首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 15 毫秒
1.
An effective application is presented of a back-propagation artificial neural network (ANN) in differentiating electro-encephalogram (EEG) power spectra of stressed and normal rats in three sleep-wakefulness stages. The rats were divided into three groups, one subjected to acute heat stress, one subjected to chronic heat stress and one a handling control group. The polygraphic sleep recordings were performed by simultaneous recording of cortical EEG, electro-oculogram (EOG) and electromyogram (EMG) on paper and in digital form on a computer hard disk. The preprocessed EEG signals (after removal of DC components and reduction of base-line movement) were fragmented into 2s artifact-free epochs for the calculation of power spectra. The slow-wave sleep (SWS), rapid eye movement (REM) sleep and awake (AWA) states were analysed separately. The power spectrum data for all three sleep-wake states in the three groups of rats were tested by a back-propagation ANN. The network contained 60 nodes in the input layer, weighted from power spectrum data from 0 to 30 Hz, 18 nodes in the hidden layer and an output node. The ANN was found effective in differentiating the EEG power spectra from stressed to normal spectral patterns following acute (92% in SWS, 85.5% in REM sleep, 91% in AWA state) as well as chronic heat exposure (95.5% in SWS, 93.8% in REM sleep, 98.5% in AWA state).  相似文献   

2.
Beam-orientation customization using an artificial neural network.   总被引:5,自引:0,他引:5  
A methodology for the constrained customization of coplanar beam orientations in radiotherapy treatment planning using an artificial neural network (ANN) has been developed. The geometry of the patients, with cancer of the prostate, was modelled by reducing the external contour, planning target volume (PTV) and organs at risk (OARs) to a set of cuboids. The coordinates and size of the cuboids were given to the ANN as inputs. A previously developed beam-orientation constrained-customization (BOCC) scheme employing a conventional computer algorithm was used to determine the customized beam orientations in a training set containing 45 patient datasets. Twelve patient datasets not involved in the training of the artificial neural network were used to test whether the ANN was able to map the inputs to customized beam orientations. Improvements from the customized beam orientations were compared with standard treatment plans with fixed gantry angles and plans produced from the BOCC scheme. The ANN produced customized beam orientations within 5 degrees of the BOCC scheme in 62.5% of cases. The average difference in the beam orientations produced by the ANN and the BOCC scheme was 7.7 degrees (+/-1.7, 1 SD). Compared with the standard treatment plans, the BOCC scheme produced plans with an increase in the average tumour control probability (TCP) of 5.7% (+/-1.4, 1 SD) whilst the ANN generated plans increased the average TCP by 3.9% (+/-1.3, 1 SD). Both figures refer to the TCP at a fixed rectal normal tissue complication probability (NTCP) of 1%. In conclusion, even using a very simple model for the geometry of the patient, an ANN was able to produce beam orientations that were similar to those produced by a conventional computer algorithm.  相似文献   

3.
An artificial-neural-network-based detector of pharyngeal wall vibration (PWV) is presented. PWV signals the imminent occurrence of obstructive sleep apnoea (OSA) in adults who suffer from OSA syndrome. Automated detection of PWV is very important in enhancing continuous positive airway pressure (CPAP) therapy by allowing automatic adjustment of the applied airway pressure by a procedure called automatic positive airway pressure (APAP) therapy. A network with 15 inputs, one output, and two hidden layers, each with two Adaline nodes, is used as part of a PWV detection scheme. The network is initially trained using nasal mask pressure data from five positively diagnosed OSA patients. The performance of the ANN-based detector is evaluated using data from five different OSA patients. The results show that on the average it correctly detects the presence of PWV events at a rate of ≅92% and correctly distinguishes normal breaths ≅98% of the time. Further, the ANN-based detector accuracy is not affected by the pressure level required for therapy.  相似文献   

4.
We present a novel method for classifying alert vs drowsy states from 1 s long sequences of full spectrum EEG recordings in an arbitrary subject. This novel method uses time series of interhemispheric and intrahemispheric cross spectral densities of full spectrum EEG as the input to an artificial neural network (ANN) with two discrete outputs: drowsy and alert. The experimental data were collected from 17 subjects. Two experts in EEG interpretation visually inspected the data and provided the necessary expertise for the training of an ANN. We selected the following three ANNs as potential candidates: (1) the linear network with Widrow-Hoff (WH) algorithm; (2) the non-linear ANN with the Levenberg-Marquardt (LM) rule; and (3) the Learning Vector Quantization (LVQ) neural network. We showed that the LVQ neural network gives the best classification compared with the linear network that uses WH algorithm (the worst), and the non-linear network trained with the LM rule. Classification properties of LVQ were validated using the data recorded in 12 healthy volunteer subjects, yet whose EEG recordings have not been used for the training of the ANN. The statistics were used as a measure of potential applicability of the LVQ: the t-distribution showed that matching between the human assessment and the network output was 94.37+/-1.95%. This result suggests that the automatic recognition algorithm is applicable for distinguishing between alert and drowsy state in recordings that have not been used for the training.  相似文献   

5.
6.
No doubt a noninvasive technique for detection of cerebral ischemic extent, before the formation of the focus, is extremely valuable. This paper presents a new approach to early evaluate the degree of ischemic injury by combining bispectrum estimation of electroencephalograms (EEGs) with artificial neural network (ANN). The graded ischemic injuries in 24 Sprague-Dawley (SD) rats were induced for different periods of 8, 18, 30 min by infusing physiological saline along the left blood stream, based on the model for rat ischemic cerebral injury described in this paper. Four channels of EEG were collected in each rat at scheduled time of ischemia. The maximum bicoherence index and the weighted center of bispectrum (WCOB) were extracted from the EEGs and were used as input feature vector of a four-layer (12-7-2-1) ANN for prediction. Training and testing the ANN used the 'leave one out' strategy. The levels of ischemic injury were verified and classified by observing the ischemic area by conventional hematoxylin and eosin (HE) staining and the heat shock protein (HSP70) test. The proposed method was able to correctly detect ischemic extent in average accuracy of 91.67% of the cases. The results show that this scheme can be expected to diagnose ischemic cerebral injury in its earlier phases.  相似文献   

7.
At present, algorithms used in nuclear medicine to reconstruct single photon emission computerized tomography (SPECT) data are usually based on one of two principles: filtered backprojection and iterative methods. In this paper a different algorithm, applying an artificial neural network (multilayer perception) and error backpropagation as training method are used to reconstruct transaxial slices from SPECT data. The algorithm was implemented on an Elscint XPERT workstation (i486, 50 MHz), used as a routine digital image processing tool in our departments. Reconstruction time for a 64 x 64 matrix is approximately 45 s/transaxial slice. The algorithm has been validated by a mathematical model and tested on heart and Jaszczak phantoms. Phantom studies and very first clinical results ((111)In octreotide SPECT, 99mTc MDP bone SPECT) show in comparison with filtered backprojection an enhancement in image quality.  相似文献   

8.
Outcome prediction is becoming increasingly important in medicine, but when a resource is scarce the need for accurate prediction becomes acute. Prediction based on biostatistical models has been in use for many years, but in areas such as renal transplantation their results have been disappointing. Recently however, there has been growing interest in the use of artificial neural networks for prediction. The creation of a large database containing high quality data on renal transplantation patients in Wales offers an ideal opportunity to research a new area viz., the ability of these techniques to accurately predict outcomes such as the appearance of disease in transplant recipients or the time to graft failure. This paper describes the use of neural networks to identify patients who risk the development of cytomegalovirus disease--a significant cause of mortality and morbidity in these patients. The neural networks we examined produced overall correct classifications well in excess of 80% in each of the two groups involved, diseased and non-diseased. These predictions are a considerable improvement on current methods and encourage the belief that renal transplantation data may respond well to analysis by neural networks.  相似文献   

9.
Muscle modelling is an important component of body segmental motion analysis. Although many studies had focused on static conditions the relationship between electromyographic (EMG) signals and joint torque under voluntary dynamic situations has not been well investigated. The aim of this study was to investigate the performance of a recurrent artificial neural network (RANN) under voluntary dynamic situations for torque estimation of the elbow complex. EMG signals together with kinematic data, which included angle and angular velocity, were used as the inputs to estimate the expected torque during movement. Moreover, the roles of angle and angular velocity in the accuracy of prediction were investigated, and two models were compared. One model used EMG and joint kinematic inputs and the other model used only EMG inputs without kinematic data. Six healthy subjects were recruited, and two average angular velocities (60o s−1 and 90o s−1) with three different loads (0 kg, 1 kg, 2 kg) in the hand position were selected to train and test the RANN between 90o elbow flexion and full elbow extension (0o). After training, the root mean squared error (RMSE) between expected torque and predicted torque of the model, with EMG and joint kinematic inputs in the training data set and the test data set were 0.17±0.03 Nm and 0.35±0.06 Nm, respectively. The RMSE values between expected torque and predicted torque of the model, with only EMG inputs in the training data set and the test set, were 0.57±0.07 Nm and 0.73±0.11 Nm, respectively. The results showed that EMG signals together with kinematic data gave significantly better performance in the joint torque prediction; joint angle and angular velocity provided important information in the estimation of joint torque in voluntary dynamic movement.  相似文献   

10.
The palmar pinch force estimation is highly relevant not only in biomechanical studies, the analysis of sports activities, and ergonomic design analyses but also in clinical applications such as rehabilitation, in which information about muscle forces influences the physician's decisions on diagnosis and treatment. Force transducers have been used for such purposes, but they are restricted to grasping points and inevitably interfere with the human haptic sense because fingers cannot directly touch the environmental surface. We propose an estimation method of the palmar pinch force using surface electromyography (SEMG). Three myoelectric sites on the skin were selected on the basis of anatomical considerations and a Fisher discriminant analysis (FDA), and SEMG at these sites yields suitable information for pinch force estimation. An artificial neural network (ANN) was implemented to map the SEMG to the force, and its structure was optimized to avoid both under- and over-fitting problems. The resulting network was tested using SEMG signals recorded from the selected myoelectric sites of ten subjects in real time. The training time for each subject was short (approximately 96 s), and the estimation results were promising, with a normalized root mean squared error (NRMSE) of 0.081 ± 0.023 and a correlation (CORR) of 0.968 ± 0.017.  相似文献   

11.
OBJECTIVE: To propose an ensemble model of artificial neural networks (ANNs) to predict cardio-respiratory morbidity after pulmonary resection for non-small cell lung cancer (NSCLC). METHODS: Prospective clinical study was based on 489 NSCLC operated cases. An artificial neural network ensemble was developed using a training set of 348 patients undergoing lung resection between 1994 and 1999. Predictive variables used were: sex of the patient, age, body mass index, ischemic heart disease, cardiac arrhythmia, diabetes mellitus, induction chemotherapy, extent of resection, chest wall resection, perioperative blood transfusion, tumour staging, forced expiratory volume in 1s percent (FEV(1)%), and predicted postoperative FEV(1)% (ppoFEV(1)%). The analysed outcome was the occurrence of postoperative cardio-respiratory complications prospectively recorded and codified. The artificial neural network ensemble consists of 100 backpropagation networks combined via a simple averaging method. The probabilities of complication calculated by ensemble model were obtained to the actual occurrence of complications in 141 cases operated on between January 2000 and December 2001 and a receiver operating characteristic (ROC) curve for this method was constructed. RESULTS: The prevalence of cardio-respiratory morbidity was 0.25 in the training and 0.30 in the validation series. The accuracy for morbidity prediction (area under the ROC curve) was 0.98 by the ensemble model. CONCLUSION: In this series an artificial neural network ensemble offered a high performance to predict postoperative cardio-respiratory morbidity.  相似文献   

12.
Mental stress has been identified as one of the major contributing factors that leads to various diseases such as heart attack, depression, and stroke. To avoid this, stress quantification is important for clinical intervention and disease prevention. This study aims to investigate the feasibility of exploiting electroencephalography (EEG) signals to discriminate between different stress levels. We propose a new assessment protocol whereby the stress level is represented by the complexity of mental arithmetic (MA) task for example, at three levels of difficulty, and the stressors are time pressure and negative feedback. Using 18-male subjects, the experimental results showed that there were significant differences in EEG response between the control and stress conditions at different levels of MA task with p values < 0.001. Furthermore, we found a significant reduction in alpha rhythm power from one stress level to another level, p values < 0.05. In comparison, results from self-reporting questionnaire NASA-TLX approach showed no significant differences between stress levels. In addition, we developed a discriminant analysis method based on multiclass support vector machine (SVM) with error-correcting output code (ECOC). Different stress levels were detected with an average classification accuracy of 94.79%. The lateral index (LI) results further showed dominant right prefrontal cortex (PFC) to mental stress (reduced alpha rhythm). The study demonstrated the feasibility of using EEG in classifying multilevel mental stress and reported alpha rhythm power at right prefrontal cortex as a suitable index.  相似文献   

13.
14.
15.
The lengthy process of manually optimizing a feedforward backpropagation artificial neural network (ANN) provided the incentive to develop an automated system that could fine-tune the network parameters without user supervision. A new stopping criterion was introduced--the logarithmic-sensitivity index--that manages a good balance between sensitivity and specificity of the output classification. The automated network automatically monitored the classification performance to determine when was the best time to stop training-after no improvement in the performance measure (either highest correct classification rate, lowest mean squared error or highest log-sensitivity index value) occurred in the subsequent 500 epochs. Experiments were performed on three medical databases: an adult intensive care unit, a neonatal intensive care unit and a coronary surgery patient database. The optimal network parameter settings found by the automated system were similar to those found manually. The results showed that the automated networks performed equally well or better than the manually optimized ANNs, and the best classification performance was achieved using the log-sensitivity index as a stopping criterion.  相似文献   

16.
17.
Su M  Miften M  Whiddon C  Sun X  Light K  Marks L 《Medical physics》2005,32(2):318-325
A method to predict radiation-induced pneumonitis (RP) using an artificial neural network (ANN) was investigated. A retrospective study was applied to the clinical data from 142 patients who have been treated with three-dimensional conformal radiotherapy for tumors in the thoracic region. These data were classified, based on their treatment outcome, into two patient clusters: with RP (Np=26) and without RP (Np= 116). An ANN was designed as a classifier. To perform the classification, a patient-treatment outcome with RP was assigned a value of 1, and a patient treatment outcome without RP was assigned a value of -1. The input of the ANN was limited to the patient lung dose-volume data only. A volume vector (VD) that describes patient lung subvolumes receiving more than a set of threshold doses was used as the network input variable. A zero value was used as the threshold to set the output value into -1 or 1. Three ANNs (ANN_1, ANN_2, and ANN_3), each with three layers, were trained to perform this classification function and to show the effect of training data on the ANN performance. Radial basis function was applied as the hidden layer neuron activation function and a sigmoid function was selected as the output layer neuron function. Backpropagation with a conjugate gradient algorithm was used to train the network. ANN_1 was trained and tested by using the leave-one-out method. ANN_2 was trained by randomly selecting 2/3 of the patient data, and tested by the remaining 1/3 of the data. ANN_3 was trained by a user selecting 2/3 of the patient data, and tested by the remaining 1/3 of the data. The predictive accuracy was verified as the area under a receiver operator characteristic (ROC) curve. The correct classification rates of 73% for RP cases, and 99% for non-RP cases were obtained from ANN_1. The corresponding correct classification rates of 44% for RP cases, and 89% for non-RP cases were obtained from ANN_2. From the ANN_3 test phase, the corresponding correct classification rates of 55% for RP cases, and 95% non-RP cases were achieved. The area under ROC curve was 0.85+/-0.05, 0.68+/-0.10, and 0.81+/-0.09 for ANN_1, ANN _2, and ANN_3, respectively, within its asymmetric 95% confidence interval. The sensitivity was 95%, 57%, and 71%, and the specificity was 94%, 88%, and 90% for ANN_1, ANN_2, and ANN_3, respectively. Preliminary results suggest that the ANN approach provides a useful tool for the prediction of radiation-induced lung pneumonitis, using the patient lung dose-volume information.  相似文献   

18.
The CT scanner-displayed radiation dose information is based on CT dose index (CTDI) over an integration length of 100 mm (CTDI(100)), which is lower than the CTDI over an infinite integration length (CTDI(∞)). In an adult or a pediatric body CT scan, the limiting equilibrium dose can be established near the central scan plane, and CTDI(∞) more closely indicates the accumulated dose than CTDI(100). The aim of this study was to (a) evaluate CTDI efficiencies, ?(CTDI(100)) = CTDI(100)/CTDI(∞), for a multi-detector CT (MDCT) scanner, (b) examine the dependences of ?(CTDI(100)) on kV, beam width, phantom diameter, phantom length and position in phantom and (c) investigate how to estimate CTDI(∞) based on the CT scanner-displayed information. We performed a comprehensive Geant4-based simulation study of a clinical CT scanner, and calculated ?(CTDI(100)) for a range of parameters. The results were compared with the ?(CTDI(100)) data of previous studies. Differences in the ?(CTDI(100)) values of these studies were assessed. A broad analysis of the ?(CTDI(100)) variations with the above-mentioned parameters was presented. Based on the results, we proposed a practical approach to obtain the weighted CTDI(∞) using the CT scanner-displayed information. A reference combination of 120 kV and a beam width close to 20 mm can be selected to determine the efficiencies of the weighted CTDI by using either phantom measurements or computer simulations. The results can be applied to estimate the weighted CTDI(∞) for 80-140 kV and the beam widths within 40 mm. Errors in the weighted CTDI(∞) due to the variations of kV and beam width can be 5% or less for the MDCT scanners.  相似文献   

19.
AIMS: Although the characteristic of invasive pattern which contributes to Jass's classification is a sensitive prognostic marker in rectal cancer, reproducibility of its assessment has been shown to be problematic. As another histological parameter of invasive margin, we examined the prognostic significance of tumour 'budding' and attempted to establish its appropriate criteria. METHODS AND RESULTS: A total of 638 rectal cancer specimens was examined. We defined tumour 'budding' as an isolated single cancer cell or a cluster composed of fewer than five cancer cells. We divided these into two groups by their intensity, i.e. the number of 'budding' foci within a microscopic field of x 250. Rectal cancer with high-grade 'budding' (>or= 10 foci in a field) was observed in 30.1% of patients, and was associated with lower 5-year survival rates (40.7%) than patients with low-grade 'budding' (84.0%) (P < 0.0001). Based on multivariate analysis, tumour 'budding' was selected as the significant independent variable, together with the number of nodes involved, extramural spread, lymphocytic infiltration, apical nodal involvement and tumour differentiation. Kappa coefficient of two-graded tumour 'budding' in the intraobserver study was 0.84. CONCLUSIONS: Because of its value as a prognostic indicator and its reproducibility, tumour 'budding' would be a good index to estimate the aggressiveness of rectal cancer.  相似文献   

20.
Impedance cardiography is a low-cost noninvasive technique, based on monitoring of the thoracic impedance, for estimation of stroke volume (SV). Impedance cardiogram (ICG) is the negative of the first derivative of the impedance signal. A technique for beat-to-beat SV estimation using impedance cardiography and artificial neural network (ANN) is proposed. A three-layer feed-forward ANN with error back-propagation algorithm is optimized by examining the effects of number of neurons in the hidden layer, activation function, training algorithm, and set of input parameters. The input parameters are obtained by automatic detection of the ICG characteristic points, and the target values are obtained by beat-to-beat SV measurements from time-aligned Doppler echocardiogram. The technique is evaluated using an ICG-echocardiography database with recordings from subjects with normal health in the under-rest and post-exercise conditions and from subjects with cardiovascular disorders in the under-rest condition. The proposed technique performed much better than the earlier established equation-based estimations, and it resulted in correlation coefficient of 0.93 for recordings from subjects with cardiovascular disorders. It may be helpful in improving the acceptability of impedance cardiography in clinical practice.
Graphical abstract ?
  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号