Volume 12, Issue 2

At present, there is no need to convince anyone that menisci are crucial structures dealing with a huge number of responsibilities, and its absence in a knee joint results in irretrievable chondral damage. A lot of methods have been recently developed to treat meniscal tears: physical therapy as a first and, for some cases, a last step, bonding by biodegradable sutures, screws, or arrows, collagen and polyurethane scaffolds designed for partial meniscus replacement, and finally allograft transplantation. However, all of them have numerous limitations and can be used in specific conditions only. That is the reason why partial and total meniscectomy is up to this time a common operation in the case of degenerative or complex meniscus tears despite its well-known degenerative consequences. Trials to overcome those limitations are ongoing, and the challenge to invent a long-term successful regeneration method or to design a substitute that well mimics an anatomical meniscus is still in front of us.

It is well known that the structure of neural network and the amount of available training data influence the accuracy of developed models; however, the exact character of this relation depends on the chosen problem. Thus, it was decided to analyze what impact these parameters have on the solution of the problem on which we work – the prediction of final height of children treated with growth hormone. It was observed that multilayer perceptron with a wide range of numbers of hidden neurons (from 1 to 100) could solve the problem almost equally well. Thus, this task seems to be rather simple, not requiring complex models. Larger networks tended to produce less accurate results and did not generalize well while working with the data not used in training. Repeating the experiment with the training data set reduced to 50% of its original content, as expected, caused a decrease in accuracy.

Arterial blood pressure (ABP) waveforms provide plenty of pathophysiological information about the cardiovascular system. ABP pulse analysis is a routine process used to investigate the health status of the cardiovascular system. ABP pulses correspond to the contraction and relaxation phenomena of the human heart. The contracting or pumping phase of the cardiac chamber corresponds to systolic pressure, whereas the resting or filling phase of the cardiac chamber corresponds to diastolic pressure. An ABP waveform commonly comprises systolic peak, diastolic onset, dicrotic notch, and dicrotic peak. Automatic ABP delineation is extremely important for various biomedical applications. In this paper, a delineator for onset and systolic peak detection in ABP signals is presented. The algorithm uses a recently developed empirical wavelet transform (EWT) for the delineation of arterial blood pulses. EWT is a new mathematical tool used to decompose a given signal into different modes and is based on the design of an adaptive wavelet filter bank. The performance of the proposed delineator is evaluated and validated over ABP waveforms of standard databases, such as the MIT-BIH Polysomnoghaphic Database, Fantasia Database, and Multiparameter Intelligent Monitoring in Intensive Care Database. In terms of pulse onset detection, the proposed delineator achieved an average error rate of 0.11%, sensitivity of 99.95%, and positive predictivity of 99.92%. In a similar manner for systolic peak detection, the proposed delineator achieved an average error rate of 0.10%, sensitivity of 99.96%, and positive predictivity of 99.92%.

Component analysis is one of the most important methods used for electroencephalographic (EEG) signal decomposition, and the so-called independent component analysis (ICA) is commonly used. The main function of the ICA algorithm is to find a linear representation of non-Gaussian data whose elements are statistically independent or at least as independent as possible. There are many commercial solutions for EEG signal acquisition. Usually, together with the EEG, one gets a dedicated software to handle the signal. However, quite often, the software does not provide researchers with all necessary functions. A high-performance, dense-array EGI-EEG system is distributed with the NetStation software. Although NetStation is a powerful tool, it does not have any implementation of the ICA algorithm. This causes many problems for researchers who want to export raw data from the amplifier and then work on it using some other tools such as EEGLAB for MATLAB, as these data are not fully compatible with the EGI format. We will present the C++ implementation of ICA that can handle filtered data from the EGI with better affordability. Our tool offers visualization of raw signal and ICA algorithm results and will be distributed under Freeware license.

One of the most common stomatognathic system dysfunctions on the skeletal level is the maxilla’s narrowing. It is distinguished by front-teeth crowding, protrusion of the lower teeth past the front teeth, as well as a high-arched palate. The key method of orthodontic treatment of this pathology is applying dental braces with the palatal extension system working on the skeletal level. The most popular device is the Biederman appliance with the Hyrax screw, designed before the era of technological progress. As a result, the aim of the project was to present new constructional solutions for devices applied in cases of quick palatal suture expansion. Two biocompatible material solutions were prepared for the key part of the device – the screw. A comparative tension analysis with the use of two titanium alloys (Ti-13Nb-13Zr and Ti-6Al-4V) has been performed by means of the finite-element method.

In the artificial neural network field, no universal algorithm of modeling ensures obtaining the best possible model for a given task. Researchers frequently regard artificial neural networks with suspicion caused by the lack of repeatability of single experiments. We propose a systematic approach that may increase the probability of finding the optimal network architecture. In the experiments, the average effectiveness in groups of networks rather than single networks should be compared. Such an approach facilitates the analysis of the results caused by changes in the network parameters, while the influence of chance effects becomes negligible. As an example of this protocol, we present optimization of a neural network applied for prediction of persistent facial pain in patients operated for chronic rhinosinusitis. In the stepwise approach, the percentage of correct predictions was gradually increased from 54% to 75% for the external validation set.

As the contribution of specific parameters is not known and significant intersubject variability is expected, a decision system allowing adaptation for subject and environment conditions has to be designed to evaluate biomedical signal classification. A decision support system has to be trained in its desirable functionality prior to being used for patient monitoring evaluation. This paper describes a decision system based on data mining with Random Forests, allowing the adaptation for subject and environment conditions. This methodology may lead to specific system scoring by an artificial intelligence-supported patient monitoring evaluation system, which may help find a way of making decisions concerning future treatment and have influence on the quality of patients’ life.