Si-Min Ruan

Si-Min Ruan

Auto-generated profile, based on publicly available information

Si-Min Ruan

Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, The First Affiliated Hospital of Sun Yat-sen University, No. 58 Zhongshan Road 2, Guangzhou, 510080, People's Republic of China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2018 in European Radiology
Verified
Journal Article
Closed access
PDF file
HHHang-Tong Hu
Hang-Tong Hu
ZWZhu Wang
Zhu Wang
XHXiao-Wen Huang
Xiao-Wen Huang
SCShu-Ling Chen
Shu-Ling Chen
XZXin Zheng
Xin Zheng
MKMing Kuang
Ming Kuang

3 September 2018 in European Radiology
Verified
Journal Article
Open access
PDF file
WLWei Li
Wei Li
YHYang Huang
Yang Huang
BZBo-Wen Zhuang
Bo-Wen Zhuang
GLGuang-Jian Liu
Guang-Jian Liu
HHHang-Tong Hu
Hang-Tong Hu
WWWei Wang
Wei Wang
Objective To assess significant liver fibrosis by multiparametric ultrasomics data using machine learning. Materials and Methods This prospective study consisted of 144 patients with chronic hepatitis B. Ultrasomics—high-throughput quantitative data from ultrasound imaging of liver fibrosis—were generated using conventional radiomics, original radiofrequency (ORF) and contrast-enhanced micro-flow (CEMF) features. Three categories of features were explored using pairwise correlation and hierarchical clustering. Features were selected using diagnostic tests for fibrosis, activity and steatosis stage, with the histopathological results as the reference. The fibrosis staging performance of ultrasomics models with combinations of the selected features was evaluated with machine-learning algorithms by calculating the area under the receiver-operator characteristic curve (AUC). Results ORF and CEMF features had better predictive power than conventional radiomics for liver fibrosis stage (both p < 0.01). CEMF features exhibited the highest diagnostic value for activity stage (both p < 0.05), and ORF had the best diagnostic value for steatosis stage (both p < 0.01). The machine-learning classifiers of adaptive boosting, random forest and support vector machine were found to be optimal algorithms with better (all mean AUCs = 0.85) and more stable performance (coefficient of variation = 0.01–0.02) for fibrosis staging than decision tree, logistic regression and neural network (mean AUC = 0.61–0.72, CV = 0.07–0.08). The multiparametric ultrasomics model achieved much better performance (mean AUC values of 0.78–0.85) than the features from a single modality in discriminating significant fibrosis (≥ F2). Conclusion Machine-learning-based analysis of multiparametric ultrasomics can help improve the discrimination of significant fibrosis compared with mono or dual modalities. Key Points • Multiparametric ultrasomics has achieved much better performance in the discrimination of significant fibrosis (≥ F2) than the single modality of conventional radiomics, original radiofrequency and contrast-enhanced micro-flow. • Adaptive boosting, random forest and support vector machine are the optimal algorithms for machine learning.

20 April 2021 in Journal of Gastroenterology and Hepatology
Verified
Journal Article
Open access
PDF file
HHHang‐Tong Hu
Hang‐Tong Hu
WWWei Wang
Wei Wang
LCLi-Da Chen
Li-Da Chen
SRSi‐Min Ruan
Si‐Min Ruan
SCShuling Chen
Shuling Chen
MKMing Kuang
Ming Kuang
Background and Aim: This study aims to construct a strategy that uses assistance from artificial intelligence (AI) to assist radiologists in the identification of malignant versus benign focal liver lesions (FLLs) using contrast‐enhanced ultrasound (CEUS).Methods: A training set (patients = 363) and a testing set (patients = 211) were collected from our institute. On four‐phase CEUS images in the training set, a composite deep learning architecture was trained and tuned for differentiating malignant and benign FLLs. In the test dataset, AI performance was evaluated by comparison with radiologists with varied levels of experience. Based on the comparison, an AI assistance strategy was constructed, and its usefulness in reducing CEUS interobserver heterogeneity was further tested.Results: In the test set, to identify malignant versus benign FLLs, AI achieved an area under the curve of 0.934 (95% CI 0.890–0.978) with an accuracy of 91.0%. Comparing with radiologists reviewing videos along with complementary patient information, AI outperformed residents (82.9–84.4%, P = 0.038) and matched the performance of experts (87.2–88.2%, P = 0.438). Due to the higher positive predictive value (PPV) (AI: 95.6% vs residents: 88.6–89.7%, P = 0.056), an AI strategy was defined to improve the malignant diagnosis. With the assistance of AI, radiologists exhibited a sensitivity improvement of 97.0–99.4% (P < 0.05) and an accuracy of 91.0–92.9% (P = 0.008–0.189), which was comparable with that of the experts (P = 0.904).Conclusions: The CEUS‐based AI strategy improved the performance of residents and reduced CEUS's interobserver heterogeneity in the differentiation of benign and malignant FLLs.

19 December 2018 in European Radiology
Verified
Journal Article
Closed access
PDF file
LCLi-Da Chen
Li-Da Chen
SRSi-Min Ruan
Si-Min Ruan
YLYuan Lin
Yuan Lin
JLJin-Yu Liang
Jin-Yu Liang
SSShun-Li Shen
Shun-Li Shen
WWWei Wang
Wei Wang

7 September 2018 in World Journal of Gastroenterology
Verified
Journal Article
Open access
LCLi-Da Chen
Li-Da Chen
SRSi-Min Ruan
Si-Min Ruan
JLJin-Yu Liang
Jin-Yu Liang
ZYZheng Yang
Zheng Yang
SSShun-Li Shen
Shun-Li Shen
WWWei Wang
Wei Wang
To develop a contrast-enhanced ultrasound (CEUS) predictive model for distinguishing intrahepatic cholangiocarcinoma (ICC) from hepatocellular carcinoma (HCC) in high-risk patients. This retrospective study consisted of 88 consecutive high-risk patients with ICC and 88 high-risk patients with HCC selected by propensity score matching between May 2004 and July 2016. Patients were assigned to two groups, namely, a training set and validation set, at a 1:1 ratio. A CEUS score for diagnosing ICC was generated based on significant CEUS features. Then, a nomogram based on the CEUS score was developed, integrating the clinical data. The performance of the nomogram was then validated and compared with that of the LR-M of the CEUS Liver Imaging Reporting and Data System (LI-RADS). The most useful CEUS features for ICC were as follows: rim enhancement (64.5%), early washout (91.9%), intratumoral vein (58.1%), obscure boundary of intratumoral non-enhanced area (64.5%), and marked washout (61.3%, all P < 0.05). In the validation set, the area under the curve (AUC) of the CEUS score (AUC = 0.953) for differentiation between ICC and HCC was improved compared to the LI-RADS (AUC = 0.742) (P < 0.001). When clinical data were added, the CEUS score nomogram was superior to the LI-RADS nomogram (AUC: 0.973 vs 0.916, P = 0.036, Net Reclassification Improvement: 0.077, Integrated Discrimination Index: 0.152). Subgroup analysis demonstrated that the CEUS score model was notably improved compared to the LI-RADS in tumors smaller than 5.0 cm (P < 0.05) but not improved in tumors smaller than 3.0 cm (P > 0.05). The CEUS predictive model for differentiation between ICC and HCC in high-risk patients had improved discrimination and clinical usefulness compared to the CEUS LI-RADS.

1 April 2024 in Radiology
Verified
Journal Article
Closed access
LCLi-Da Chen
Li-Da Chen
ZHZe-Rong Huang
Ze-Rong Huang
HYHong Yang
Hong Yang
MCMei-Qing Cheng
Mei-Qing Cheng
HHHang-Tong Hu
Hang-Tong Hu
WWWei Wang
Wei Wang
A sequential algorithm combining the noninvasive tests Fibrosis-4 Index (FIB-4) and a US deep learning (DL) model showed higher diagnostic accuracy and improved referral management for all-cause advanced liver fibrosis compared with FIB-4 or the DL model alone.