Computational and Mathematical Methods in Medicine

2011 international joint conference on neural networks (ijcnn)

Over the years, programming languages have grown more powerful, but correspondingly more complex; and while that complexity is fine and appropriate for professional programmers, it hinders and discourages beginning Computer Science students.

Python: the tutorial

There are a number of applications in consumer and industrial products environments in which there is a need to display a message in a restricted space. Two general display methods were compared in the present research using an 8-character horizontal display. Text appeared either as a sequence ofsmall right-to-left jumps ('leading'), or as a sequence of whole or partword patterns (rapid serial visual presentations, RSVP]). Upper versus lower-case letters and slow (171 words per minute, WPM) versus fast (260 WPM) presentation rates were compared. In all conditions, sentences were read more accurately in the RSVP format than in the leading format. Recommendations for future displays of verbal messages are discussed.

Reading text presented on a small display

PURPOSE The accurate prediction of intrafraction lung tumor motion is required to compensate for system latency in image-guided adaptive radiotherapy systems. The goal of this study was to identify an optimal prediction model that has a short learning period so that prediction and adaptation can commence soon after treatment begins, and requires minimal reoptimization for individual patients. Specifically, the feasibility of predicting tumor position using a combination of a generalized (i.e., averaged) neural network, optimized using historical patient data (i.e., tumor trajectories) obtained offline, coupled with the use of real-time online tumor positions (obtained during treatment delivery) was examined. METHODS A 3-layer perceptron neural network was implemented to predict tumor motion for a prediction horizon of 650 ms. A backpropagation algorithm and batch gradient descent approach were used to train the model. Twenty-seven 1-min lung tumor motion samples (selected from a CyberKnife patient dataset) were sampled at a rate of 7.5 Hz (0.133 s) to emulate the frame rate of an electronic portal imaging device (EPID). A sliding temporal window was used to sample the data for learning. The sliding window length was set to be equivalent to the first breathing cycle detected from each trajectory. Performing a parametric sweep, an averaged error surface of mean square errors (MSE) was obtained from the prediction responses of seven trajectories used for the training of the model (Group 1). An optimal input data size and number of hidden neurons were selected to represent the generalized model. To evaluate the prediction performance of the generalized model on unseen data, twenty tumor traces (Group 2) that were not involved in the training of the model were used for the leave-one-out cross-validation purposes. RESULTS An input data size of 35 samples (4.6 s) and 20 hidden neurons were selected for the generalized neural network. An average sliding window length of 28 data samples was used. The average initial learning period prior to the availability of the first predicted tumor position was 8.53 ± 1.03 s. Average mean absolute error (MAE) of 0.59 ± 0.13 mm and 0.56 ± 0.18 mm were obtained from Groups 1 and 2, respectively, giving an overall MAE of 0.57 ± 0.17 mm. Average root-mean-square-error (RMSE) of 0.67 ± 0.36 for all the traces (0.76 ± 0.34 mm, Group 1 and 0.63 ± 0.36 mm, Group 2), is comparable to previously published results. Prediction errors are mainly due to the irregular periodicities between cycles. Since the errors from Groups 1 and 2 are within the same range, it demonstrates that this model can generalize and predict on unseen data. CONCLUSIONS This is a first attempt to use an averaged MSE error surface (obtained from the prediction of different patients' tumor trajectories) to determine the parameters of a generalized neural network. This network could be deployed as a plug-and-play predictor for tumor trajectory during treatment delivery, eliminating the need for optimizing individual networks with pretreatment patient data.

Feasibility of predicting tumor motion using online data acquired during treatment and a generalized neural network optimized with offline patient tumor trajectories.

During radiotherapy treatment for thoracic and abdomen cancers, for example, lung cancers, respiratory motion moves the target tumor and thus badly affects the accuracy of radiation dose delivery into the target. A real-time image-guided technique can be used to monitor such lung tumor motion for accurate dose delivery, but the system latency up to several hundred milliseconds for repositioning the radiation beam also affects the accuracy. In order to compensate the latency, neural network prediction technique with real-time retraining can be used. We have investigated real-time prediction of 3D time series of lung tumor motion on a classical linear model, perceptron model, and on a class of higher-order neural network model that has more attractive attributes regarding its optimization convergence and computational efficiency. The implemented static feed-forward neural architectures are compared when using gradient descent adaptation and primarily the Levenberg-Marquardt batch algorithm as the ones of the most common and most comprehensible learning algorithms. The proposed technique resulted in fast real-time retraining, so the total computational time on a PC platform was equal to or even less than the real treatment time. For one-second prediction horizon, the proposed techniques achieved accuracy less than one millimeter of 3D mean absolute error in one hundred seconds of total treatment time.

/pdf/a-fast-neural-network-approach-to-predict-lung-tumor-motion-4au6ixh1xe.pdf

A Fast Neural Network Approach to Predict Lung Tumor Motion during Respiration for Radiation Therapy Applications

Concept drift robust adaptive novelty detection for data streams

This paper recalls the practical calculation of Learning Entropy (LG) for novelty detection, extends it for various gradient techniques and discusses its use for multivariate dynamical systems with ability of distinguishing between data perturbations or system-function perturbations. LG has been recently introduced for novelty detection in time series via supervised incremental learning of polynomial filters, i.e. higher-order neural units (HONU). This paper demonstrates LG also on enhanced gradient descent adaptation techniques that are adopted and summarized for HONU. As an aside, LG is proposed as a new performance index of adaptive filters. Then, we discuss Principal Component Analysis and Kernel PCA for HONU as a potential method to suppress detection of data-measurement perturbations and to enforce LG for system-perturbation novelties.

Learning entropy for novelty detection a cognitive approach for adaptive filters

Alzheimer's disease is diagnosed via means of daily activity assessment. The EEG recording evaluation is a supporting tool that can assist the practitioner to recognize the illness, especially in the early stages. This paper presents a new approach for detecting Alzheimer's disease and potentially mild cognitive impairment according to the measured EEG records. The proposed method evaluates the amount of novelty in the EEG signal as a feature for EEG record classification. The novelty is measured from the parameters of EEG signal adaptive filtration. A linear neuron with gradient descent adaptation was used as the filter in predictive settings. The extracted feature (novelty measure) is later classified to obtain Alzheimer's disease diagnosis. The proposed approach was cross-validated on a dataset containing EEG records of 59 patients suffering from Alzheimer's disease; seven patients with mild cognitive impairment (MCI) and 102 controls. The results of cross-validation yield 90.73% specificity and 89.51% sensitivity. The proposed method of feature extraction from EEG is completely new and can be used with any classifier for the diagnosis of Alzheimer's disease from EEG records.

/pdf/novelty-detection-based-approach-for-alzheimer-s-disease-and-4uxk8hyk0b.pdf

Novelty detection-based approach for Alzheimer’s disease and mild cognitive impairment diagnosis from EEG

The paper presents new approach to dementia detection in time series of measured EEG. The proposed method introduced in this paper evaluates EEG signal according to included novelty. This novelty is evaluated using prediction error and increment of adaptive weights obtained during adaptive prediction of individual EEG channels. Normalization of learning rate was used for adaptation of predictor. The linear dynamic neuron was used as a predictor with gradient descent adaptation. The method was cross-validated on dataset containing 110 patients suffering with dementia and 110 controls. Best achieved results with our method tested on validation dataset were 90% of specificity and 90% of sensitivity. The achievements and limiting assumptions of this method are discussed as well.

/pdf/adaptive-classification-of-eeg-for-dementia-diagnosis-1zlpcdsuuw.pdf

Matous Cejnek

Papers

A Fast Neural Network Approach to Predict Lung Tumor Motion during Respiration for Radiation Therapy Applications

Concept drift robust adaptive novelty detection for data streams

Learning entropy for novelty detection a cognitive approach for adaptive filters

Novelty detection-based approach for Alzheimer’s disease and mild cognitive impairment diagnosis from EEG

Adaptive classification of EEG for dementia diagnosis