Background: This study evaluated the performances of neural networks in terms of denoizing metal artifacts in computed tomography (CT) images to improve diagnosis based on the CT images of patients. Methods: First, head-and-neck phantoms were simulated (with and without dental implants), and CT images of the phantoms were captured. Six types of neural networks were evaluated for their abilities to reduce the number of metal artifacts. In addition, 40 CT patients' images with head-and-neck cancer (with and without teeth artifacts) were captured, and mouth slides were segmented. Finally, simulated noisy and noise-free patient images were generated to provide more input numbers (for training and validating the generative adversarial neural network [GAN]). Results: Results showed that the proposed GAN network was successful in denoizing artifacts caused by dental implants, whereas more than 84% improvement was achieved for images with two dental implants after metal artifact reduction (MAR) in patient images. Conclusion: The quality of images was affected by the positions and numbers of dental implants. The image quality metrics of all GANs were improved following MAR comparison with other networks.

[ABSTRACT]  [FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]

Background: Lung cancer images require large memory storage and transmission bandwidth for sending the data. Compressive sensing (CS), as a method with a statistical approach in signal sampling, provides different output patterns based on information sources. Thus, it can be considered that CS can be used for feature extraction of compressed information. Methods: In this study, we proposed a novel texture extraction-based CS for lung cancer classification. We classify three types of lung cancer, including adenocarcinoma (ACA), squamous cell carcinoma (SCC), and benign lung cancer (N). The classification is carried out based on texture extraction, which is processed in 2 stages, the first stage to detect N and the second to detect ACA and SCC. Results: The simulation results show that two-stage texture extraction can improve accuracy by an average of 84%. The proposed system is expected to be decision support in assisting clinical diagnosis. In terms of technical storage, this system can save memory resources. Conclusions: The proposed two-step texture extraction system combined with CS and K- Nearest Neighbor has succeeded in classifying lung cancer with high accuracy; the system can also save memory storage. It is necessary to examine the complexity of the proposed method so that it can be analyzed further.

[ABSTRACT]  [FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]

Background: Fish is a food ingredient that is consumed throughout the world. When fishes die, their freshness begins to decrease. The freshness of the fish can be determined by the aroma it produces. The purpose of this study is to monitor the odor of fish using a collection of gas sensors that can detect distinct odors. Methods: The sensor was tested with three kinds of samples, namely Pseudomonas aeruginosa, tuna, and tuna that was contaminated with P. aeruginosa bacteria. During the process of collecting sensor data, all samples were placed in a vacuum so that the gas or aroma produced was not contaminated with other aromas. Eight sensors were used which were designed and implemented in an electronic nose (E-nose) device that can withstand aroma. The data collection process was carried out for 48 h, with an interval of 6 h for each data collection. Data processing was performed by using the principal component analysis and support vector machine (SVM) methods to obtain a plot score visualization and classification and to determine the aroma pattern of the fish. Results: The results of this study indicate that the E-nose system is able to smell fish based on the hour with 95% of the cumulative variance of the main component in the classification test between fresh tuna and tuna fish contaminated with P. aeruginosa. Conclusion: The SVM classifier was able to classify the healthy and unhealthy fish with an accuracy of 99%. The sensors that provided the highest response are the TGS 825 and TGS 826 sensors.

[ABSTRACT]  [FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]

Background: In Persian medicine (PM), measuring the wrist pulse is one of the main methods for determining a person's health status and temperament. One problem that can arise is the dependence of the diagnosis on the physician's interpretation of pulse wave features. Perhaps, this is one reason why this method has yet to be combined with modern medical methods. This paper addresses this concern and outlines a system for measuring pulse signals based on PM. Methods: A system that uses data from a customized device that logs the pulse wave on the wrist was designed and clinically implemented based on PM. Seven convolutional neural networks (CNNs) have been used for classification. Results: The pulse wave features of 34 participants were assessed by a specialist based on PM principles. Pulse taking was done on the wrist in the supine position (named Malmas in PM) under the supervision of the physician. Seven CNNs were implemented for each participant's pulse characteristic (pace, rate, vessel elasticity, strength, width, length, and height) assessment, and then, each participant was classified into three classes. Conclusion: It appears that the design and construction of a customized device combined with the deep learning algorithm can measure the pulse wave features according to PM and it can increase the reliability and repeatability of the diagnostic results based on PM.

[ABSTRACT]  [FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]

Background: Drowsy driving is one of the leading causes of severe accidents worldwide. In this study, an analyzing method based on drowsiness level proposed to detect drowsiness through electroencephalography (EEG) measurements and vehicle dynamics data. Methods: A driving simulator was used to collect brain data in the alert and drowsy states. The tests were conducted on 19 healthy men. Brain signals from the parietal, occipital, and central parts were recorded. Observer Ratings of Drowsiness (ORD) were used for the drowsiness stages assessment. This study used an innovative method, analyzing drowsiness EEG data were in respect to ORD instead of time. Thirteen features of EEG signal were extracted, then through Neighborhood Component Analysis, a feature selection method, 5 features including mean, standard deviation, kurtosis, energy, and entropy are selected. Six classification methods including K-nearest neighbors (KNN), Regression Tree, Classification Tree, Naive Bayes, Support vector machines Regression, and Ensemble Regression are employed. Besides, the lateral position and steering angle as a vehicle dynamic data were used to detect drowsiness, and the results were compared with classification result based on EEG data. Results: According to the results of classifying EEG data, classification tree and ensemble regression classifiers detected over 87.55% and 87.48% of drowsiness at the moderate level, respectively. Furthermore, the classification results demonstrate that if only the single-channel P4 is used, higher performance can achieve than using data of all the channels (C3, C4, P3, P4, O1, O2). Classification tree classifier and regression classifiers showed 91.31% and 91.12% performance with data from single-channel P4. The best classification results based on vehicle dynamic data were 75.11 through KNN classifier. Conclusion: According to this study, driver drowsiness could be detected at the moderate drowsiness level based on features extracted from a single-channel P4 data.

[ABSTRACT]  [FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]

Objective: The current work aims to design and develop an automatically controlled wearable electrolarynx, a voice substitution device for laryngeal carcinoma survivals. Methods: The physical activity of mouth opening is sensed, amplified, and made to act as an enable signal to trigger the wearable electrolarynx. The resulting speech is recorded and compared for its voice reaction durations with that of manual electrolarynx and normal speaking methods. Perception evaluations of 5 subjects from 10 speech-language therapists are obtained. Results: The wearable electrolarynx turn-on in 13 μs once the mouth movement for speech is sensed. The voice initiation time and termination durations are 215.68 m and 231.41 ms, respectively. Results indicate that there is no significant difference (P < 0.05) between the voice reaction durations of wearable electrolarynx and normal speaking methods. The subjective evaluation results show that there is a significant improvement (P < 0.05) in intelligibility and noise reduction when compared to a commercially available electrolarynx with an average intra-class correlation coefficient of 0.68 from analysis of variance two factors without replication. Conclusions: The assessment of the wearable and automatically controlled electrolarynx provides hands-free speech and easy control over the device.

[ABSTRACT]  [FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]

[FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]

To develop a wearable device that can detect epilepsy seizures. In particular, due to their prevalence, attention is focused on detecting the generalized tonic-clonic seizure (GTCS) type. When a seizure is detected, an alert phone call is initiated and an alarm SMS sent to the nearest health-care provider (and/or a predesignated family member), including the patient's location as global positioning system (GPS) coordinates. A wearable belt is developed including an Arduino processor that constantly acquires data from four different sensing modalities and monitors the acquired signal patterns for abnormalities. The sensors are a heart rate sensor, electromyography sensor, blood oxygen level (oxygen saturation) sensor, and an accelerometer to detect sudden falls. Higher-than-normal threshold levels are established for each sensor's signal. If two or more signal measurements exceed the corresponding threshold value for a predetermined time interval, then the seizure alarm is triggered. Clinical trials were not pursued in this study as this is the initial phase of system development (phase 0). Instead, the instrumented belt seizure detection prototype was tested on nine healthy individuals mimicking, to some degree, seizure symptoms. A total of eighteen trials took place of which half had <2 sensor thresholds exceeded and no alarm, whereas the other half resulted in activating the alarm when two or more sensor thresholds were exceeded for at least the predetermined time interval corresponding to each of the higher-than-normal sensor readings. For each trial that triggered the alarm when a seizure was detected, the on-board GPS and global system for mobile communication (GSM) units successfully initiated an alert phone call to a predesignated number in addition to sending an SMS message, including GPS location coordinates. Continuous real-time monitoring of signals from the four different sensors allows the developed wearable belt to detect GTCS while reducing false alarms. The proposed device produces an important alarm that may save a patient's life.

[ABSTRACT]  [FULL TEXT]  [PDF]

The COVID-19 has become an important health issue in the world and has endangered human health. The purpose of this research is to use an intelligent system model of adaptive neuro-fuzzy inference system (ANFIS) using twelve variables of input for the diagnosis of COVID-19. The evaluation of the model was performed using the information of 500 patients referred to and suspected of the COVID-19. Three hundred and fifty people were used as training data and 150 people were used as test and validation data. Information on 12 important parameters of COVID-19 such as fever, cough, headache, respiratory rate, Ct-chest, medical history, skin rash, age, family history, loss of olfactory sensation and taste, digestive symptoms, and malaise was also reported in patients with severe disease. ANFIS identified COVID-19 in accuracy, sensitivity, and specificity with more than 95%, 94%, and 95%, respectively, which indicates the high efficiency of the system in the correct diagnosis of individuals. The proposed system accurately detected more than 95% COVID-19 as well as mild, moderate, and acute severity. Due to the time-constraint, limitations, and error of COVID-19 diagnostic tools, the proposed system can be used in high-precision primary detection, as well as saving time and cost.

[ABSTRACT]  [FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]

Ongoing novel coronavirus (COVID-19) with high mortality is an infectious disease in the world which epidemic in 2019 with human-human transmission. According to the literature, S-protein is one of the main proteins of COVID-19 that bind to the human cell receptor angiotensin-converting enzyme 2 (ACE2). In this study, it was attempted to identify the main effective drugs approved that may be repurposed to the binding site of ACE2. High throughput virtual screening based on the docking study was performed to know which one of the small-molecules had a potential interaction with ACE2 structure. Forasmuch as investigating and identifying the best ACE2 inhibitors among more than 3,500 small-molecules is time-consuming, supercomputer was utilized to apply docking-based virtual screening. Outputs of the proposed computational model revealed that vincristine, vinbelastin and bisoctrizole can significantly bind to ACE2 and may interface with its normal activity.

[ABSTRACT]  [FULL TEXT]  [PDF]  [Mobile Full text]  [EPub]