| Volume 29, Issue 3 | |
| Studying the Effects of the Aquatic Exercise Rehabilitation Training on the Patients with Knee Ligament Injury | 191-200 |
| Jian Ge, Wei Dong | |
| doi: 10.7546/ijba.2025.29.3.000929 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Jian Ge, Wei Dong (2025) Studying the Effects of the Aquatic Exercise Rehabilitation Training on the Patients with Knee Ligament Injury, Int J Bioautomation, 29 (3), 191-200, doi: 10.7546/ijba.2025.29.3.000929 | |
| Abstract: As one of the most complex and flexible joints in the human body, the knee joint is highly susceptible to injury during exercise. Therefore, it is crucial to adopt a scientific approach to deal with sports knee injuries in a timely and effective manner. This study selected 20 individuals with similar physical parameters, like height and weight, from Tangshan Polytechnic College, China, all of whom had knee joint injuries caused by training. They were randomly divided into an experimental group and a control group. The experimental group underwent aquatic rehabilitation training, while the control group received conventional land-based rehabilitation training. Their knee joints were assessed for pain levels, range of motion, functions, and weight-bearing capacity before and after the experiment. It was found that the flexion range of the knee joint of people receiving aquatic exercise rehabilitation training was 10° greater than those receiving conventional training, the basic function score of the knee joint was approximately three points higher, and the bearing strength of the knee joint was about 10 kg larger. The experimental results show that both aquatic exercise rehabilitation training and conventional rehabilitation training can improve knee injuries caused by exercise; however, the rehabilitation effect of aquatic exercise rehabilitation training is better than that of conventional training.
Keywords: Knee joint injury, Aquatic exercise, Rehabilitation training | |
| Alzheimer’s Disease Dementia Detection Using Transfer Learning Based Convolutional Neural Network Model | 201-216 |
| Amar A. Dum, Kshama V. Kulhalli, Priyanka Singh | |
| doi: 10.7546/ijba.2025.29.3.000950 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Amar A. Dum, Kshama V. Kulhalli, Priyanka Singh (2025) Alzheimer’s Disease Dementia Detection Using Transfer Learning Based Convolutional Neural Network Model, Int J Bioautomation, 29 (3), 201-216, doi: 10.7546/ijba.2025.29.3.000950 | |
| Abstract: Alzheimer’s disease (AD) is the most common type of dementia that is not a result of natural aging. In most countries, it is one of the leading causes of death for seniors. One of the main methods for detecting AD is by magnetic resonance imaging (MRI). Several machine learning (ML) and deep learning (DL) techniques have been put out in recent years for the automated detection of AD, but the accuracy of these techniques is currently limited. So, the primary goal of this research is to offer a model for precise AD detection that is based on transfer learning. For the purpose of detecting AD in this paper, we have used two different models. We studied and evaluated models from two different platforms, GoogleNet and residual networks (ResNet). Different variants of ResNet (ResNet18, ResNet34, ResNet50, and ResNet101) were studied. In this study, specificity, accuracy, positive predictive rate, sensitivity, F1 score, balanced accuracy, Fowlkes-Mallows index, and Youden’s J statistics were investigated. ResNet18, ResNet34, ResNet50, and ResNet101 have shown a precision of 97.28%, 98.25%, 98.41%, and 98.57%. GoogleNet has accuracy rate of 96.32%. The learning curve is also presented in this work, and shows a good fit for the ResNet101 model. The proposed networks were compared on the basis of computational time. ResNet101 performed better than other networks in all the parameters and had the largest computational time. MRI images from the Alzheimer’s disease neuroimaging initiative (ADNI) database have been used and compared with similar work based on ML and DL. A comparison with the existing methods showed that the proposed method could help in the reliable detection of AD.
Keywords: Alzheimer’s disease, Dementia detection, Convolutional neural network, Transfer learning | |
| A Non-invasive Deep Learning Model for Prostate Cancer Diagnosis with MRI | 217-230 |
| Mohammed Ridha Youbi, Amel Feroui | |
| doi: 10.7546/ijba.2025.29.3.001043 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Mohammed Ridha Youbi, Amel Feroui (2025) A Non-invasive Deep Learning Model for Prostate Cancer Diagnosis with MRI, Int J Bioautomation, 29 (3), 217-230, doi: 10.7546/ijba.2025.29.3.001043 | |
| Abstract: Prostate cancer (PCa) remains a significant global health concern, with accurate Gleason grade assessment crucial for guiding treatment. Traditional histopathology relies on invasive biopsy and subjective evaluation. This study proposes a novel non-invasive approach for Gleason grade prediction using magnetic resonance imaging (MRI) and deep learning (DL). Our method comprises three main steps: tumor region segmentation using Fuzzy c-means (FCM); relevant feature extraction via modified residual network (ResNet50) model; and Gleason grade classification using a convolutional neural network (CNN). Through extensive experimentation, the proposed CNN model achieved an accuracy of 92.00%, sensitivity of 92.00%, specificity of 92.00%, and an area under the curve receiver operating characteristic (AUC-ROC) of 0.95. These robust results highlight the potential of our DL framework to accurately differentiate between low-grade and high-grade PCa, thereby automating aspects of the diagnostic process, reducing reliance on subjective interpretation, and ultimately improving patient outcomes and treatment decisions.
Keywords: MRI, Prostate cancer, Non-invasive Gleason grade, Image segmentation, Convolutional neural network classification, Feature extraction | |
| Motion Force Analysis of Group B Difficulty Movements in College Students’ Aerobics Based on Surface Electromyography Characteristics | 231-244 |
| Change Bu, Yangyang Liu | |
| doi: 10.7546/ijba.2025.29.3.000986 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Change Bu, Yangyang Liu (2025) Motion Force Analysis of Group B Difficulty Movements in College Students’ Aerobics Based on Surface Electromyography Characteristics, Int J Bioautomation, 29 (3), 231-244, doi: 10.7546/ijba.2025.29.3.000986 | |
| Abstract: This paper aims to understand the motion force characteristics of college students when performing group B difficulty movements in aerobics through surface electromyography and 3D camera technology. Subjects were five male aerobics national first-grade. The surface electromyography characteristics were collected by Noraxon electromyography system and kinematic characteristics were collected by a motion capture system. Subjects were required to perform the B588 movement (1/2 turn pike jump 1/2 twist to push up) three times, and the best one was analysed. The average value was taken to analyse the athletes’ motion force characteristics. Results showed that in the take-off phase, the lower limb muscles primarily underwent electrical discharge. The left rectus femoris muscle exhibited the highest discharge during the cushioning and extension phases, measuring 256.17 μV and 185.77 μV, respectively, with full extension of the hip and knee joints. During the flight phase, both lower limb and abdominal muscles exerted noticeable force while maintaining extended knee and ankle joints, although there was a slight difference in angle between left and right ankles. In the landing phase, all muscles exerted significant force and the elbow joints were primarily responsible for joint cushioning. Completing the B588 movement requires athletes to have higher levels of lower limb explosive force, body balance force, and joint control force. During the training process, athletes should focus on strengthening muscle strength and improving ankle joint stability.
Keywords: Surface electromyography, Aerobics, B588 movement, Difficult movements, Kinematics |
Sponsored by National Science Fund of Bulgaria, Grant No КП-06-НП6-14, 2025
© 2025, BAS, Institute of Biophysics and Biomedical Engineering