Journal of Healthcare Engineering

Chest diseases are very serious health problems in the life of people. These diseases include chronic obstructive pulmonary disease, pneumonia, asthma, tuberculosis, and lung diseases. The timely diagnosis of chest diseases is very important. Many methods have been developed for this purpose. In this paper, we demonstrate the feasibility of classifying the chest pathologies in chest X-rays using conventional and deep learning approaches. In the paper, convolutional neural networks (CNNs) are presented for the diagnosis of chest diseases. The architecture of CNN and its design principle are presented. For comparative purpose, backpropagation neural networks (BPNNs) with supervised learning, competitive neural networks (CpNNs) with unsupervised learning are also constructed for diagnosis chest diseases. All the considered networks CNN, BPNN, and CpNN are trained and tested on the same chest X-ray database, and the performance of each network is discussed. Comparative results in terms of accuracy, error rate, and training time between the networks are presented.

It is known that improvement in walking function can be achieved in patients suffering a movement disorder after stroke or spinal cord injury by providing intensive locomotor training. Rehabilitation robots allow for a longer and more intensive training than that achieved by conventional therapies. Robot assisted treadmill training also offers the ability to provide objective feedback within one training session and to monitor functional improvements over time. This article provides an overview of the technical features and reports the clinical data available for one of these systems known as "Lokomat". First, background information is given for the neural mechanisms of gait recovery. The basic technical approach of the Lokomat system is then described. Furthermore, new features are introduced including cooperative control strategies, assessment tools and augmented feedback. These features may be capable of further enhancing training intensity and patient participation. Findings from clinical studies are presented covering the feasibility as well as efficacy of Lokomat assisted treadmill training.

According to World Health Organization (WHO) estimations, one out of five adults worldwide will be obese by 2025. Worldwide obesity has doubled since 1980. In fact, more than 1.9 billion adults (39%) of 18 years and older were overweight and over 600 million (13%) of these were obese in 2014. 42 million children under the age of five were overweight or obese in 2014. Obesity is a top public health problem due to its associated morbidity and mortality. This paper reviews the main techniques to measure the level of obesity and body fat percentage, and explains the complications that can carry to the individual's quality of life, longevity and the significant cost of healthcare systems. Researchers and developers are adapting the existing technology, as intelligent phones or some wearable gadgets to be used for controlling obesity. They include the promoting of healthy eating culture and adopting the physical activity lifestyle. The paper also shows a comprehensive study of the most used mobile applications and Wireless Body Area Networks focused on controlling the obesity and overweight. Finally, this paper proposes an intelligent architecture that takes into account both, physiological and cognitive aspects to reduce the degree of obesity and overweight.

Glaucoma is the second most common cause for blindness around the world and the third most common in Europe and the USA. Around 78 million people are presently living with glaucoma (2020). It is expected that 111.8 million people will have glaucoma by the year 2040. 90% of glaucoma is undetected in developing nations. It is essential to develop a glaucoma detection system for early diagnosis. In this research, early prediction of glaucoma using deep learning technique is proposed. In this proposed deep learning model, the ORIGA dataset is used for the evaluation of glaucoma images. The U-Net architecture based on deep learning algorithm is implemented for optic cup segmentation and a pretrained transfer learning model; DenseNet-201 is used for feature extraction along with deep convolution neural network (DCNN). The DCNN approach is used for the classification, where the final results will be representing whether the glaucoma infected or not. The primary objective of this research is to detect the glaucoma using the retinal fundus images, which can be useful to determine if the patient was affected by glaucoma or not. The result of this model can be positive or negative based on the outcome detected as infected by glaucoma or not. The model is evaluated using parameters such as accuracy, precision, recall, specificity, and F-measure. Also, a comparative analysis is conducted for the validation of the model proposed. The output is compared to other current deep learning models used for CNN classification, such as VGG-19, Inception ResNet, ResNet 152v2, and DenseNet-169. The proposed model achieved 98.82% accuracy in training and 96.90% in testing. Overall, the performance of the proposed model is better in all the analysis.

Cataract is one of the leading causes of blindness in the world’s population. A method to evaluate blurriness for cataract diagnosis in retinal images with vitreous opacity is proposed in this paper. Three types of features are extracted, which include pixel number of visible structures, mean contrast between vessels and background, and local standard deviation. To avoid the wrong detection of vitreous opacity as retinal structures, a morphological method is proposed to detect and remove such lesions from retinal visible structure segmentation. Based on the extracted features, a decision tree is trained to classify retinal images into five grades of blurriness. The proposed approach was tested using 1355 clinical retinal images, and the accuracies of two-class classification and five-grade grading compared with that of manual grading are 92.8% and 81.1%, respectively. The kappa value between automatic grading and manual grading is 0.74 in five-grade grading, in which both variance and P value are less than 0.001. Experimental results show that the grading difference between automatic grading and manual grading is all within 1 grade, which is much improvement compared with that of other available methods. The proposed grading method provides a universal measure of cataract severity and can facilitate the decision of cataract surgery.

With the widespread adoption of e-Healthcare and telemedicine applications, accurate, intelligent disease diagnosis systems have been profoundly coveted. In recent years, numerous individual machine learning-based classifiers have been proposed and tested, and the fact that a single classifier cannot effectively classify and diagnose all diseases has been almost accorded with. This has seen a number of recent research attempts to arrive at a consensus using ensemble classification techniques. In this paper, a hybrid system is proposed to diagnose ailments using optimizing individual classifier parameters for two classifier techniques, namely, support vector machine (SVM) and multilayer perceptron (MLP) technique. We employ three recent evolutionary algorithms to optimize the parameters of the classifiers above, leading to six alternative hybrid disease diagnosis systems, also referred to as hybrid intelligent systems (HISs). Multiple objectives, namely, prediction accuracy, sensitivity, and specificity, have been considered to assess the efficacy of the proposed hybrid systems with existing ones. The proposed model is evaluated on 11 benchmark datasets, and the obtained results demonstrate that our proposed hybrid diagnosis systems perform better in terms of disease prediction accuracy, sensitivity, and specificity. Pertinent statistical tests were carried out to substantiate the efficacy of the obtained results.

Breast cancer is the most common cancer among women worldwide with about half a million cases reported each year. Mammary thermography can offer early diagnosis at low cost if adequate thermographic images of the breasts are taken. The identification of breast cancer in an automated way can accelerate many tasks and applications of pathology. This can help complement diagnosis. The aim of this work is to develop a system that automatically captures thermographic images of breast and classifies them as normal and abnormal (without cancer and with cancer). This paper focuses on a segmentation method based on a combination of the curvature function k and the gradient vector flow, and for classification, we proposed a convolutional neural network (CNN) using the segmented breast. The aim of this paper is to compare CNN results with other classification techniques. Thus, every breast is characterized by its shape, colour, and texture, as well as left or right breast. These data were used for training as well as to compare the performance of CNN with three classification techniques: tree random forest (TRF), multilayer perceptron (MLP), and Bayes network (BN). CNN presents better results than TRF, MLP, and BN.

Combined ultrasound and photoacoustic imaging has attracted significant interests for intravascular imaging such as atheromatous plaque detection, with ultrasound imaging providing spatial location and morphology and photoacoustic imaging highlighting molecular composition of the plaque. Conventional ultrasound imaging systems utilize piezoelectric ultrasound transducers, which suffer from limited frequency bandwidths and reduced sensitivity with miniature transducer elements. Recent advances on optical methods for both ultrasound generation and detection have shown great promise, as they provide efficient and ultrabroadband ultrasound generation and sensitive and ultrabroadband ultrasound detection. As such, all-optical ultrasound imaging has a great potential to become a next generation ultrasound imaging method. In this paper, we review recent developments on optical ultrasound transmitters, detectors, and all-optical ultrasound imaging systems, with a particular focus on fiber-based probes for intravascular imaging. We further discuss our thoughts on future directions on developing combined all-optical photoacoustic and ultrasound imaging systems for intravascular imaging.

CT image information data under deep learning algorithms was adopted to evaluate small airway function and analyze the clinical efficacy of different glucocorticoid administration ways in asthmatic children with small airway obstruction. The Res-NET in the deep learning algorithm was used to perform feature extraction, summary classification, and other reconstruction of CT images. A deep learning network model Mask-R-CNN was constructed to enhance the ability of image reconstruction. A total of 118 children hospitalized with acute exacerbation of asthma in the hospital were recruited. After acute exacerbation treatment, 96 children with asthma were screened out for small airway obstruction, which were divided into glucocorticoid aerosol inhalation group (group A, 32 cases), glucocorticoid combined with bronchodilator aerosol inhalation group (group B, 32 cases), and oral hormone therapy group (group C, 32 cases). Asthmatic children with small airway obstruction were screened after acute exacerbation treatment and were rolled into glucocorticoid aerosol inhalation group (group A), glucocorticoid combined with bronchodilators aerosol inhalation group (group B), and oral hormone therapy group (group C). Lung function indicators (maximal mid-expiratory flow (MMEF75 and 25), 50% forced expiratory flow (FEF50), and 75% forced expiratory flow (FEF75)), FeNO level, and airway inflammation indicators (IL-6, IL-35, and eosinophilic (EOS)) were compared before and one month after treatment. The ratio of airway wall thickness to outer diameter (T/D) and the percentage of airway wall area to total airway area (WA%) were measured by e-Health high-resolution CT (HRCT). The constructed network model was used to measure the patient's coronary artery plaque and blood vessel volume, and the image was reconstructed on the Res-Net network. It was found that the MSE value of the Res-Net network was the lowest, and the efficiency was very high during the training process. T/D and WA (%) of asthmatic children with small airway obstruction after treatment were significantly lower than those before treatment ( $P<0.01$ ). After treatment, MMEF75/25 and FEF75 were significantly higher than those before treatment ( $P<0.05$ ). Lung function-related indicator FEF50 was significantly higher than that before treatment ( $P<0.01$ ). FeNO level after treatment was remarkably lower than that before treatment ( $P<0.01$ ). In addition, lung function-related indicators, airway inflammation indicators, and FeNO level improved the most in group C, followed by group B, and those improvements in group A were the least obvious, with great differences among groups ( $P<0.05$ ). In summary, the Res-Net model proposed was of certain feasibility and effectiveness for CT image segmentation and can effectively improve the clinical evaluation of patient CT image information. Glucocorticoids could improve small airway function and airway inflammation in asthmatic children with small airway obstruction, and oral corticosteroids were more effective than aerosol inhalation therapy.

A method based on measurement correlation (MC) and linear minimum mean square error (LMMSE) for multichannel surface electromyography (sEMG) signal decomposition was developed in this study. This MC-LMMSE method gradually and iteratively increases the correlation between an optimized vector and a reconstructed matrix that is correlated with the measurement matrix. The performance of the proposed MC-LMMSE method was evaluated with both simulated and experimental sEMG signals. Simulation results show that the MC-LMMSE method can successfully reconstruct up to 53 innervation pulse trains with a true positive rate greater than 95%. The performance of the MC-LMMSE method was also evaluated using experimental sEMG signals collected with a 64-channel electrode array from the first dorsal interosseous muscles of three subjects at different contraction levels. A maximum of 16 motor units were successfully extracted from these multichannel experimental sEMG signals. The performance of the MC-LMMSE method was further evaluated with multichannel experimental sEMG data by using the “two sources” method. The large population of common MUs extracted from the two independent subgroups of sEMG signals demonstrates the reliability of the MC-LMMSE method in multichannel sEMG decomposition.