth, Qilu Hosp, 107 Wenhuaxi Rd, Jinan 250012, Puerto Rico, Peoples R China
7.Shandong Univ, State & Shandong Prov Joint Key Lab Translat Card, Qilu Hosp, 107 Wenhuaxi Rd, Jinan 250012, Puerto Rico, Peoples R China

Wu, Min,Wu, Huaiuy,Wu, Lili,et al. A deep learning classification of metacarpophalangeal joints synovial proliferation in rheumatoid arthritis by ultrasound images[J]. JOURNAL OF CLINICAL ULTRASOUND,2022.

Wu, Min.,Wu, Huaiuy.,Wu, Lili.,Cui, Chen.,Shi, Siyuan.,...&Dong, Fajin.(2022).A deep learning classification of metacarpophalangeal joints synovial proliferation in rheumatoid arthritis by ultrasound images.JOURNAL OF CLINICAL ULTRASOUND.

Wu, Min,et al."A deep learning classification of metacarpophalangeal joints synovial proliferation in rheumatoid arthritis by ultrasound images".JOURNAL OF CLINICAL ULTRASOUND (2022).