MLMailan Liu

Mailan Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mailan Liu has a total of 104 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Randomised comparative effectiveness trial evaluating the efficacy and safety of acupuncture-related integrative therapy combined with celecoxib for chronic pain in patients with knee osteoarthritis: protocol

    by Xinran Xiao, Saiyang Liu, Anzhe Tian, Cheng Guo, Chao Liu, Zhixian Gong, Feng Zhong, Wen Zhang, Weiai Liu, Chang She, et al.

    Introduction: Knee osteoarthritis (KOA) is a prevalent chronic degenerative joint disorder that seriously affects mobility and quality of life in older adults. Pharmacological treatments such as celecoxib are commonly used for symptom relief, but their long-term use may be limited by adverse effects. Acupuncture has been widely used as a complementary non-pharmacological treatment for KOA and may help reduce pain and improve function; however, its onset of benefit may be relatively gradual. Combining acupuncture-related integrative therapy with celecoxib may provide more rapid symptom relief while potentially improving sustained clinical outcomes and reducing reliance on prolonged pharmacological treatment. This study aims to evaluate the comparative effectiveness and safety of acupuncture-related integrative therapy, celecoxib and their combination in patients with KOA in a multicentre randomised controlled trial. Methods and analysis: This is a multicentre, three-arm, parallel-group randomised controlled trial that will be conducted in three hospitals in Hunan Province, China. A total of 282 participants with KOA will be randomly assigned in a 1:1:1 ratio to receive acupuncture-related integrative therapy, celecoxib therapy or combined acupuncture-related integrative therapy and celecoxib for 4 weeks, with an additional 4-week follow-up period. The primary outcome is the change in Visual Analogue Scale score for activity-related knee pain from baseline to week 4. Secondary outcomes include the Western Ontario and McMaster Universities Osteoarthritis Index, clinical response rate, knee range of motion, 30-second chair-stand test, 40-metre fast-paced walk test and incidence of adverse events. Outcome assessments will be conducted at baseline, week 2, week 4 and week 8. Safety will be monitored throughout. Data will be analysed using the intention-to-treat principle. Ethics and dissemination: The study has been approved by the ethics committees of all centres (HN-LL-KY-2025-007-01, 2025-KY-019-01, 2025042705). The study findings will be disseminated through publication in peer-reviewed journals and presentations at national or international academic conferences. Trial registration number: ITMCTR2026000093. Registered on 5 December 2025. The first participant was recruited on 27 February 2026.

  • Open Access

    Protocol for the real-world evidence of acupuncture for chronic neck pain in the elderly: an observational multi-centre cohort study

    by Anzhe Tian, Mailan Liu, Mengxia Xiao, Chao Liu, Cheng Guo, Xinran Xiao, Saiyang Liu, Xiang Li

    Introduction: Chronic neck pain (CNP) refers to persistent pain lasting more than 3 months originating from the muscles, bones, joints, or tendons in the cervical region. With global population growth and the accelerating trend of aging, the number of elderly patients suffering from neck pain is continuously increasing, and the associated health burden and socioeconomic costs cannot be overlooked. Previous studies have shown that acupuncture therapy in Traditional Chinese Medicine (TCM) is effective in alleviating pain among elderly patients with CNP. However, few studies have investigated the overall effectiveness of various acupuncture therapies in real-world clinical settings for managing CNP in the elderly. Methods and analysis: A total of 212 eligible older adults with CNP will be enrolled and classified into an acupuncture group or a non-acupuncture group according to routine clinical practice, patient preference, and physician judgment. All participants will receive treatment three times per week for 4 weeks, followed by an 8-week follow-up period. The primary outcome will be the proportion of patients with at least 50% reduction from baseline in the worst pain intensity measured by Visual Analogue Scale (VAS) (0–100, higher scores signify worse pain) at baseline and after treatment. Secondary outcomes include changes in the Northwick Park Neck Pain Questionnaire (NPQ) score, changes in the Tanaka Yasuhisa 20-point assessment scale, and alterations in the cervical pressure pain threshold (PPT). VAS, NPQ and Tanaka Yasuhisa 20-point score will be assessed at weeks 0, 4, 8, and 12. PPT will be measured at weeks 0 and 4. Adverse events will be recorded in detail during the trial. Ethics and dissemination: The study has been approved by our ethics review boards (Protocol Approval HN-LL-KY-2025-009-01, 2025-KY-019-01, No. 2025042704). The study findings will be disseminated through presentation at a high-impact medical journal, with online access. Conclusion: The findings of this study will provide potential evidence for manual acupuncture in the treatment of CNP. Clinical trial registration: https://itmctr.ccebtcm.org.cn , ITMCTR2025002064.

  • Open Access

    Attention residual network for medical ultrasound image segmentation

    by Honghua Liu, Peiqin Zhang, Jiamin Hu, Yini Huang, Shanshan Zuo, Lu Li, Mailan Liu, Chang She

    Ultrasound imaging can distinctly display the morphology and structure of internal organs within the human body, enabling the examination of organs like the breast, liver, and thyroid. It can identify the locations of tumors, nodules, and other lesions, thereby serving as an efficacious tool for treatment detection and rehabilitation evaluation. Typically, the attending physician is required to manually demarcate the boundaries of lesion locations, such as tumors, in ultrasound images. Nevertheless, several issues exist. The high noise level in ultrasound images, the degradation of image quality due to the impact of surrounding tissues, and the influence of the operator’s experience and proficiency on the determination of lesion locations can all contribute to a reduction in the accuracy of delineating the boundaries of lesion sites. In the wake of the advancement of deep learning, its application in medical image segmentation is becoming increasingly prevalent. For instance, while the U-Net model has demonstrated a favorable performance in medical image segmentation, the convolution layers of the traditional U-Net model are relatively simplistic, leading to suboptimal extraction of global information. Moreover, due to the significant noise present in ultrasound images, the model is prone to interference. In this research, we propose an Attention Residual Network model (ARU-Net). By incorporating residual connections within the encoder section, the learning capacity of the model is enhanced. Additionally, a spatial hybrid convolution module is integrated to augment the model’s ability to extract global information and deepen the vertical architecture of the network. During the feature fusion stage of the skip connections, a channel attention mechanism and a multi-convolutional self-attention mechanism are respectively introduced to suppress noisy points within the fused feature maps, enabling the model to acquire more information regarding the target region. Finally, the predictive efficacy of the model was evaluated using publicly accessible breast ultrasound and thyroid ultrasound data. The ARU-Net achieved mean Intersection over Union (mIoU) values of 82.59% and 84.88%, accuracy values of 97.53% and 96.09%, and F1-score values of 90.06% and 89.7% for breast and thyroid ultrasound, respectively.


  • Guyuan Jiannao decoction improves neurovascular unit dysfunction by regulating PI3K/AKT/NF-κB signaling pathway in cerebral small vessel disease rats

    by Ziyan Zhong, Hongping Long, Nuokun Li, Tongtong Liu, Mei Wu, Jielin Wang, Mailan Liu, Xiuli Zhang, Zhigang Mei, Rui Fang, et al.


  • Open Access

    Classification of CT scan and X-ray dataset based on deep learning and particle swarm optimization

    by Honghua Liu, Mingwei Zhao, Chang She, Han Peng, Mailan Liu, Bo Li

    In 2019, the novel coronavirus swept the world, exposing the monitoring and early warning problems of the medical system. Computer-aided diagnosis models based on deep learning have good universality and can well alleviate these problems. However, traditional image processing methods may lead to high false positive rates, which is unacceptable in disease monitoring and early warning. This paper proposes a low false positive rate disease detection method based on COVID-19 lung images and establishes a two-stage optimization model. In the first stage, the model is trained using classical gradient descent, and relevant features are extracted; in the second stage, an objective function that minimizes the false positive rate is constructed to obtain a network model with high accuracy and low false positive rate. Therefore, the proposed method has the potential to effectively classify medical images. The proposed model was verified using a public COVID-19 radiology dataset and a public COVID-19 lung CT scan dataset. The results show that the model has made significant progress, with the false positive rate reduced to 11.3% and 7.5%, and the area under the ROC curve increased to 92.8% and 97.01%.


  • Open Access

    Research on multi-label recognition of tongue features in stroke patients based on deep learning

    by Honghua Liu, Peiqin Zhang, Yini Huang, Shanshan Zuo, Lu Li, Chang She, Mailan Liu

    Stroke has become the leading cause of disability in adults worldwide. Early precise rehabilitation intervention is crucial for the recovery of stroke patients, with the key lying in accurately identifying patients’ physical characteristics during the rehabilitation phase. Compared to diagnostic techniques such as medical neuroimaging, traditional Chinese medicine(TCM) tongue diagnosis offers good accessibility and ease of application. However, conventional TCM tongue diagnosis relies on the experience of doctors, which introduces a degree of subjectivity, especially since stroke patients exhibit unique characteristics in tongue texture, shape, and coating, making accurate diagnosis more challenging. To address this issue, this paper proposes a deep learning-based automatic recognition approach for the tongue images of stroke patients, aiming to improve the accuracy of automatic extraction and recognition of stroke-related tongue features through image processing and machine learning techniques. First, this study performs image cropping and data augmentation on tongue images. Then, considering that tongue color, coating color, and coating texture are interrelated in TCM theory and jointly reflect the body’s physiological and pathological state, a label-guided multi-label recognition model for tongue images is designed. This model extracts features from the tongue images of stroke patients, learns the correlations among the features, and performs classification to automatically identify key characteristics such as tongue shape, color, and coating. Finally, the model’s performance is quantitatively evaluated. Experimental results show that the proposed deep learning model outperforms several advanced deep learning models, such as resnet and densenet, and existing single-task tongue classification models in automatically recognizing stroke patients’ tongue images. This research improves the accuracy of feature extraction and recognition of tongue characteristics in stroke patients during rehabilitation, providing a convenient and feasible technical approach for real-time evaluation and diagnosis in the stroke rehabilitation process. It has significant clinical application value and research significance.


  • Open Access

    Meta-analysis comparing the effect of combined acupuncture plus statin therapy versus statin therapy alone on lipid levels of patients with angina pectoris of coronary heart disease

    by Zhaobo Yan, Mailan Liu, Xianming Wu, Jiaojiao Xiong, Zhihong Yang, Ning Zhang, Xiaofang Yang, Mi Liu

    Objectives: Establish clinical evidence regarding acupuncture combined with statin for blood lipid control in patients with angina pectoris (AP) of coronary heart disease (CHD) by systematically analyzing data from all available studies. Design: A systematic review and meta-analysis. Data sources: The literature search involved eight databases (China National Knowledge Infrastructure, Chinese Biomedical Literature Database, Wanfang, VIP Database for Chinese Technical Periodicals, PubMed, Embase, Web of Science, and Cochrane Library) and was finished on February 1, 2024. Eligibility criteria: Random controlled trials (RCTs) investigating the efficacy of acupuncture combined with statin on lipid levels in patients with AP of CHD were eligible. The outcomes assessed were the lipid metabolism indicators, including TC, TG, LDL-C, and HDL-C, as well as the safety of the treatment. Data extraction and synthesis: Data extraction and quality evaluation were conducted by two independent reviewers, with any discrepancies discussed by a third researcher. Pooled mean differences (MD) with 95% confidence intervals (CIs) were calculated for each outcome. Sensitivity and subgroup analyses were carried out to explore the heterogeneity. Publication bias was assessed using a funnel plot. The quality of the evidence was evaluated using the GRADE system. Results: The final meta-analysis included nine eligible studies involving 754 patients. When comparing statin group, the acupuncture plus statin group showed lower levels of TC (MD=-0.48, 95% CI: −0.61 to −0.35, P P P =0.0001), and higher levels of HDL-C (MD=0.16, 95% CI: 0.06 to 0.26, P =0.001). Each study included in the analysis exhibited some degree of bias. Significant publication bias was detected for the primary outcomes. Evidence quality for the primary outcomes was graded as very low. Conclusions: Acupuncture as an adjunctive treatment can further improve lipid profile in individuals diagnosed with AP of CHD based on statin therapy. However, the clinical significance of this effect remains unclear; it is necessary to confirm the findings through more high-quality RCTs in the future. Trial registration number: PROSPERO CRD42023465292. STRENGTHS AND LIMITATIONS OF THIS STUDY: This comprehensive systematic review will collect data regarding the combined therapy (acupuncture + statin) on lipid profiles in patients with AP of CHD to provide new evidence supporting the use of acupuncture treatment for AP of CHD. Subgroup analysis based on the duration of intervention and types of acupuncture will provide a more detailed evaluation of the effectiveness of the combined therapy. A thorough evaluation of the quality of the evidence for the primary outcomes was conducted using the Grading of Recommendation Assessment, Development, and Evaluations (GRADE) system. This review has limited ability to draw clear conclusions due to poor quality of evidence. We restricted the literature search to eight electronic databases and ignored a search for gray literature, which may miss important literature and could introduce publication bias.

  • Open Access

    Uncertainty analysis and optimization of laser thermal pain treatment

    by Honghua Liu, Chang She, Zhiliang Huang, Lei Wei, Qian Li, Han Peng, Mailan Liu

    Uncertainty in operating parameters during laser thermal pain treatment can yield unreliable results. To ensure reliability and effectiveness, we performed uncertainty analysis and optimization on these parameters. Firstly, we conducted univariate analysis to identify significant operational parameters. Next, an agent model using RBNN regression determined the relationship between these parameters, the constraint function, and the target function. Using interval uncertainty analysis, we obtained confidence distributions and established a nonlinear interval optimization model. Introducing RPDI transformed the model into a deterministic optimization approach. Solving this with a genetic algorithm yielded an optimal solution. The results demonstrate that this solution significantly enhances treatment efficacy while ensuring temperature control stability and reliability. Accounting for parameter uncertainties is crucial for achieving dependable and effective laser thermal pain treatment. These findings have important implications for advancing the clinical application of this treatment and enhancing patient outcomes.


  • Open Access

    Uncertainty analysis and optimization for mild moxibustion

    by Honghua Liu, Zhiliang Huang, Lei Wei, He Huang, Qian Li, Han Peng, Mailan Liu

    During mild moxibustion treatment, uncertainties are involved in the operating parameters, such as the moxa-burning temperature, the moxa stick sizes, the stick-to-skin distance, and the skin moisture content. It results in fluctuations in skin surface temperature during mild moxibustion. Existing mild moxibustion treatments almost ignore the uncertainty of operating parameters. The uncertainties lead to excessive skin surface temperature causing intense pain, or over-low temperature reducing efficacy. Therefore, the interval model was employed to measure the uncertainty of the operation parameters in mild moxibustion, and the uncertainty optimization design was performed for the operation parameters. It aimed to provide the maximum thermal penetration of mild moxibustion to enhance efficacy while meeting the surface temperature requirements. The interval uncertainty optimization can fully consider the operating parameter uncertainties to ensure optimal thermal penetration and avoid patient discomfort caused by excessive skin surface temperature. To reduce the computational burden of the optimization solution, a high-precision surrogate model was established through a radial basis neural network (RBNN), and a nonlinear interval model for mild moxibustion treatment was formulated. By introducing the reliability-based possibility degree of interval (RPDI), the interval uncertainty optimization was transformed into a deterministic optimization problem, solved by the genetic algorithm. The results showed that this method could significantly improve the thermal penetration of mild moxibustion while meeting the skin surface temperature requirements, thereby enhancing efficacy.