Ronghua Yan

Ronghua Yan


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 October 2023 in Journal of Hepatocellular Carcinoma
Verified
Journal Article
Open access
PDF file
JYJing Yang
Jing Yang
SLShuang Liang
Shuang Liang
HLHuahui Liu
Huahui Liu
CHCai Hu
Cai Hu
SGSainan Guan
Sainan Guan
RYRonghua Yan
Ronghua Yan
Purpose: To investigate the efficacy and safety of microwave ablation (MWA) assisted by ultrasound fusion imaging (FI) for primary and secondary liver cancers with a diameter of 3– 7 cm. Patients and Methods: A retrospective analysis was conducted on patients with primary and secondary liver cancers (3– 7 cm) who underwent MWA with ultrasound FI assistance in our hospital from April 2020 to May 2022. Technical success, technique efficacy, local tumor progression (LTP), major complication, intrahepatic distant recurrence (IDR), and overall survival (OS) were assessed during the follow-up period. In addition, the ablation results of tumors between the medium-sized group (3.1– 5.0 cm) and large-sized group (5.1– 7.0 cm) were compared. Results: 31 patients with 35 primary and secondary liver cancers were treated with MWA assisted by ultrasound FI. Complete ablation was achieved in 34 lesions with a technical success rate of 97.1%. Major complications occurred in 6.5% of patients (2/31), while no ablation-related deaths were reported. The median follow-up time of this study was 24 months (range:10 to 35 months). The technique efficacy rate was 97.1% (34/35), with LTP occurring in three lesions at a rate of 8.8% (3/34). The incidence of IDR was 38.7% (12/31) and the 2-year cumulative OS rate reached 96.7%. Moreover, there were no statistical differences in technique efficacy rate (p=0.286), LTP rate (p=0.328), major complication rate (p=0.503), IDR (p=0.857), and OS (p=0.118) between medium-sized group and large-sized group. Conclusion: Ultrasound FI-assisted MWA has the potential to be an effective and safe therapeutic strategy for primary and secondary liver cancers ranging from 3– 7 cm in size.

2 August 2023 in Frontiers in Endocrinology
Verified
Journal Article
Open access
CHCai Hu
Cai Hu
SLShuang Liang
Shuang Liang
HLHuahui Liu
Huahui Liu
JYJing Yang
Jing Yang
HKHaiyu Kang
Haiyu Kang
EXErjiao Xu
Erjiao Xu
Objectives: To construct a prognostic nomogram to predict the ablation zone disappearance for patients with papillary thyroid microcarcinoma (PTMC) after microwave ablation (MWA).Materials and methods: From April 2020 to April 2022, patients with PTMC who underwent MWA treatment were collected retrospectively. Ultrasound (US) or contrast-enhanced ultrasound (CEUS) was performed at 1 day, 1, 3, 6, 12, 18 and 24 months after MWA to observe the curative effect after ablation. The volume, volume reduction rate (VRR) and complete disappearance rate of the ablation zone at each time point were calculated. Univariate and multivariate logistic regression analysis were used to determine the prognostic factors associated with the disappearance of the ablation zone after MWA, and the nomogram was established and validated.Results: 72 patients with PTMCs underwent MWA were enrolled into this study. After MWA, no tumor progression (residual, recurrence or lymph node metastasis) and major postoperative complications occurred. The ablation zone in 28 (38.89%) patients did not completely disappear after MWA in the follow-up period. Three variables, including age (odds ratio [OR]: 1.216), calcification type (OR: 12.283), initial maximum diameter (OR: 2.051) were found to be independent prognostic factors predicting ablation zone status after MWA by multivariate analysis. The above variables and outcomes were visualized by nomogram (C-index=0.847).Conclusions: MWA was a safe and effective treatment for PTMC. Older patients with macrocalcification and larger size PTMCs were more unlikely to obtain complete disappearance of ablation zones. Incomplete disappearance of ablation zone was not related to recurrence.

2 August 2024 in Abdominal Radiology
Verified
Journal Article
Closed access
PDF file
JLJia Lin
Jia Lin
HLHuahui Liu
Huahui Liu
SLShuang Liang
Shuang Liang
LLLiping Luo
Liping Luo
SGSainan Guan
Sainan Guan
EXErjiao Xu
Erjiao Xu

30 November 2024 in Abdominal Radiology
Verified
Journal Article
Closed access
PDF file
QZQingjing Zeng
Qingjing Zeng
RYRonghua Yan
Ronghua Yan
LZLanxia Zhang
Lanxia Zhang
XYXuan Yu
Xuan Yu
YWYuxuan Wu
Yuxuan Wu
KLKai Li
Kai Li

25 December 2025 in JMIR Medical Informatics
Verified
Journal Article
Open access
XDXingwei Dai
Xingwei Dai
MKMan Ke
Man Ke
DXDixing Xie
Dixing Xie
MMMengting Mei
Mengting Mei
SWSi Wei
Si Wei
RYRonghua Yan
Ronghua Yan
Background: Mammography is a key imaging modality for breast cancer screening and diagnosis, with the Breast Imaging Reporting and Data System (BI-RADS) providing standardized risk stratification. However, BI-RADS category 4 lesions pose a diagnostic challenge due to their wide malignancy probability range and substantial overlap between benign and malignant findings. Moreover, current interpretations rely heavily on radiologists’ expertise, leading to variability and potential diagnostic errors. Recent advances in large language models (LLMs), such as ChatGPT-4o, Claude 3 Opus, and DeepSeek-R1, offer new possibilities for automated medical report interpretation. Objective: This study aims to explore the feasibility of LLMs in evaluating the benign or malignant subcategories of BI-RADS category 4 lesions based on free-text mammography reports. Methods: This retrospective, single-center study included 307 patients (mean age 47.25, 11.39 years) with BI-RADS category 4 mammography reports between May 2021 and March 2024. Three LLMs (ChatGPT-4o, Claude 3 Opus, and DeepSeek-R1) classified BI-RADS 4 subcategories from the reports’ text only, whereas radiologists based their classifications on image review. Pathology served as the reference standard, and the reproducibility of LLMs’ predictions was assessed. The diagnostic performance of radiologists and LLMs was compared, and the internal reasoning behind LLMs’ misclassifications was analyzed. Results: ChatGPT-4o demonstrated higher reproducibility than DeepSeek-R1 and Claude 3 Opus (Fleiss κ 0.850 vs 0.824 and 0.732, respectively). Although the overall accuracy of LLMs was lower than that of radiologists (senior: 74.5%; junior: 72.0%; DeepSeek-R1: 63.5%; ChatGPT-4o: 62.4%; Claude 3 Opus: 60.8%), their sensitivity was higher (senior: 80.7%; junior: 68.0%; DeepSeek-R1: 84.0%; ChatGPT-4o: 84.7%; Claude 3 Opus: 92.7%), while specificity remained lower (senior: 68.3%; junior: 76.1%; DeepSeek-R1: 43.0%; ChatGPT-4o: 40.1%; Claude 3 Opus: 28.9%). DeepSeek-R1 achieved the best prediction accuracy among LLMs with an area under the receiver operating characteristic curve of 0.64 (95% CI 0.57-0.70), followed by ChatGPT-4o (0.62, 95% CI 0.56-0.69) and Claude 3 Opus (0.61, 95% CI 0.54-0.67). By comparison, junior and senior radiologists achieved higher area under the receiver operating characteristic curves of 0.72 (95% CI 0.66-0.78) and 0.75 (95% CI 0.69-0.80), respectively. DeLong testing confirmed that all three LLMs performed significantly worse than both junior and senior radiologists (all P<.05), and no significant difference was observed between the two radiologist groups (P=.55). At the subcategory level, ChatGPT-4o yielded an overall F1-score of 47.6%, DeepSeek-R1 achieved 45.6%, and Claude 3 Opus achieved 36.2%. Conclusions: LLMs are feasible for distinguishing between benign and malignant lesions in BI-RADS category 4, with good stability and high sensitivity, but relatively insufficient specificity. They show potential in screening and may assist radiologists in reducing missed diagnoses.

23 August 2024 in British Journal of Radiology
Verified
Journal Article
Closed access
PDF file
QLQiqi Liu
Qiqi Liu
SLShuang Liang
Shuang Liang
HLHuahui Liu
Huahui Liu
LLLiping Luo
Liping Luo
SWShanshan Wu
Shanshan Wu
EXErjiao Xu
Erjiao Xu
To investigate the efficacy and safety of ultrasound(US)-guided microwave ablation (MWA) without artificial ascites (AA) inpatients with sub-cardiac liver cancers. This retrospective study included patients with the left lobe and caudate lobe of the liver cancer who underwent US-guided MWA in our institute from January 2020 to December 2022. According to whether the target lesion was located ≤ 5 mm from the pericardium, patients were divided into the sub-cardiac (SC) group and the non-sub-cardiac (NSC) group. In the SC group, AA was not employed during the ablation procedure. The results of technical success, technical efficiency, local tumor progression (LTP), and major complications were recorded. A total of 79 patients with 87 lesions were enrolled. There were 38 patients with 38 lesions in the SC group and 41 patients with 49 lesions in the NSC group. The median follow-up of all patients was 15 (range, 3-44) months. There was no significant difference in technical success rates (100% versus 100%), technique efficiency rates (100% versus 95.7%), LTP rates (2.63% versus 0%,), and major complication rates (2.63% versus 7.32%) between the SC group and the NSC group (p > 0.05). No cardiac-related complications occurred. US-guided MWA without AA for sub-cardiac liver cancers was safe and effective. The clinical prognosis of thermal ablation without artificial ascites in the treatment of sub-cardiac liver cancers is still unclear. The finding of this study provided evidence supporting the efficacy and safety of ultrasound-guided microwave ablation without artificial ascites for treating this tricky location.