Journal of Medical Signals and Sensors
Volume:13 Issue: 3, Jul-Sep 2023

Backgorund: 

Nowadays, everybody’s life is dominated by COVID‑19, which might have been the source of severe acute respiratory syndrome coronavirus 2. This virus disrupts the lungs first of all. Recently, it has been found that coronavirus may affect the brain. Because all body actions rely on the brain, hence investigating its healthy is an essential item in coronavirus effects.

Brain image segmentation can be helpful in the detection of the regions damaged by the effects of coronavirus. Since every image given by photography devices may have noises, therefore, first of all, the brain magnetic resonance angiography (MRA) images must be denoised for best investigation. In the present paper, we have presented the construction of multishearlets based on multiwavelets for the first time and have used them for the purpose of denoising. Multiwavelets have some advantages to wavelets. Therefore, we have used them in the shearlet system to expand the properties of multiwavelets in all directions. After denoising, we have proposed a scheme for the automatic characterization of the initial curve in the active contour model for segmentation. Detecting the initial curve is a challenging task in active contour‑based segmentation because detecting an initial curve far from the desired region can lead to unfavorable results.

The results show the performance of using multishearlets in detecting affected regions by COVID‑19. Using multishearlets has led to the high value of peak signal‑to‑noise ratio and Structural similarity index measure in comparison with original shearlets. Original shearlets are constructed from wavelets whereas we have constructed multishearlets from multiwavelets.

The results show that multishearlets can neutralize the effect of noise in MRA images in a good way rather than shearlets. Moreover, the proposed scheme for segmentation can lead to 0.99 accuracy.

Virtual wedge (VW) is used in radiotherapy to compensate for missing tissues and create a uniform dose distribution in tissues. According to TECDOC‑1583 and technical reports series no. 430, evaluating the dose calculation accuracy is essential for the quality assurance of treatment planning systems (TPSs). In this study, the dose calculation accuracy of the collapsed cone superposition (CCS) algorithm in the postmastectomy radiotherapy of the chest wall for breast cancer was evaluated by comparing the calculated and measured dose in VW fields.

Two tangential fields with the typical VW angles were planned using ISOgray TPS in a thorax phantom. The CCS algorithm was used for dose calculation at 6 and 15 MV photon beams. The obtained dose distributions from EBT3 film spaces and TPS were evaluated using the gamma index.

The measured and calculated dose values using VW in a heterogeneous medium with different beam energies were in a good agreement with each other (acceptance rate: 88.0%–93.4%). The calculated and measured data did not differ significantly with an increase/decrease in wedge angle. In addition, the results demonstrated that ISOgray overestimated and underestimated the dose of the soft tissue and lung in the planned volume, respectively.

According to the results of gamma index analysis, the calculated dose distribution using VW model with the CCS algorithm in a heterogeneous environment was within acceptable limits.

Watermarking such as other security concepts is an ongoing challenging research issue, especially for medical images, to protect patient privacy. Medical images need to be shared and transferred between hospitals and specialists as quickly as possible for better diagnosis. Fast and simple watermarking is needed as well as the robust transferring of channel noise, such as salt and pepper noise and robust cropping that may occur from specialists and signature encryption for patient privacy.

In this article, a highly robust and simple watermarking method is introduced. The proposed method has very low computational complexity and at the same time, it is very robust to interference and uses simple computations such as (XORs) Exclusive ORs and rotations that can be done in real‑time. The proposed method uses a combination of hidden neighboring signature information, Sudoku permutation, and noise pre‑processing to achieve high robustness against salt and pepper noise and cropping. Simple signature encryption is also used.

The proposed method is examined in different medical image datasets. The experimental results indicate the proposed watermarking system is robust to salt and pepper noise density of up to 90% and about 70% cropping. The number of computations including encryption is five XOR per pixel and a rotation per block of signature size.

A novel method for medical image watermarking is presented. The proposed method is in the spatial domain, has encryption, and uses only XOR computation. The proposed method is highly robust to noise and cropping which is necessary for medical uses. The proposed method can be used efficiently for real‑time watermarking for medical and nonmedical image datasets.

Computed tomography (CT) of the brain is associated with radiation exposure to the lens of the eyes. Therefore, it is necessary to optimize scan settings to keep radiation exposure as low as reasonably achievable without compromising diagnostic image information. The aim of this study was to compare the effectiveness of the five practical techniques for lowering eye radiation exposure and their effects on diagnostic image quality in pediatric brain CT.

The following scan protocols were performed: reference scan, 0.06‑mm Pbeq bismuth shield, 30% globally lowering tube current (GLTC), reducing tube voltage (RTV) from 120 to 90 kVp, gantry tilting, and combination of gantry tilting with bismuth shielding. Radiation measurements were performed using thermoluminescence dosimeters. Objective and subjective image quality was evaluated.

All strategies significantly reduced eye dose, and increased the posterior fossa artifact index and the temporal lobe artifact index, relative to the reference scan. GLTC and RTV increased image noise, leading to a decrease signal‑to‑noise ratio and contrast‑to‑noise ratio. Except for bismuth shielding, subjective image quality was relatively the same as the reference scan.

Gantry tilting may be the most effective method for reducing eye radiation exposure in pediatric brain CT. When the scanner does not support gantry tilting, GLTC might be an alternative.

Time perception refers to the capability to recognize the passage of time. The cerebellum is located at the back of the brain, underlying the occipital and temporal lobes. Dyschronometria is a cerebellar dysfunction, in which a person cannot precisely estimate the amount of time that has passed. Cardiac indicators such as heart rate (HR) variability have been associated with mental function in healthy individuals. Moreover, time perception has been previously studied concerning cardiac signs. Human time perception is influenced by various factors such as attention and drowsiness. An electroencephalogram (EEG) is a suitable modality for evaluating cortical reactions due to its affordability and usefulness. Because EEG has a high sequential outcome, it offers valuable data to explore variability in psychological situations. An electrocardiogram (ECG) records electrical signals from the heart to examine various heart conditions. The electromyography (EMG) technique detects electrical impulses produced by muscles.

EEG, ECG, and EMG are integrated during time perception. This study evaluated the human body’s time perception through the neurological, cardiovascular, and muscular systems using a simple neurofeedback exercise after time perception tasks. The three biosignals which are EEG, ECG, and EMG were investigated to use them as biomarkers for recognizing time perception difficulty as the main goal of the study. Five healthy college students with no health issues participated, and their EEG, ECG, and EMG were recorded while relaxing and performing a time wall estimation task and neurofeedback training. Previous research has shown the relationship between EEG frequency bands and the frontal center during time perception. Investigating the connection between ECG, EEG, and EMG under time perception conditions is significant.

The results show that ECG (HR), EEG (Delta wave), and EMG (root mean square) are critical features in time perception difficulties.

The ability and outcomes of multiple biomarkers might allow for improved diagnosis and monitoring of the progress of any treatment applications such as biofeedback training. Furthermore, those biomarkers could be used as useful for evaluating and treating dyschronometria.

Atrial fibrillation (AF) is a life threatening disease and can cause stroke, heart failure, and sometimes death. To reduce the rate of mortality and morbidity due to increased prevalence of AF, early detection of the same becomes a prior concern. Traditional machine learning (TML) algorithms and ensemble machine learning (EML) algorithms are proposed to detect AF in this article. The performances of both these methods are compared in this study. Methodology involves computation of RR interval features extracted from electrocardiogram and its classification into: normal, AF, and other rhythms. TML techniques such as Classification and Regression Tree, K Nearest Neighbor, C4.5, Iterative Dichotomiser 3, Support Vector Machine and EML classifier such as Random Forest (RF), and Rotation Forest are used for classification. The proposed method is evaluated using PhysioNet challenge 2017. During the tenfold cross validation, it is observed that RF classifier provided good classification accuracy of 99.10% with area under the curve of 0.998. Apart from contributing a new methodology, the proposed study also experimentally proves higher performance with ensemble learning method, RF. The methodology has many applications in health care management systems including defibrillators, cardiac pacemakers, etc.

Complete edentulism is one of the most common problems encountered by geriatric individuals. With advanced aging, despite attempts made to retain natural dentition, loss of entire teeth is yet observed. For precise denture fabrication, a digital sensor device was used during the making procedure. The use of sensor device aided in better appreciation and more retentiveness of denture.

The Holter monitor captures the electrocardiogram (ECG) and detects abnormal episodes, but physicians still use manual cross‑checking. It takes a considerable time to annotate a long‑term ECG record. As a result, research continues to be conducted to produce an effective automatic cardiac episode detection technique that will reduce the manual burden. The current study presents a signal processing framework to detect ventricular ectopic beat (VEB) episodes in long‑term ECG signals of cross‑database. The proposed study has experimented with the cross‑database of open‑source and proprietary databases. The ECG signals were preprocessed and extracted the features such as pre‑RR interval, post‑RR interval, QRS complex duration, QR slope, and RS slope from each beat. In the proposed work, four models such as support vector machine, k‑means nearest neighbor, nearest mean classifier, and nearest RMS (NRMS) classifiers were used to classify the data into normal and VEB episodes. Further, the trained models were used to predict the VEB episodes from the proprietary database. NRMS has reported better performance among four classification models. NRMS has shown the classification accuracy of 98.68% and F1‑score of 94.12%, recall rate of 100%, specificity of 98.53%, and precision of 88.89% with an open‑source database. In addition, it showed an accuracy of 99.97%, F1‑score of 94.54%, recall rate of 98.62%, specificity of 99.98%, and precision of 90.79% to detect the VEB cardiac episodes from the proprietary database. Therefore, it is concluded that the proposed framework can be used in the automatic diagnosis system to detect VEB cardiac episodes.