RESUMO
A non-invasive deep learning method is proposed for reconstructing arterial blood pressure signals from photoplethysmography signals.The method employs U-Net as a feature extractor,and a module referred to as bidirectional temporal processor is designed to extract time-dependent information on an individual model basis.The bidirectional temporal processor module utilizes a BiLSTM network to effectively analyze time series data in both forward and backward directions.Furthermore,a deep supervision approach which involves training the model to focus on various aspects of data features is adopted to enhance the accuracy of the predicted waveforms.The differences between actual and predicted values are 2.89±2.43,1.55±1.79 and 1.52±1.47 mmHg on systolic blood pressure,diastolic blood pressure and mean arterial pressure,respectively,suggesting the superiority of the proposed method over the existing techniques,and demonstrating its application potential.
RESUMO
Objective:To introduce the local human body metabolic rate measurement system based on the Smartphone with the Android operating system and realizes the transmission of physiological data from the detecting module to Smartphone. Methods:Embedding Bluetooth module in the module of detecting physiological parameters, the measurement target is fingers, so the detected physiological data can be sent to Smartphone with Android system. By develop apk application program, the Smartphone can realize the operation of opening the Bluetooth devices and searching the around Bluetooth devices, to realize the data transmission by the Socket connection, we develop the software which realizes showing data. Results:The Smartphone received the metabolic rate parameters from Bluetooth, and show the result on the surface. A study of the technology of transmitting physiological parameters information through the interface of Bluetooth in Android Smartphone is made in this paper. Conclusion:The paper is based on the Mobile Medicine Measuring System, realizes the technology of physiological parameters transmission through Bluetooth in Android system, which has a great broad application.
RESUMO
Lung cancer is the most common tumor and one of the malignant tumors with the lowest livability after diagnosis, as is known so far. Large-scale image database is the foundation of developing computer-aided diagnosis methods, education and training in lung cancer diagnosis to improve medical diagnostic efficiency and to reduce the doctors' burden. In this study, aiming at improving the low data storage efficiency and solving the lacking of tool for data visualization and data retrieval existing in the use of traditional Lung Image Database Consortium (LIDC) from the lung cancer database, we developed a new lung cancer image database platform including an improved data model, a data integration tool, an image and annotation visualization tool and a data retrieving component. Firstly, the data format in LIDC was analyzed and an improved information model was provided to manage and manipulate large amount data stored in it. Next, some tools such as data integration component, DICOM, image and annotation visualization tool, and data query were designed and implemented. The study demonstrated that the lung cancer image database platform had the capacity of data collection, visualization, and query, and could promote diagnose lung cancer research.
Assuntos
Humanos , Algoritmos , Bases de Dados Factuais , Diagnóstico por Computador , Armazenamento e Recuperação da Informação , Métodos , Neoplasias Pulmonares , Diagnóstico por Imagem , Patologia , Interpretação de Imagem Radiográfica Assistida por Computador , Métodos , Tomografia Computadorizada por Raios X , Métodos , Padrões de ReferênciaRESUMO
Objective: Develop an assistant diagnosis system for arrhythinias which can reduce doctors' workload and improve their veracity of diagnosing ECG. Methods: Firstly, this paper achieves filter and detection of waves using wavelet transform and extracts parameters; Secondly, it reduces parameters using rough set and identifies arrhythmias according to relevant rules; At last, it gets the membership of abnormal heart beat by fuzzy neural network. Results: The main modules such as filter, detection of waves and identification of arrhythmias are achieved well, and a complete system is formed. Conclusions: This system can identify nineteen arrhythmaias and get their membership and position. It could assist doctors in making the proper diagnosis on ECG potentially.
RESUMO
Objective:The abstraction of characteristics in CT perfusion image is crucial in the clinical diagnosis of brain infarction and cerebral tumor.Methods:After describing the relevant parameters of CT cerebral perfusion imaging,such as cerebral blood flow (CBF),cerebral blood volume (CBV),the mean transition time (MTT) and the permeability surface (PS).With using Visual C ++ programming and CT scan images sequence obtained,the time-density curves of the brain tumor region were visualized.The more accurate hemodynamic parameters were calculated through an improved algorithm basing on the deconvolution and measuring method of the length,angle,area and other parameters.Conclusion:The quantitative analysis of feature parameter is of great benefit to clinical doctor in making timely diagnosis and treatment of brain tumor.
RESUMO
Ultrasound based tissue thermal lesion non-invasive detection is of great significance in high intensity focused ultrasound (HIFU) clinical application. In this paper, we propose a sub-pixel method to quantify the ultrasound image change caused by HIFU as correlation-distance. The support vector machine (SVM) was trained by using correlation distance as samples, and the recognition effect was tested. Results showed that sub-pixel cross-correlation vector field could reflect the ablation lesions position. SVM based classification method can recognize HIFU beam lesion degree effectively.
Assuntos
Humanos , Algoritmos , Diagnóstico por Imagem , Métodos , Ablação por Ultrassom Focalizado de Alta Intensidade , Reconhecimento Automatizado de Padrão , Métodos , Máquina de Vetores de SuporteRESUMO
Noninvasive detection of tissue lesion is an important aided way in the process of high intensity focused ultrasound (HIFU) treatment. A new method is proposed for noninvasive detection of tissue lesion based on self-organizing maps (SOM) network. Tissue lesion, created by HIFU exposures, inevitably leads to change in B-mode image, since some new interfaces will appear in tissue. The difference-sub-image near focus of HIFU, where the tissue lesion appears, is used. Feature of lesion in difference-sub-image is extracted using the method based on SOM network. Experimental results show that the performance of the method proposed in this paper is better than that of others, such as the methods based on average gray, energy and standard deviation of difference-sub-image.
Assuntos
Humanos , Ablação por Ultrassom Focalizado de Alta Intensidade , Neoplasias , Terapêutica , Redes Neurais de Computação , Processamento de Sinais Assistido por ComputadorRESUMO
Objective To design an ECG Holter system based on wireless data communication. Methods The system utilized low power microcontroller MSP430F149 to achieve wireless data transmission by module MC35I. ECG data which stored temporarily in SD card were transmitted in the form of SMS through wireless networks. The received messages were converted into intact files of ECG by data integration. Results It realizes ECG playback, analysis and can send messages automatically to inform relatives and doctors. Conclusion The preliminary clinical application indicates that the Holter has stable performance and strong anti-interference ability, and especially suitable for critical patient care.
RESUMO
Objective To present a method based on wavelet transform for detecting the QRS complexes of electrocardio-gram(ECG) without preprocessing.Methods By comparing three different kinds of wavelets,the first derivative of Gaussian function wavelet whose coefficient of wavelet is more sensitive adopted for MIT-BIH Arrhythmia Database which is widely and internationally accepted in the end.The catastrophe points of QRS complexes are detected by time-frequency analyz-ing.Results The method is proved to be precise and effective by applied to detect the QRS complexes of the ECG record provided by MIT-BIH.Conclusion The method is satisfied real time of ECG monitoring system and has preferable potential application.
RESUMO
Objective To develop an ECG telemonitoring system which can meet many needs of cardiopaths with enjoying medical care out of hospitals.Methods The signals of collection and pretreatment in ECG105 that were transmitted to the computer through serial port,the computer's powerful functions in analyzing and processing signal were utilized fully to design ECG telemonitoring system based on virtual instrument by LabVIEW.Results The system can redisplay and analyze the stored signal and judge whether the heart rate is abnormal,and implement ECG data remote transmission.Conclusion The display,storage,redisplay,diagnosis and tekecommunications of ECG can be achieved conveniently and provide convenience for many cardiopaths with its powerful functions and low cost.
RESUMO
Objective To design LCD system based on MSP430 using LCD controller S1D13700. Methods MSP430's control bus adopted the communication mode of MSC-51 singlechips, and was connected with S1D13700 by 8-bit data bus. The address buses were linked by the modes of indirect address and direct address respectively. Results The design was used for displaying cardiac wave and its parameters in cardiac monitor successfully. Conclusion The S1D13700's driver program, accomplished with standard ANSI-C, is gifted with brilliant versatility, and thus can be used in the design of the portable device.
RESUMO
Dual-kilovolt technique was realized in dual energy X-ray imaging system with computer controlled KV adjustment, filter switching and image acquirement. The dual energy images can be obtained in 2-3 seconds to avoid moving artifact. Low energy photons in high energy X-ray beam can be attenuated effectively by a 2 mm Cu filter to separate the spectra of the high and low energy X-rays. A simplified dual energy decomposition method was used to obtain the soft tissue image. An example of chest dual energy radiographs is presented to illustrate the performance of the system.
Assuntos
Humanos , Imagem Radiográfica a Partir de Emissão de Duplo Fóton , Métodos , Radiografia Torácica , Processamento de Sinais Assistido por ComputadorRESUMO
This paper deals with a portable monitor system on liquid crystal display (LCD) based on this available ordinary ECG machine, which is low power and suitable for China's specific condition. Apart from developing the overall scheme of the system, this paper also has completed the design of the hardware and the software. The 80c196 single chip microcomputer is taken as the central microprocessor and real time electrocardiac single is data treated and analyzed in the system. With the performance of ordinary monitor, this machine also possesses the following functions: five types of arrhythmia analysis, alarm, freeze, and record of automatic pappering, convenient in carrying, with alternate-current (AC) or direct-current (DC) powered. The hardware circuit is simplified and the software structure is optimized in this paper. Multiple low power designs and LCD unit design are adopted and completed in it. Popular in usage, low in cost price, the portable monitor system will have a valuable influence on China's monitor system field.
Assuntos
Humanos , Arritmias Cardíacas , Fenômenos Fisiológicos Cardiovasculares , Eletrocardiografia , Desenho de Equipamento , Cristais Líquidos , Microcomputadores , Monitorização Fisiológica , SoftwareRESUMO
This paper has reviewed the development of artificial intelligence in medical practice and medical diagnostic expert systems, and has summarized the application of artificial neural network. It explains that a source of difficulty in medical diagnostic system is the co-existence of multiple diseases--the potentially inter-related diseases. However, the difficulty of image expert systems is inherent in high-level vision. And it increases the complexity of expert system in medical image. At last, the prospect for the development of artificial intelligence in medical image expert systems is made.
Assuntos
Inteligência Artificial , Teorema de Bayes , Diagnóstico por Imagem , Sistemas Inteligentes , Redes Neurais de ComputaçãoRESUMO
Objective To design a computer aided method in HIFU treatment system to monitor the size,shape and location of HIFU lesion automatically.Methods According to ultrasound image's characters of high noise,low resolution and weak edge,a double zero level set,double speed approach was proposed to extract the contour of organ and lesion area.The serial "lice" contours were used to reconstruct three dimension(3D) HIFU lesion area in the sample.Results Experiments show that level set contour extraction method based 3D reconstruction is helpful in monitoring the size,shape and location in the organ.Conclusion This method has the feasibility to be introduced as an auxiliary technique monitoring HIFU lesion area automatically.