Search

We introduce a method to extract the photoacoustic (PA) signal from a contrast reduction of the interference spectrum acquired by spectral domain optical coherence tomography (SDOCT). This all-optical detection is achieved in a noncontact manner directly on the water surface covered on the sample by using its specular reflection. During SDOCT exposure, the phase of the interference spectrum keeps shaking according to the water surface vibration induced by PA excitation. This results in an interference contrast reduction which is quantified by a fast Fourier transform (FFT) for PA imaging. A tungsten filament, asparagus fern leaf, and mouse auricle are imaged to demonstrate the method.

The temperature distribution of normal human skin is symmetrical. Facial paralysis generally changes this thermal symmetry. The aim of this study is to analyze facial thermal asymmetry during the early onset of Bell's palsy, and to assess the feasibility of the diagnosis of early-onset Bell's palsy using infrared thermography (IRT). Fifteen subjects with Bell's palsy and 15 healthy volunteers were considered in this study. The infrared thermal images of the front, left, and right sides of all the subjects were collected and analyzed. Each group of facial thermograms was divided into 16 symmetrical regions of interest (ROIs) with respect to the left and right sides. Three different temperature difference calculation methods were used to express the degree of thermal symmetry between the left- and right-side ROIs, namely, the mean temperature difference (ΔTroi), maximum temperature difference (ΔTmax), and minimum temperature difference (ΔTmin). Among the facial ROIs, there were significant differences in the thermal symmetries of the frontal region, medial canthus region, and infraorbital region between subjects with and without Bell's palsy (p

Artificial intelligence is a discipline which focuses on the study of simulating and extending human intelligence, while machine learning (ML) is one of the most rapidly developing subfields of AI research. The research of ML in the field of traditional Chinese medicine (TCM), has a bright prospect, as well as a profound significance. To explore the feasibility of using ML methods to approximate the diagnosis of TCM, support vector machine (SVM) is introduced and investigated for syndrome element differentiation of TCM in this paper. Based on 670 medical records, SVM was used to approximate the mapping relations between inputs (set of clinical manifestations) and outputs (set of syndrome elements). The value orders of syndrome elements were adopted to evaluate the approximation results, while attribute partial order structure diagram was employed to discover and visualize the knowledge of the records. Back propagation neural network (BPNN) and extreme learning machine (ELM), as comparative methods, were also employed to deal with the medical data. The value order’s matching results between real and predicted results shows that, for SVM, the matched degree of each record is no less than 65%, while there are at least 88% records whose matched degree is more than 80%; and for BPNN and ELM, the highest proportion of records whose matched degree is more than 80% is only 45%. Using methods of ML to approximate the diagnosis of TCM should be feasible, and more relevant research can be conducted in the future.

In recent years, machine learning, deep learning, neural network and other artificial intelligence technologies have made significant development and breakthroughs. Thus more mature and reliable technologies start to be applied in the field of data analysis. Data analysis is the process of studying and summarizing data in detail in order to extract useful information, that is, collecting, sorting, processing and analyzing data. Moreover, in order to make the analysis results easier to understand, data visualization technology is widely employed. This paper tries to review the state-of-the-art data analysis methods based on artificial intelligence. Besides, the mainstream data visualization technology and cases are elaborated. Finally, some open problems and challenges are also put forward for the future research.

Infrared thermography (IRT), as a noncontact tool for temperature measurement, is widely applied in the study of acupuncture modernization. The aim of this study was to assess the intra- and interrater reliability of infrared image analysis of facial acupoints of subjects with facial paralysis and determine the factors influencing the variability of the measured values. A total of 26 patients with facial paralysis on one side, aged 26 to 53 years, participated voluntarily in the study. Facial infrared thermal images of all participants were analyzed by two trained raters at two different time points at a one-week interval. The intraclass correlation coefficient (ICC) was used to determine the intra- and interrater reliability of IRT measurements. The ICC values varied depending on the analyzed acupoints. The reliability of temperature measurement ranged from moderate to excellent (intrarater, ICC ranged from 0.669 to 0.990; interrater, ICC ranged from 0.661 to 0.987). The reliability of temperature difference measurement ranged from low to excellent (intrarater, ICC ranged from 0.412 to 0.882; interrater, ICC ranged from 0.334 to 0.828). The main influencing factor of reliability is the incomplete consistency in selecting acupoint positions when repeatedly positioning the same acupoint manually. Despite low reliability of temperature difference measurement at some acupoints, some auxiliary measures can be used to reduce the error of manual positioning. Thus, infrared thermal imaging still has the potential to assist in objective and quantitative research on acupuncture.

this paper focuses on the syndrome name generation method of syndrome differential based on the traditional Chinese medicine (TCM) theory. Based on the theory of TCM diagnosis, a multi-hierarchies complex model of Disease-Syndrome-Symptom has been established. Using the quantitative method, the model of three-dimensional knowledge base which expresses the relationships between syndromes and syndrome elements has been built. By targeting the clinical request for TCM diagnosis, a new method of generating the syndrome name of TCM diagnosis has been proposed based on the expression theory of structural partial-ordered attribute diagram. By using a series of heart diseases as the formal context, the TCM diagnosis knowledge has been discovered by the structural partial-ordered attribute diagram. Experiment demonstrates that the structural diagram can clearly express the relationships between syndrome name and syndrome element without crossover. The generated syndrome name is consonant with the theory of TCM diagnosis, the efficiency and validity of this method has been certificated.

Optical coherence tomography (OCT) angiography is a noninvasive imaging modality that produces volumetric views of blood flow perfusion in vivo with resolution at capillary level, which has been widely adopted to monitor cerebral perfusion status after stroke in experimental settings. Accurate quantification of cerebral perfusion from OCT angiograms is important for understanding the cerebral vascular pathophysiology and assessing the treatment of ischemic stroke. Quantification of blood vessels from OCT angiography faces some problems; one is uneven backscatter (which causes some blood vessels to be very bright, some very dark), and the other is that the brightness in the same blood vessel also changes due to the difference in diameter or depth. In this paper, we proposed a locally adaptive region growing algorithm to solve this problem. The algorithm, which confines the region growing process to a local region, is used to segment blood vessels in different images to cope well with the intensity changes in blood vessels. During segmentation, the initial seed pixels were selected with the aid of the Otsu algorithm, the growth criterion considered both global and local information, and the thresholds were also adjusted adaptively as local regions varied. After these processes are completed, we can calculate the percentage of segmented blood vessels across field of view of the images, named cerebral vascular perfusion density, and use it as an indicator to evaluate the cerebral blood perfusion of middle cerebral artery occlusion in mice. This paper demonstrates that the algorithm can produce satisfactory vascular segmentation results, and CVPD can be used as an effective indicator for evaluating post-ischemic injury.

To guarantee accurate predictions, representative samples are needed when building a calibration model for spectroscopic measurements. However, in general, it is not known whether a sample is representative prior to measuring its concentration, which is both time-consuming and expensive. In this paper, a method to determine whether a sample should be selected into a calibration set is presented. The selection is based on the difference of Euclidean norm of net analyte signal (NAS) vector between the candidate and existing samples. First, the concentrations and spectra of a group of samples are used to compute the projection matrix, NAS vector, and scalar values. Next, the NAS vectors of candidate samples are computed by multiplying projection matrix with spectra of samples. Scalar value of NAS is obtained by norm computation. The distance between the candidate set and the selected set is computed, and samples with the largest distance are added to selected set sequentially. Last, the concentration of the analyte is measured such that the sample can be used as a calibration sample. Using a validation test, it is shown that the presented method is more efficient than random selection. As a result, the amount of time and money spent on reference measurements is greatly reduced.

The optical attenuation coefficient (OAC) reflects the optical properties of various tissues or tissues of the same type under different physiological conditions. Quantitative measurement of OAC from optical coherence tomography (OCT) signals can provide additional information and can increase the potential for OCT applications. We present an optimized depth-resolved estimation (ODRE) method that derives a precise mapping between the measured OCT signal and the OAC. In contrast to previous depth-resolved estimation (DRE) methods, the optimized method can estimate the OAC in any depth range and ignore whether the light is completely attenuated. Numerical simulations and phantom experiments are used to verify its validity, and this method is applied to detect cerebral damage. In combination with OCT angiography, real-time observation of the change of blood perfusion and the degree of cerebral damage in mice with focal cerebral ischemia provides important information to help us understand the temporal relationship between brain damage and ischemia.

Facial paralysis is a condition causing decreased movement on one side of the face. A quantitative, objective, and reliable assessment method would be an invaluable tool for clinicians treating patients with this condition. This paper presents a novel framework for objective assessment of facial paralysis based on patient infrared thermal image. Facial feature localization is discussed based on facial temperature distribution specificity and edge detection. An algorithm is presented to process the infrared thermal image to obtain the facial temperature distribution features in the relevant facial regions. Three classification methods are applied to provide quantitative evaluations of facial nerve function based on the House-Brackmann scale. Experiments show infrared thermal imaging can be used as an effective tool for the automatic assessment of facial nerve function.

Formalizing of the coding rules of clinical terminology on Traditional Chinese Medicine (TCM) is an important aspect of medical information mining and has attracted interests of researchers in such diverse fields as information visualization and formal concept analysis (FCA). The main purpose of this paper is to show the use of FCA to formalize and visualize the dependencies of TCM clinical terminology. First, the TCM term and its description are defined as the object and attribute, then the hierarchical relationships of TCM terms has been formalized by concept lattice, finally anonymous nodes and non-disjoint nodes are employed for auditing the completeness, consistency and correctness of the coding rules of TCM terminology. The proposed method is validated by experiments with the case study, which demonstrates that it should be possible to produce a FCA-based method of formalizing and auditing the semantic completeness of TCM terminology.

Attribute Topology (AT) is a simple and visual representation method of formal concept. By AT, the formal concept can be computed visually and parallel. Attribute partial ordered structure diagram (APOSD) is based on the partial order relationships in math and focus on the cover and inclusion among attributes. Although AT and APOSD have already achieved mutual transformation, the definition and characteristics of attribute is not universal. This paper mainly analysis and compares the definition of attributes in AT and in APOSD, and demonstrate the equivalence of correspondingly attributes.

Traditional Chinese Medicine (TCM) prescription is the text of TCM clinical records, which is a model for studying the characteristics of TCM clinical experience and differentiation of TCM, and is an important information source for the study of the academic experience of famous doctors of TCM. For the sake of modernizing and standardizing of the study of TCM, and study the law of diagnosis and treatment of TCM using modern knowledge discovery and data mining technology, this paper presents a design scheme of printed TCM prescription recognition and filing System based on Microsoft Office Document Imaging (MODI) Optical Character Recognition (OCR) engine, which can extract information from the printed paper prescription, save the information into database, and provide interface to manage the information and file the prescription. It is an important method for inheriting the Chinese medicine experience, especially the experience of famous doctors' diagnosis and treatment of disease.

Inquiring diagnosis of Traditional Chinese medicine is one of the basic methods for diagnosing disease. Inquiry can collect the most extensive clinical information of patient. It can get many of disease information which can't be got by any other method. This paper presents a complex system model for inquiring diagnosis based on the combination of formal concept analysis theory and Traditional Chinese medicine. Computerized inquiring diagnosis system gets scores of symptoms and syndrome elements through voice interactive way between human and the system. In accordance with principles of formal concept analysis, the system generates the name of syndrome (ZHENG) and the corresponding reference treatment advices. The preliminary experimental result shows that the inquiring diagnosis system is effective and feasible.

It is crucial for an instrumentation to have an efficient method of measurement signal analysis. Especially there are multiple sensors in the instrumentation, i.e. the multi-sensor information fusion. In recent years, we intend to discover a new method of multi-source massive data analysis. Based on the research of Formal Concept Analysis theory, we proposed the Hierarchical Concept Graph Model for massive data analysis. In this paper, we briefed the theory of Formal Concept Analysis and Hierarchical Concept Graph Model, and then we represented the result of the application about our theory in massive dataset analysis. The result of our former research has demonstrated that our theory has the potential to be applied in measurement signal analysis.