Ziping Li

Automated skin biopsy histopathological image annotation using multi-instance representation and learning

With digitisation and the development of computer-aided diagnosis, histopathological image analysis has attracted considerable interest in recent years. In this article, we address the problem of the automated annotation of skin biopsy images, a special type of histopathological image analysis. In contrast to previous well-studied methods in histopathology, we propose a novel annotation method based on a multi-instance learning framework. The proposed framework first represents each skin biopsy image as a multi-instance sample using a graph cutting method, decomposing the image to a set of visually disjoint regions. Then, we construct two classification models using multi-instance learning algorithms, among which one provides determinate results and the other calculates a posterior probability. We evaluate the proposed annotation framework using a real dataset containing 6691 skin biopsy images, with 15 properties as target annotation terms. The results indicate that the proposed method is effective and medically acceptable.

Deqi Sensation in Placebo Acupuncture: A Crossover Study on Chinese Medicine Students

Objective. To evaluate the similarity of deqi sensation of real and noninvasive placebo acupuncture in healthy people with knowledge of Chinese medicine. Methods. In a crossover design, volunteers recruited from Chinese medicine college students were randomized to two groups to receive two phases of intervention with a one-week washout interval. In Group A, the participants were firstly treated by real acupuncture and then by sham needle, and the treatment sequence was reversed in Group B. VAS for pain intensity and deqi sensation was evaluated as outcomes. Results. Sixty-three volunteers were recruited and 60 were included and finished the study. In Group A, VAS was higher in Phase I than in Phase II (P = 0.017). Only treatment methods were selected as factor to VAS difference (P = 0.046) in ANOVA test. More positive deqi was reported in Group A in Phase I when treated by real acupuncture (P = 0.039), but the difference was not significant in Phase II (P = 0.301). Conclusion. The noninvasive placebo acupuncture device can effetely simulate the deqi sensation as real acupuncture, but it is less likely to evoke the active effect of deqi in real practice. This trial is registered with Chinese Clinical Trial Registry: ChiCTR-ORC-09000505.

Deep learning for acupuncture point selection patterns based on veteran doctor experience of Chinese medicine

The inheritance of clinical experience of veteran doctors of Chinese medicine (CM) plays a key role in the development and effectiveness enhancement of Chinese medicine in the history. The clinical experience are classified as the patterns of disease diagnosis and Chinese medical Zheng diagnosis, the identification of core elements of Zheng, the treatment experience and relation of herbal medicine formulae, Zheng and disease, and the common law of diagnosis and treatment in real practice. The source of the experience mainly originates from literature and manuscripts of CM masters, which are being electronically recorded during the last two decades. As a result, it makes feasible to apply data mining to the knowledge discovery through the experience of veteran CM doctors. However, the current focus on this field is limited to the published literature such as journal papers, conference proceedings and textbooks, but the paper based manuscripts personally written by the veteran doctors are usually neglected. In this paper, we established a database for Dr Situ Ling, who is a deceased famous CM acupuncture master in southern China. The study objective is to discover the acupuncture point selection patterns which require profession knowledge and experience from senior CM doctors. It is believed these patterns are deposited as underlying knowledge with various middle level concepts that can be analyzed and discover by a serial of algorithms. Thus in this work, we formularized the patterns of acupuncture point selection as a learning task with deep architecture, which attempts to capture either existent or underlying concepts so as to simulate the planning process of the combined diagnosis of western medicine and Chinese medicine. The Restricted Boltzmann Machines (RBM) was used as the main model for deep learning to process to medical record data with international standard diagnosis (ICD-10) previously made by trained doctors. Then the ICD-10 based diagnosis dataset was introduced into our framework to enhance the concepts diversity. After applying this model, the learning accuracy based on the medical record database of Dr Situ Ling was raised up to 75%. Thus this model can serve as a solution to discover the acupuncture point selection patterns of CM acupuncture veteran doctors. Furthermore, the data mining study model linked by international diagnosis standard (i.e. ICD-10), point selection patterns, and clinical symptoms will provide useful cues to reveal the essence of Zheng diagnosis through experience of CM veteran doctors.

Gender-Related Differences in Outcomes on Acupuncture and Moxibustion Treatment Among Depression Patients

OBJECTIVES This study sought to (1) assess the effectiveness of acupuncture and moxibustion with a method of soothing the liver and regulating the mind on the quality of life among patients with depression and (2) study the sex differences of acupuncture and moxibustion in the treatment of depression on the basis of patient-reported outcomes. METHODS In a single-blind, randomized, controlled trial conducted in Guangdong Province, China, in January and December 2010, 163 patients who met the criteria for depression were enrolled. Eligible patients were allocated to three treatment groups (soothing liver and regulating mind group, acupoint shallow puncturing group, and non-acupoint shallow puncturing group). In all three groups, the treatment was given twice a week for 12 weeks. The Hamilton Depression Rating Scale (HAMD) and Symptom Checklist 90 (SCL90) were used to quantitatively assess patients before and 1 and 3 months after treatment. RESULTS Non-statistically significant differences in the acupuncture and moxibustion therapeutic effects of soothing liver and regulating mind treatment were found between men and women (p>0.05). An item-by-item analysis of the SCL90 and HAMD scores showed sex differences between the efficacy of the soothing liver and regulating mind group and the group receiving acupoint shallow puncturing. Women obtained lower scores in somatization, interpersonal relationship, anxiety, terror, and extremeness items and HAMD scores in the soothing liver and regulating mind group than in the acupoint shallow puncturing group (p<0.05), while men showed no significant differences between the soothing liver and regulating mind group and the acupoint shallow puncturing group (p>0.05). CONCLUSIONS The therapeutic effect of soothing liver and regulating mind is similar for both sexes, but women were more sensitive to the efficacy of the soothing liver and regulating mind treatment compared with other methods. These findings could indicate an important issue to consider for the different acupuncture and moxibustion treatments for depression in men and women.

Soluble N-ethylmaleimide-sensitive Factor Attachment Receptor (SNARE) Protein Involved in the Remission of Depression by Acupuncture in Rats

This study aims to investigate the molecular mechanisms of acupuncture in the remission of depression. A depressive disorder model was induced by exposing Sprague-Dawley rats to chronic unpredictable stress. The rats were divided into five groups: healthy (blank group) and stressed rats (model group), and stressed rats treated with acupuncture (acupuncture group), riluzole (riluzole group), acupuncture combined with botulinum toxin A (BTX-A) injection (acupuncture+BTX-A group) or riluzole combined with BTX-A injection (riluzole+BTX-A group). Behavioral analysis showed significant differences in sucrose consumption, weight, and horizontal or vertical movements between the model and both the riluzole and acupuncture groups. No obvious differences between the riluzole+BTX-A and acupuncture+BTX-A groups were found. Moreover, no significance differences in glutamate content in the hippocampus were found among the riluzole+BTX-A, acupuncture+BTX-A and model groups (p>0.05). Western blots and reverse transcription polymerase chain reactions were employed to detect protein and mRNA expressions of VGLUT2, SNAP25, VAMP1, VAMP2, VAMP7, and syntaxin1; no obvious differences among the riluzole+BTX-A, acupuncture+BTX-A and model groups were found. These data suggest that soluble N-ethylmaleimide-sensitive factor attachment receptor proteins are involved in the remission of depression in rats treated with acupuncture.

Is adjunctive treatment with medication of liver-soothing-oriented method beneficial for depression after cerebrovascular accident?: A PRISMA-compliant meta-analysis.

Background:Adjunctive treatment with medication of liver-soothing-oriented method (MLSM) is one of the most commonly used approaches for subjects with depression after cerebrovascular accident (DCVA) in China. The purpose of this meta-analysis was to evaluate the outcome of MLSM treatment in subjects with DCVA using relevant published literature. Methods:The PubMed, Cochrane Library, Embase, Chinese databases of China National Knowledge Infrastructure, WanFang, Sinomed, and VIP were used to collect all publications until March 2016. Randomized controlled trials comparing treatments with and without MLSM for subjects with DCVA were included. The quality of each publication was assessed based on the recent Handbook (5.1 version) for Cochrane Reviewers. Cochrane Collaborations software RevMan 5.3 software was applied for data analysis. Results:Thirty studies, including 2599 cases, were identified and collected. Adjunctive treatment with MLSM noticeably enhanced total effective rates (odds ratio 3.76; 95% confidence interval [CI] 2.92–4.85, I2 = 0%, P = 0.96) in comparison to non-MLSM conventional pharmacotherapy. Compared to non-MLSM treatment, the changes of Hamilton Depression Scale in adjunctive treatment with MLSM, respectively, decreased and showed beneficial effects after 3 weeks (weighted mean difference [WMD] −4.83; 95% CI −6.82 to −2.83; I2 = 86%, P < 0.001), 4 weeks (WMD −4.20; 95% CI −5.06 to −3.33; I2 = 78%, P < 0.001), 6 weeks (WMD −3.36; 95% CI −4.05 to −2.68; I2 = 54%, P = 0.02), 8 weeks (WMD −4.83; 95% CI −5.62 to −4.04; I2 = 73%, P < 0.001), and 12 weeks (WMD −2.88; 95% CI −4.09 to −1.67; I2 = 58%, P = 0.09). As for changes in inflammatory cytokine levels, adjunctive treatment with MLSM was associated with a significant decrease in tumor necrosis factor-&agr;, IL-6, and interleukin-1&bgr; levels in comparison to non-MLSM treatment. Moreover, there were positive effects on score changes for National Institute of Health Stroke Scale, activities of daily living, Hamilton Anxiety Scale, Modified Edinburgh Scandinavian Stroke Scale, and Self-Rating Anxiety Scale. No serious adverse events were reported. Conclusion:MLSM appears to improve symptoms of depressive disorders, enhance immediate responses, and the quality of life in subjects with DCVA. The positive action of MLSM might be potentially connected with its immunoregulating effects. More prospective trials with strict design and larger sample sizes are warranted to clarify its effectiveness and safety.

Cloud computing and its decision-making for medical and health informatization in the context of big data

Cloud computing, as a new system and architecture of data mutual sharing, is composed of three service models i.e. cloud software as a service (SaaS), cloud platform as a service (PaaS) and cloud infrastructure as a service (IaaS), as well as including three key enabling technologies i.e. networks of fast wide-area, server computers of powerful and inexpensive specialty, and commodity hardware of high-performance virtualization. Cloud computing technology brings in innovative and constructive ideas for the medical and health informatization. However, it also challenges many traditional approaches to application design and management of medical-sanitary institutions or other datacenters, especially the relevant issues of security, interoperability, portability, et al. that cited as major barriers to broader adoption. Based on the concept, key technology, core problem and principles, the author attempts to discuss the main issues of cloud computing in the construction and development of the medical and health informatization. We hope these considerations can provide reference to the service for the present medical informatization construction and practical decision-making in the context of big data.

Evidence-based decision support for the clinical practice of acupuncture: Data mining approaches

The concept and methodology of evidence-based medicine (EBM) and the strategy to promote efficacy of acupuncture in clinical practice are introduced in this paper. Then it focuses on using the data mining approaches to integrate the primary evidence from real practice based on conventional clinical data and secondary evidence by systematic literature review or Meta-analysis. The new analytic method is capable of explore in-depth on the latent rules and relations of acupuncture and Chinese medicine versus the effectiveness in real practice. A data warehouse is recommended to be set up to store and manage the above evidence processed by appropriate data mining algorithms and models. As the data from different origins is hopefully to be integrated in a clinical decision support system, it will be able to provide evidence-based references and recommendations for the clinical practice of acupuncture and Chinese medicine.

A Novel Deep Model for Biopsy Image Grading

We propose in this paper a deep learning model based on convolutional neural network (CNN) for biopsy image grading. The model outputs a vector of scores indicating presence or severity of the target histopathological characteristics. Within the model, we first design a 7-layer CNN for feature representation and high level concept extraction. Each biopsy image is expressed as a feature vector through our CNN processor. We then place a sigmoid function into the output layer so as to generate a score for each target characteristic. The proposed model is evaluated on a benchmark dataset and a real biopsy image dataset to show its effectiveness.

Treatment for knee osteoarthritis by needlel-medicine of mutual reinforcement school

To introduce the epidemiology and pathogenesis of knee osteoarthritis, review the literature from home and abroad and introduce the research progress of osteoarthritis of the knee. Represent the treatment methods and mechanism of knee osteoarthritis by the needle-medicine of mutual reinforcement of school. The academic thoughts of needle-medicine of mutual reinforcement can be traced to the same origin of traditional medicine on treatment of stasis. Its operation is simple, fewer adverse events, patient compliance is high, it easy to spread.