Critical Reviews in Biomedical Engineering最新文献

Since the coronavirus came into existence and brought the entire world to a standstill, there have been drastic changes in people's lives that continue to affect them even as the pandemic recedes. The isolation reduced physical activity and hindered access to non-COVID related healthcare during lockdown and the ensuing months brought increased attention to mental health and the neurological disorders that might have been exacerbated. One nervous system disorder that affects the elderly and needs better awareness is Parkinson's disease. We have machine learning and a growing number of deep learning models to predict, and detect its onset; their scope is not completely exhaustive and can still be optimized. In this research, the authors highlight techniques that have been implemented in recent years for prediction of the disease. Models based on the less redundantly used classifiers-naive Bayes, logistic regression, linear-support vector machine, kernelizing support vector machine, and multilayer perceptron-are initially implemented and compared. Based on limitations of the results, an ensemble stack model of hyper-tuned versions using GridSearchCV out of the top performing supervised classifiers along-with extreme gradient boosting classifier is implemented to further improve overall results. In addition, a convolutional neural network-based model is also implemented, and the results are analyzed using two epoch values to compare the performance of deep learning models. The benchmark datasets-UCI Parkinson's data and the spiral and wave datasets-have been used for machine and deep learning respectively. Performance metrics like accuracy, precision, recall, support, and F1 score are utilized, and confusion matrices and graphs are plotted for visualization. 94.87% accuracy was achieved using the stacking approach.

Cancer has been the deadliest of diseases since decades constituting a large number of deaths annually. Lung cancer remains one of the most significant public health issues, accounting for a substantial proportion of cancer-related deaths globally. Despite ongoing efforts to curb the instances of lung cancer, India continues to see a high number of new diagnoses each year, estimated to be 70,000. Early detection of lung cancer can be difficult due to its asymptomatic nature in its initial stages. However, advancements in technology have given rise to computer-aided diagnostic systems to help overcome this challenge. These systems employ a variety of techniques, such as machine learning, deep learning, image analysis, and text mining, to accurately determine the presence of lung cancer. In an effort to create a more advanced model for lung cancer diagnosis, this study proposes the integration of machine learning algorithms, ensemble learning techniques, and particle swarm optimization to assess the outcomes. The results of the study suggest that the ensemble learning approach outperforms traditional machine learning techniques in terms of accuracy.

Tongue diagnosis is used in various traditional medicine cultures as a non-invasive method for assessing an individual's health. Tongue image analysis has the potential for assessing the metabolism and functionality of the internal organs, making it a quick method of diagnosis. As automated systems give quantitative and objective results thereby effective in facilitating diagnosis, a review was conducted to evaluate literature on current methods of tongue diagnosis. Different methods of tongue diagnosis in the literature were identified and compared. Information on automated tongue diagnosis system, such as image acquisition, color correction, segmentation, feature extraction and classification, particularly in traditional medicine were reviewed. The aim of the review was to identify effective image processing techniques to be compatible with automated system for tongue diagnosis using some easily available to all imaging device rather than a dedicated state of art acquisition systems, which may not be easily accessible to general public. All methods identified were either being researched or developed and no specific system was identified that is currently available for routine use in clinics or home monitoring for patients. The healthcare sector could benefit from access to validated and automated tongue diagnosis systems. The feasibility of a mobile enabled platform to intelligently make use of this traditional method of diagnosis should be explored. In order to provide cheap and quick preliminary diagnosis for clinical practice automation of this noninvasive traditional technique can prove to be a boon for health care sector.

The paper presents an overview of some modern technologies for three-dimensional (3D) bioprinting of human tissues and organs. 3D bioprinting of human organs is increasingly used for the production and transplantation of artificial biological organs. Existing technologies of 3D bioprinting using bioink on a special substrate are considered. The features of the production of bioinks using biocompatible polymer compounds, hydrogels are given, some popular modern bioprinters are noted. Modern technologies of bioprinting of tissues of human organs are considered: skin, liver, lungs, heart, brain, existing technological problems in this area are given. Based on the analysis, the future prospects for the development of bioprinting technology for human organs are noted.

Parkinson's disease (PD) is a neurodegenerative disorder. Hence, there is a tremendous demand for adapting vocal features to determine PD in an earlier stage. This paper devises a technique to diagnose PD using voice signals. Initially, the voice signals are considered an input. The signal is fed to pre-processing wherein the filtering is adapted to remove noise. Thereafter, feature extraction is done that includes fluctuation index, spectral flux, spectral centroid, Mel frequency Cepstral coefficient (MFCC), spectral spread, tonal power ratio, spectral kurtosis and the proposed Exponential delta-Amplitude modulation signal (delta-AMS). Here, exponential delta-amplitude modulation spectrogram (Exponential-delta AMS) is devised by combining delta-amplitude modulation spectrogram (delta-AMS) and exponential weighted moving average (EWMA). The feature selection is done considering the extracted features using the proposed squirrel search water algorithm (SSWA), which is devised by combining Squirrel search algorithm (SSA) and water cycle algorithm (WCA). The fitness is newly devised considering Canberra distance. Finally, selected features are fed to attention-based long short-term memory (attention-based LSTM) in order to identify the existence of PD. Here, the training of attention-based LSTM is performed with developed SSWA. The proposed SSWA-based attention-based LSTM offered enhanced performance with 92.5% accuracy, 95.4% sensitivity and 91.4% specificity.

The aim of the present study is to classify and quantify the anatomical variations of teeth in terms of form and number of root canals reported in human teeth employing the classification systems proposed previously. An electronic (PubMed) and manual search were performed to identify case reports noting any of the anatomical variations. Each alteration was studied independently. The electronic search was performed using the following keywords: anatomical aberration, root canal, permanent Dentition, case report, c-shaped canal, dens invaginatus, palato-radicular groove, palato-radicular groove, palato-gingival groove, radix entomolaris, dental fusion, dental gemination, taurodontism, dilaceration. The initial search revealed 1497 papers, of which 938 were excluded after analyzing the titles and abstracts. Therefore, 559 potential papers were considered. Of those, 140 articles did not meet the inclusion criteria. For the final revision, 419 papers were considered. We found that the mandibular first premolar had the highest prevalence of C-shaped canals. Dens invaginatus was more frequently found in the mandibular lateral incisor. Taurodontism was more prevalent in the maxillary first molar and in the mandibular first molar. Dilaceration was not clearly associated with a particular tooth. The classifications systems used in this review allowed for the better understanding and analysis of the many anatomical variations present in teeth. The variations in shape most found were dens invaginatus and radix entomolaris. The most frequently reported anatomical variation was in the number of canals.

Thermal therapies, the modulation of tissue temperature for therapeutic benefit, are in clinical use as adjuvant or stand-alone therapeutic modalities for a range of indications, and are under investigation for others. During delivery of thermal therapy in the clinic and in experimental settings, monitoring and control of spatio-temporal thermal profiles contributes to an increased likelihood of inducing desired bioeffects. In vitro thermal dosimetry studies have provided a strong basis for characterizing biological responses of cells to heat. To perform an accurate in vitro thermal analysis, a sample needs to be subjected to uniform heating, ideally raised from, and returned to, baseline immediately, for a known heating duration under ideal isothermal condition. This review presents an applications-based overview of in vitro heating instrumentation platforms. A variety of different approaches are surveyed, including external heating sources (i.e., CO2 incubators, circulating water baths, microheaters and microfluidic devices), microwave dielectric heating, lasers or the use of sound waves. We discuss critical heating parameters including temperature ramp rate (heat-up phase period), heating accuracy, complexity, peak temperature, and technical limitations of each heating modality.

The extraction of fetal electrocardiogram (FECG) is of great significance for perinatal fetal monitoring. In order to improve the prediction accuracy of FECG, a FECG extraction method based on extreme learning machine (ELM) optimized by an improved particle swarm optimization (IPSO) was proposed (IPSO-ELM). First, according to the characteristics of the mixed signal on the maternal abdominal wall, and based on the global search ability of IPSO, the initial weight matrix and hidden layer bias of ELM were optimized to match with the mixed signal of the maternal abdominal wall and the network topology. Then, an ELM model was established using the optimal network parameters obtained by IPSO. The nonlinear transformation of the maternal ECG (MECG) signal to the abdominal wall was estimated by the IPSO-ELM network. Finally, the non-linearly transformed MECG signal was mixed with the abdominal wall subtract to obtain clear FECG. The experimental results of clinical ECG signals in DaISy dataset showed that, compared with the traditional normalized minimum mean square error, support vector machine method, and ELM neural network methods, the proposed method can extract clearer FECG signals and improve the signal-to-noise ratio of extracted FECG.

Many researchers have developed computer-assisted diagnostic (CAD) methods to diagnose breast cancer using histopathology microscopic images. These techniques help to improve the accuracy of biopsy diagnosis with hematoxylin and eosin-stained images. On the other hand, most CAD systems usually rely on inefficient and time-consuming manual feature extraction methods. Using a deep learning (DL) model with convolutional layers, we present a method to extract the most useful pictorial information for breast cancer classification. Breast biopsy images stained with hematoxylin and eosin can be categorized into four groups namely benign lesions, normal tissue, carcinoma in situ, and invasive carcinoma. To correctly classify different types of breast cancer, it is important to classify histopathological images accurately. The MobileNet architecture model is used to obtain high accuracy with less resource utilization. The proposed model is fast, inexpensive, and safe due to which it is suitable for the detection of breast cancer at an early stage. This lightweight deep neural network can be accelerated using field-programmable gate arrays for the detection of breast cancer. DL has been implemented to successfully classify breast cancer. The model uses categorical cross-entropy to learn to give the correct class a high probability and other classes a low probability. It is used in the classification stage of the convolutional neural network (CNN) after the clustering stage, thereby improving the performance of the proposed system. To measure training and validation accuracy, the model was trained on Google Colab for 280 epochs with a powerful GPU with 2496 CUDA cores, 12 GB GDDR5 VRAM, and 12.6 GB RAM. Our results demonstrate that deep CNN with a chi-square test has improved the accuracy of histopathological image classification of breast cancer by greater than 11% compared with other state-of-the-art methods.