Xiaoyan Xiao

Xiaoyan Xiao

Auto-generated profile, based on publicly available information

Xiaoyan Xiao

Department of Nephrology, Qilu Hospital, Shandong University, Jinan, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
15 February 2022 in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
Verified
Journal Article
Closed access
XCXiaoxiao Cui
Xiaoxiao Cui
PZPengfei Zhang
Pengfei Zhang
YLYujun Li
Yujun Li
Zhi LiuZhi Liu
Zhi Liu
XXXiaoyan Xiao
Xiaoyan Xiao
SLShuo Li
Shuo Li
Segmentation of the left ventricular (LV) myocardium in 2-D echocardiography is essential for clinical decision making, especially in geometry measurement and index computation. However, segmenting the myocardium is a time-consuming process and challenging due to the fuzzy boundary caused by the low image quality. The ground-truth label is employed as pixel-level class associations or shape regulation in segmentation, which works limit for effective feature enhancement for 2-D echocardiography. We propose a training strategy named multiconstrained aggregate learning (referred to as MCAL), which leverages anatomical knowledge learned through ground-truth labels to infer segmented parts and discriminate boundary pixels. The new framework encourages the model to focus on the features in accordance with the learned anatomical representations, and the training objectives incorporate a boundary distance transform weight (BDTW) to enforce a higher weight value on the boundary region, which helps to improve the segmentation accuracy. The proposed method is built as an end-to-end framework with a top-down, bottom-up architecture with skip convolution fusion blocks and carried out on two datasets (our dataset and the public CAMUS dataset). The comparison study shows that the proposed network outperforms the other segmentation baseline models, indicating that our method is beneficial for boundary pixels discrimination in segmentation.

24 November 2020 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YCYankun Cao
Yankun Cao
ZWZiqiao Wang
Ziqiao Wang
Zhi LiuZhi Liu
Zhi Liu
YLYujun Li
Yujun Li
XXXiaoyan Xiao
Xiaoyan Xiao
Guang YangGuang Yang
Guang Yang
Intravascular ultrasound (IVUS) can provide high-resolution cross-sectional images of coronary arteries, showing detailed information of the vascular lumen, tube wall, and athermanous plaques, which is helpful for the discovery or identification of early coronary atherosclerotic plaques. Multiple parameters extractable from the IVUS image can help the cardiologist analyze the pathology and assist in disease diagnosis and postoperative treatment. Typically, cardiologists manually label the intima and adventitia in the IVUS image, and obtain a limited number of parameters through the IVUS instrument, which is time consuming and labor-intensive. To assist the cardiologist in automatically obtaining more clinically relevant value parameters, a fully automatic IVUS multiparameter extraction framework is proposed. Based on the intima and adventitia obtained by DeepLab V3+, we propose a targeted noise reduction preprocessing framework adapted to IVUS. The framework implements the basic parameter extraction of IVUS through two newly proposed algorithms. And through the standard medical formula, the basic parameters are converted into 10 standard medical indicators. Standardized medical indicators are obtained by clinically relevant basic parameters. In terms of accuracy, this article used a clinical database obtained from Qilu Hospital of Shandong University and compared the results of the framework with the gold standard of cardiologists. The relative error of continuous IVUS main parameters between frames did not exceed 10.10%. The relative error of independent IVUS did not exceed 10.03%. Based on the distribution consistency of the parameters and the gold standard, a Bland-Altman plot of the parameters is proposed. It was verified that this distribution is basically in line with the gold standard of cardiologists. The algorithm in this article obtained a total of 10 parameters, far exceeding the parameters obtained by cardiologists and traditional IVUS machines. Its accuracy and speed can also meet the requirements of cardiologists for clinical diagnosis.

1 August 2016 in Electrochimica Acta
Verified
Journal Article
Closed access
XLXiaomin Lei
Xiaomin Lei
TLTingting Li
Tingting Li
YZYunpeng Zuo
Yunpeng Zuo
WYWenmin Yin
Wenmin Yin
LWLong Wu
Long Wu
HHHeyou Han
Heyou Han

13 November 2026 in JMIR Medical Informatics
Verified
Journal Article
Open access
MCMiaomiao Cheng
Miaomiao Cheng
HWHuiru Wang
Huiru Wang
QZQi Zhang
Qi Zhang
JQJun Qin
Jun Qin
LGLei Gong
Lei Gong
XXXiaoyan Xiao
Xiaoyan Xiao
Background: Discharge instructions are an important component of the transition from hospital to home for patients with diabetic kidney disease (DKD), whose care often involves multiple comorbidities, medications, and stage-specific management needs. However, producing complete, accurate, clear, and personalized instructions can be challenging for junior physicians. Objective: This study aimed to evaluate whether large language model (LLM) assistance improves the quality of DKD discharge instructions produced by junior physicians and whether its benefits vary according to chronic kidney disease (CKD) stage. Methods: The study included 101 hospitalized patients with DKD. Discharge instructions for each patient were initially drafted by a group of junior residents (resident group); subsequently, another group of residents at the same level, with the assistance of DeepSeek-V3.2 (AI-assisted group), generated a separate set of discharge instructions for the same 101 patients, resulting in a total of 202 documents. Four clinical experts, including 2 nephrologists and 2 endocrinologists, independently scored both versions of the discharge instructions using a 5-point Likert scale across 5 dimensions: completeness, accuracy, safety, clarity, and personalization. Interrater reliability was assessed using the intraclass correlation coefficient (ICC). Results: Interrater reliability was excellent in both the resident group (ICC=0.817, 95% CI 0.763‐0.864; P <.001) and the AI-assisted group (ICC=0.860, 95% CI 0.816‐0.897; P <.001). Compared with resident-only instructions, AI-assisted instructions received significantly higher scores across 5 evaluation dimensions and the overall evaluation (all Bonferroni-adjusted P <.001), with large effect sizes ( r =0.741‐0.927). In the resident-only group, CKD stage was negatively correlated with accuracy, safety, clarity, and overall quality (Spearman ρ=−0.33 to −0.37; all P <.001), whereas no significant correlations were observed for most dimensions in the AI-assisted group (|ρ|.05). The proportion of cases achieving a ≥1-point improvement in overall quality was 99% (100/101; 95% CI 94.6%‐100.0%). Conclusions: LLM assistance improved the completeness, clarity, and personalization of DKD discharge instructions generated by junior physicians, with advantages greatest in complex cases. A human-AI collaborative model is a promising approach to reduce documentation burden.