Journal of Biomedical Physics & Engineering
Volume:13 Issue: 5, Sep-Oct 2023

Artificial neural network helps humans in a wide range of activities, such as sports.

This paper aims to investigate the effect of artificial intelligence on decision-making related to human gait and sports biomechanics, using computer-based software, and to investigate the impact of artificial intelligence on individuals’ biomechanics during gait and sports performance.

This review was conducted in compliance with the PRISMA guidelines. Abstracts and citations were identified through a search based on Science Direct, Google Scholar, PubMed, Elsevier, Springer Link, Web of Science, and Scopus search engines from 1995 up to 2023 to obtain relevant literature about the impact of artificial intelligence on biomechanics. A total of 1000 articles were found related to biomechanical characteristics of gait and sport and 26 articles were directly pertinent to the subject.

The extent of the application of artificial intelligence in sports biomechanics in various fields. In addition, various variables in the fields of kinematics, kinetics, and the field of time can be investigated based on artificial intelligence. Conventional computational techniques are limited by the inability to process data in its raw form. Artificial Intelligence (AI) and Machine Learning (ML) techniques can handle complex and high-dimensional data. 

The utilization of specialized systems and neural networks in gait analysis has shown great potential in sports performance analysis. Integrating AI into this field would be a significant advancement in sport biomechanics. Coaches and athletes can develop more precise training regimens with specialized performance prediction models.

Radiation therapy, the most common form of cancer treatment, can result in late complications, such as secondary breast and thyroid cancers.

This study aimed to evaluate the risk of secondary cancers using two radiobiological models of Excess Absolute Risk (EAR) and Excess Relative Risk (ERR) in patients with brain cancer undergoing radiotherapy for improved survival rates of cancer patients.

In this expository cross-sectional study, 45 patients under the age of 40 years underwent Whole Brain Radiotherapy (WBRT) using a compact accelerator in Shahid Ramezanzadeh Hospital, Yazd, Iran. Out-of-field organ dose measurement was performed using a Thermoluminescent Dosimeter (TLD) to determine the dose to thyroid and breast tissues. The risk of secondary cancers in these organs was calculated 3, 5, 10, 15, and 20 years after radiation therapy.

The mean values of thyroid cancer risk in men and women were 0.418±0.509 and 0.274±0.306, respectively. ERR values of breast cancer in 3-, 5-, 10-, 15-, and 20-year women undergoing radiation therapy were 1.084±2.938, 0.594±1.407, 0.248±0.497, 0.138±0.248, and 0.091±0.148, respectively. EAR values of breast cancer in 3-, 5-, 10-, 15-, and 20-year women following radiation therapy were 0.064±0.060, 0.077±0.071, 0.119±0.100, 0.178±0.248, and 0.259±0.178, respectively. 

After irradiation, the risk of secondary cancer is affected by factors, such as the patient’s age and gender. The secondary thyroid cancer is higher than that of other organs, such as the breast, in the patients undergoing WBRT.

Radiotherapy is considered a compromise between the amount of killed tumor cells and the damage caused to the healthy tissue. Regarding this, radiobiological modeling is performed to individualize and optimize treatment strategies.

This study aimed to determine the normal tissue complication probability (NTCP) of acute ocular pain following radiotherapy.

In this prospective observational study, the clinical data were collected from 45 patients with head and neck cancers and skull-base tumors, and dosimetric data were recorded after contouring the eye globe. Acute ocular pain was prospectively assessed with a three-month follow-up. The Lyman-Kutcher-Berman (LKB) parameters were estimated using the Area Under Curve (AUC) of Receiver Operating Characteristic (ROC) maximization and Maximum Likelihood (MLH) methods, and the NTCP of acute ocular pain was then determined using generalized LKB radiobiological model. The model performance was evaluated with AUC, Brier score, and Hosmer-Lemeshow tests.

Six out of 45 (13.33%) patients developed acute ocular pain (grade 1 or more). LKB model showed a weak dose-volume effect (n=0.09), tolerance dose for a 50% complication (TD50) of 27.54 Gy, and slope parameter (m) of 0.38. The LKB model showed high prediction performance. The LKB model predicted that NTCP would be less than 25% if the generalized equivalent uniform dose (gEUD) was kept below 20 Gy. 

The LKB model showed a high performance in determining the NTCP of ocular pain so that the probability of ocular pain will be less than 25% if the eye globe mean dose is kept below 12 Gy.

Multiple sclerosis (MS) is the most common non-traumatic disabling disease. The aim of this study is to investigate the ability of radiomics features for diagnosing active plaques in patients with MS from T2 Fluid Attenuated Inversion Recovery (FLAIR) images. In this experimental study, images of 82 patients with 122 MS lesions were investigated. Boruta and Relief algorithms were used for feature selection on the train data set (70%). Four different classifier algorithms, including Multi-Layer Perceptron (MLP), Gradient Boosting (GB), Decision Tree (DT), and Extreme Gradient Boosting (XGB) were used as classifiers for modeling. Finally, Performance metrics were obtained on the test data set (30%) with 1000 bootstrap and 95% confidence intervals (95% CIs). A total of 107 radiomics features were extracted for each lesion, of which 7 and 8 features were selected by the Relief method and Boruta method, respectively. DT classifier had the best performance in the two feature selection algorithms. The best performance on the test data set was related to Boruta-DT with an average accuracy of 0.86, sensitivity of 1.00, specificity of 0.84, and Area Under the Curve (AUC) of 0.92 (95% CI: 0.92-0.92).  Radiomics features have the potential for diagnosing MS active plaque by T2 FLAIR image features. Additionally, choosing the feature selection and classifier algorithms plays an important role in the diagnosis of active plaque in MS patients. The radiomics-based predictive models predict active lesions accurately and non-invasively.

In the bystander effect, non-irradiated cells receive biological signals from adjacent irradiated cells and undergo a variety of alterations, considered recently in non-ionizing irradiation like ultrasound waves. In this study, the bystander effect of therapeutic ultrasound exposure alone and in combination with cisplatin was determined. This study aims to determine the bystander effect caused by ultrasound and cisplatin. This experimental study was conducted on the human melanoma cell line including two groups of target and bystander cells. The target cell group was divided into three sub-groups of ultrasound irradiation alone, cisplatin alone, and ultrasound irradiation in the presence of cisplatin that the culture medium of these three groups of cells was transferred to the bystander cell group using the medium transfer technique. Then, apoptotic bystander cells and the expression of P53 and HO-1 in target and bystander groups were measured. The results of the MTT (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide) and apoptosis assay showed that cell death in target and bystander groups receiving the ultrasound with cisplatin is higher than in the ultrasound without cisplatin. PCR (the polymerase chain reaction) results in the target and bystander groups receiving treatments with increased expression of the P53 gene. Target and bystander groups receiving the ultrasound without cisplatin showed a decrease in HO-1 gene expression, while the ultrasound with cisplatin showed an increase in the HO-1 gene compared to the control group.  Combining ultrasound with ultrasound and without it can transfer bystander signals to the cells that are not directly treated.

Percutaneous vertebroplasty employs bone cement for injecting into the fractured vertebral body (VB) caused by spinal metastases. Radioactive bone cement and also brachytherapy seeds have been utilized to suppress the tumor growth in the VB.
This study aims to investigate the dose distributions of low-energy brachytherapy seeds, and to compare them to those of radioactive bone cement, by Monte Carlo simulation.
In this simulation study, nine CT scan images were imported in Geant4. For the simulation of brachytherapy, I-125, Cs-131, or Pd-103 seeds were positioned in the VB, and for the simulation of vertebroplasty, the VB was filled by a radioactive cement loaded by P-32, Ho-166, Y-90, or Sm-153 radioisotopes. The dose-volume histograms of the VB, and the spinal cord (SC) were obtained after segmentation, considering that the reference dose is the minimum dose covered 95% of the VB.
The SC sparing was improved by using beta-emitting cement because of their steep gradient dose distribution. I-125 seeds and Y-90 radioisotope showed better VB coverage for brachytherapy and vertebroplasty techniques, respectively. Pd-103 seeds and P-32 radioisotope showed better SC sparing for brachytherapy and vertebroplasty, respectively. The minimum mean doses that covered 100% of the VB were 62.0%, 56.5%, and 45.0% for I-125, Cs-131, and Pd-103 seeds, and 28.3%, 28.6%, 32.9%, and 17.7%, for P-32, Ho-166, Y-90, and Sm-153 sources, respectively. 
I-125 and Cs-131 seeds may be useful for large tumors filling the entire VB, and also for the extended tumors invading multiple vertebrae. Beta-emitting bone cement is recommended for tumors located near the SC.

Competitive sailing requires efforts pertinent to physiological limitations and coordination between different parts of the body. Such coordination depends on the torques applied by muscles to the joints. This study aims to simulate the motion and provide a control law for the joint torques in order to track the desired motion paths. In this analytical study, an inverse dynamics based control is employed in order to simulate the motion by tracking the desired movement trajectories. First, the dynamics equations are obtained using Lagrange method for 5 degrees of freedom (5 DOF) model. In the following, a robust control scheme with inverse dynamics method based on the Proportional-Integral-Derivative (PID) approach is employed to track the desired joint angles obtained from the experiment. The simulation results demonstrate the performance of the proposed control method. Low settling times are achieved for the entire joint, which is appropriate in comparison with the time period of each cycle (3.75 s). Also, the maximum torques required to be applied to the joints are in physiological range.  This study provided an appropriate model for the analysis of human movement in rowing sport. The model can also be cited in terms of basic biological theories in addition to practical computational uses in biomechanical engineering. Accordingly, the generated control signals can help to improve the interactive body movements during paddling and in designing robotic arms for automatic rowing.

Although stiffness of neck muscles, the limitation of cervical range of motion (ROM), and forward head posture (FHP) are proposed as clinical characteristics of cervicogenic headache (CGH), adequate consistent data failed to support these characteristics. This study aims to compare the elastic modulus of suboccipital muscles, cervical ROM, and FHP between individuals suffering from CGH and healthy controls. In this cross-sectional study, 20 individuals with a history of CGH and 20 normal individuals participated. Sonography images and a universal goniometer (UG) were used to assess elastic modulus and cervical ROM, respectively. In addition, FHP was assessed based on measuring craniovertebral angle (CVA) using a digital imaging technique and also the distance of anterior tragus of the ear with the vertical line passed from anterior of lateral malleolus according to the Kendall and McCreary method. Elastic modulus of suboccipital muscles in the CGH group was significantly higher than that of the normal group (P=0.008). The two groups were not significantly different in terms of FHP. Moreover, ROM of cervical extension (P=0.035), right rotation (P=0.046), and left rotation (P=0.018) showed a significant reduction in the CGH group compared to the control group.  Suboccipital muscles are stiffer and ROM of cervical rotation and extension is smaller in CGH patients than the healthy controls, but FHP is not different between the groups, leading to diagnosing CGH and treatment.

Positron Emission Mammography (PEM) is a nuclear medicine imaging tool, playing a significant role in the diagnosis of patients with breast cancer. These days, many research has been done in order to improve the performance of this system.
This study aims to propose a new method for optimizing the size of axial Field of View (FOV) in PEMs and improving the performance of the systems.
In this analytical study, a conventional Inveon PET is simulated using GATE in order to validate the simulation. For this simulation, the mean relative difference is 2.91%, showing the precision and correction of simulation and consequently it is benchmarked. In the next step, for design of the new optimized detector, several validated simulations are performed in order to find the best geometry.
The best result is obtained with the axial FOV of 101.7 mm. It has 1.6×1.6×15 mm3 lutetium yttrium orthosilicate (LYSO) crystals. The detector consists of 6 block rings with 30 detector blocks in each ring. In this paper, the performance of the scanner is improved and the geometry is optimized. Sensitivity and scatter fraction of the designed scanner are 4.65% and 21.2%, respectively, also noise equivalent count rate (NECR) is 105.442 kcps. 
The results showed 1 up to 3% improvement in the sensitivity of this new detector compared with different PEMs.

Hypertension is associated with severe complications, and its detection is important to provide early information about a hypertension event, which is essential to prevent further complications. This study aimed to investigate a strategy for hypertension detection without a cuff using parameters of bioelectric signals, i.e., Electrocardiogram (ECG), Photoplethysmogram (PPG,) and an algorithm of Swarm-based Support Vector Machine (SSVM). This experimental study was conducted to develop a hypertension detection system. ECG and PPG bioelectrical records were collected from the Medical Information Mart for Intensive Care (MIMIC) from normal and hypertension participants and processed to find the parameters, used for the inputs of SSVM and comprised Pulse Arrival Time (PAT) and the characteristics of PPG signal derivatives. The SSVM was n Support Vector Machine (SVM) algorithm optimized using particle swarm optimization with Quantum Delta-potential-well (QDPSO). The SSVMs with different inputs were investigated to find the optimal detection performance. The proposed strategy was performed at 96% in terms of F1-score, accuracy, sensitivity, and specificity with better performance than the other methods tested and methods and also could develop a cuff-free hypertension monitoring system.  Hypertension using SSVM, ECG, and PPG parameters is acceptably performed. The hypertension detection had lower performance utilizing only PPG than both ECG and PPG.

Pressure ulcers are a significant concern in patient care, particularly for those with limited mobility and extended hospital stays. Wavy mattresses are shown an effective tool for preventing or promoting the healing of these wounds by preventing pressure localization in different body regions. The current study aimed to present a novel double-layered wavy mattress design for the prevention and recovery of pressure ulcers, addressing some of the limitations of existing mattresses. The novel mattress includes double-layered cells, with the upper and lower layers, filled with water and air, respectively. The temperature of water in the cells can be manually adjusted to meet patients’ needs, prevent skin sweating, regulate body temperature, and promote blood flow in areas susceptible to pressure ulcers. Patients who used this novel mattress during their hospitalization experienced a significantly shorter recovery period for bedsores compared to those who used other mattresses, showing that the novel wavy mattress is an effective tool for preventing and recovering from pressure ulcers in long-term hospitalized patients with limited mobility.