Ruiqing Liu

Dr. Ruiqing Liu


Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
5 January 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
XYXiulong Yi
Xiulong Yi
YFYou Fu
You Fu
RLRuiqing Liu
Ruiqing Liu
HZHao Zhang
Hao Zhang
RHRong Hua
Rong Hua
Recently, automatic radiology report generation, which targets to generate multiple sentences that can accurately describe medical observations for given X-ray images, has gained increasing attention. Existing methods commonly employ the attention mechanism for accurate word generation. However, such attention-based methods fail to leverage useful image-level global features, thereby limiting the model's reasoning ability. To tackle this challenge, we propose two-stage global enhancement layers to facilitate the Transformer to generate more reliable reports from a global perspective. Specifically, the $1^{st}$ Global Enhancement Layer ( $1^{st}$ GEL) is designed to capture the global visual context features by establishing the relationships between image-level global features and previously generated words. The $2^{nd}$ Global Enhancement Layer ( $2^{nd}$ GEL) is devised to capture the region-global level features by building the relationships between image-level global features and region-level information. The experiments demonstrate that by integrating the aforementioned two-stage global enhancement layers into the Transformer model, our proposal achieves state-of-the-art (SOTA) performance on various Natural Language Generation (NLG) evaluation metrics. Further Clinical Efficacy (CE) evaluations also validate that our proposal is able to predict more critical information. The Code will be available at https://github.com/SKD-HPC/TSGET .

27 November 2024 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
XYXiulong Yi
Xiulong Yi
YFYou Fu
You Fu
JYJianzhi Yu
Jianzhi Yu
RLRuiqing Liu
Ruiqing Liu
HZHao Zhang
Hao Zhang
RHRong Hua
Rong Hua
Radiology report generation that aims to accurately describe medical findings for given images, is pivotal in contemporary computer-aided diagnosis. Recently, despite considerable progress, current radiology report generation models still struggled to achieve consistent quality across difficult and easy samples, which dramatically impacts their clinical value. To solve this problem, we explore the difficult samples mining in radiology report generation and propose the Linear Hybrid-Reward based Reinforced Focal Learning (LHR-RFL) to effectively guide the model to allocate more attention towards some difficult samples, thereby enhancing its overall performance in both general and intricate scenarios. In implementation, we first propose the Linear Hybrid-Reward (LHR) module to better quantify the learning difficulty, which employs a linear weighting scheme that assigns varying weights to three representative Natural Language Generation (NLG) evaluation metrics. Then, we propose the Reinforced Focal Learning (RFL) to adaptively adjust the contributions of difficult samples during training, thereby augmenting their impact on model optimization. The experimental results demonstrate that our proposed LHR-RFL improves the performance of the base model across all NLG evaluation metrics, achieving an average performance improvement of 20.9% and 13.2% on IU X-ray and MIMIC-CXR datasets, respectively. Further analysis also proves that our LHR-RFL can dramatically improve the quality of reports for difficult samples. The source code will be available at https://github.com/SKD-HPC/LHR-RFL.

4 April 2022 in Gastroenterology Research and Practice
Verified
Journal Article
Open access
PDF file
YYYi Yin
Yi Yin
XLXiaofeng Lu
Xiaofeng Lu
ZLZhun Li
Zhun Li
SLSong Liu
Song Liu
LSLihua Shao
Lihua Shao
WZWei-Ming Zhu
Wei-Ming Zhu
Background. Bone loss is common in patients with inflammatory bowel disease (IBD). The aim of the present study was to determine the prevalence of metabolic bone disease in patients newly diagnosed with IBD and to identify the risk factors for bone loss over time. Methods. We performed a retrospective, both cross-sectional and longitudinal, study to extract the risk factors of bone loss (including osteopenia and osteoporosis) in patients newly diagnosed with IBD, using dual-energy X-ray absorptiometry (DXA). Results. A total of 639 patients newly diagnosed with IBD that had at least one DXA were included in the cross-sectional study. Osteopenia and osteoporosis were diagnosed in 24.6 and 5.4 of patients, respectively. Age at diagnosis, body mass index, and serum phosphorus were identified as independent factors associated with bone loss at baseline. A total of 380 of the 639 IBD patients (including 212 CD patients and 168 UC patients) with at least a second DXA scan were included in the longitudinal study. 42.6 of the patients presented a worsening of bone loss in the follow-up study. Menopause, albumin, and use of corticosteroids were identified as independent factors associated with worsening of bone loss. Conclusions. Metabolic bone disease is common in IBD patients, and there is a significant increase in prevalence of bone loss over time. Postmenopausal female, malnourished patients, and those requiring corticosteroid treatment are at risk for persistent bone loss. Therefore, BMD measurements and early intervention with supplementation of calcium and vitamin D are recommended in IBD patients with high-risk factors.

9 July 2024 in Journal of Ethnopharmacology
Verified
Journal Article
Open access
ZXZitong Xu
Zitong Xu
GZGang Zhao
Gang Zhao
LZLize Zhang
Lize Zhang
CQCuixia Qiao
Cuixia Qiao
HWHao Wang
Hao Wang
YYYou You
You You
Based on the core pathogenesis of hepatosplenic disorder and qi transformation disorder in ulcerative colitis, Tong-Xie-Yao-Fang (TXYF) is a classical traditional Chinese medicine commonly used to treat ulcerative colitis. Our study revealed that it has the potential to prevent colitis-associated colorectal cancer, which embodies the academic concept in traditional Chinese medicine of treating the disease before it develops. This study was aimed at evaluating the therapeutic role of TXYF in treating colitis-associated colorectal cancer and exploring its possible underlying mechanisms. A colitis-associated colorectal cancer model was established in mice using azoxymethane and dextran sulfate sodium salt to examine the therapeutic effect of TXYF. The mouse body weights were observed. Hematoxylin-eosin staining was used to evaluate mouse colon histopathology. Colon cancer cells and colon epithelial cells were used to explore the potential molecular mechanisms. The proliferation and apoptosis of cells were detected by CCK8 and cell colony assays, flow cytometry and western blotting. The epithelial-mesenchymal transition (EMT) and mitophagy markers were examined by immunohistochemistry, western blotting, quantitative real-time PCR and immunofluorescence staining. TXYF inhibited the tumorigenesis of mice with colitis-associated colorectal cancer and the growth of inflammatory colon cells. TXYF induced mitophagy in colon cancer cells through the PTEN-induced putative kinase 1 (PINK1)/Parkin pathway to reverse EMT, which was consistent with the results in mice with colitis-associated colorectal cancer. The results of the present study demonstrated that TXYF effectively inhibited the progression of colitis-associated colorectal cancer through the PINK1/Parkin pathway, which provides new evidence for prevention strategies for this disease.

19 April 2024 in Frontiers in Nutrition
Verified
Journal Article
Open access
ZWZhibo Wang
Zhibo Wang
BSBaoying Sun
Baoying Sun
YYYimiao Yu
Yimiao Yu
JLJingnong Liu
Jingnong Liu
DLDuo Li
Duo Li
RLRuiqing Liu
Ruiqing Liu
Background: Postoperative complications in adhesive small bowel obstruction (ASBO) significantly escalate healthcare costs and prolong hospital stays. This study endeavors to construct a nomogram that synergizes computed tomography (CT) body composition data with inflammatory-nutritional markers to forecast postoperative complications in ASBO.Methods: The study’s internal cohort consisted of 190 ASBO patients recruited from October 2017 to November 2021, subsequently partitioned into training (n = 133) and internal validation (n = 57) groups at a 7:3 ratio. An additional external cohort comprised 52 patients. Body composition assessments were conducted at the third lumbar vertebral level utilizing CT images. Baseline characteristics alongside systemic inflammatory responses were meticulously documented. Through univariable and multivariable regression analyses, risk factors pertinent to postoperative complications were identified, culminating in the creation of a predictive nomogram. The nomogram’s precision was appraised using the concordance index (C-index) and the area under the receiver operating characteristic (ROC) curve.Results: Postoperative complications were observed in 65 (48.87%), 26 (45.61%), and 22 (42.31%) patients across the three cohorts, respectively. Multivariate analysis revealed that nutrition risk score (NRS), intestinal strangulation, skeletal muscle index (SMI), subcutaneous fat index (SFI), neutrophil-lymphocyte ratio (NLR), and lymphocyte-monocyte ratio (LMR) were independently predictive of postoperative complications. These preoperative indicators were integral to the nomogram’s formulation. The model, amalgamating body composition and inflammatory-nutritional indices, demonstrated superior performance: the internal training set exhibited a 0.878 AUC (95% CI, 0.802–0.954), 0.755 accuracy, and 0.625 sensitivity; the internal validation set displayed a 0.831 AUC (95% CI, 0.675–0.986), 0.818 accuracy, and 0.812 sensitivity. In the external cohort, the model yielded an AUC of 0.886 (95% CI, 0.799–0.974), 0.808 accuracy, and 0.909 sensitivity. Calibration curves affirmed a strong concordance between predicted outcomes and actual events. Decision curve analysis substantiated that the model could confer benefits on patients with ASBO.Conclusion: A rigorously developed and validated nomogram that incorporates body composition and inflammatory-nutritional indices proves to be a valuable tool for anticipating postoperative complications in ASBO patients, thus facilitating enhanced clinical decision-making.

11 February 2025 in BMC Medical Imaging
Verified
Journal Article
Open access
PDF file
ZWZhibo Wang
Zhibo Wang
LZLing Zhu
Ling Zhu
SLShunli Liu
Shunli Liu
DLDalue Li
Dalue Li
JLJingnong Liu
Jingnong Liu
RLRuiqing Liu
Ruiqing Liu
Adhesive small bowel obstruction (ASBO) is a common emergency that requires prompt medical attention, and the timing of surgical intervention poses a considerable challenge. Although computed tomography (CT) is widely used, its effectiveness in accurately identifying bowel strangulation is limited. The potential of radiomics models to predict the necessity for surgical resection in ASBO cases is not yet fully explored. The aim of this study is to identify risk factors for surgical resection in patients with ASBO and to develop a predictive model that integrates radiomic features with clinical data. This model designed to estimate the likelihood of surgical intervention and aid in clinical decision-making for acute ASBO cases. From January 2019 to February 2022, we enrolled 188 ASBO patients from our hospital, dividing them randomly into a training cohort (n = 131) and a test cohort (n = 57) using a 7:3 ratio. We collected baseline clinical data and extracted radiomic features from CT images to compute a radiomic score (Rad-score). A nomogram was developed that combines clinical characteristics and Rad-score. The performance of clinical, radiomic, and combined nomogram models was evaluated in both cohorts. Of the 188 patients, 92 underwent surgical resection, while 96 did not. The nomogram integrated factors such as white blood cell count, duration of obstruction, and preoperative infection indicators (fever, tachycardia, peritonitis), along with CT findings (elevated wall density, thickened wall, mesenteric fluid, ascites, bowel wall gas, small bowel feces, and hyperdensity of mesenteric fat) (p < 0.1). This combined model accurately predicted the need for surgical resection, with area under the curve (AUC) values of 0.761 (95% CI, 0.628–0.893) for the test cohort. Calibration curves showed strong agreement between predicted and observed outcomes, and decision curve analysis validated the model’s utility for acute ASBO cases. We developed and validated a CT-based nomogram that combines radiomic features with clinical data to predict the risk of surgical resection in ASBO patients. This tool offers valuable support for treatment planning and decision-making in emergent situations.