Browsing by Author "Dawit Assefa Haile"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Biomechanical and Finite Element Analysis of Compressive Forces on the Lumbar Spine During Lifting Task by Ethiopian Construction Laborers
    (Addis Ababa University, 2025-12-01) Beya Mulugeta; Dawit Assefa Haile
    Lower back pain (LBP) is a prevalent issue, particularly in physically demanding occupations like construction work, where heavy lifting and poor ergonomic practices significantly increase injury risks. In 2020, an estimated 619 million people worldwide were affected by LBP, with projections signifying a rise to 843 million by 2050. The construction sector in Ethiopia reports a high inci dence of work-related lower back pain, yet research quantifying this issue is scarce. The current study aims to assess the biomechanical impacts of different lifting techniques and weight combi nations on the lumbar spine to identify key factors contributing to lower back pain among con struction laborers. To achieve this, the study evaluated 210 scenarios involving various lifted weights (0 to 125kg), lw - length of moment arm from lifted weight (0 to 0.5 meters), and α - angle between the extensor muscle force with body weight and lifted load (0°to 90°) using finite element analysis (FEA). The methodology involved converting 2D CT scan images into a 3D model for precise simulation of spinal stress under different conditions followed by model validation and FEA. The results revealed a maximum compressive force of 1419.71N when lifting 125kg at a 0° angle with a 0.5m moment arm and minimum compressive force of 126.196N at 90° angle with zero moment arm were obtained. The Von Mises stress result also ranged from 17.44MPa to 542.2MPa, showing peak stress at 0° angle and minimum at 90°. Increased weight and longer moment arms significantly raised the stress, particularly affecting the facet joints of L3, L4 and L5 of lumbar spine with the anterior part of L5 lumbar spine exhibiting significant stress. Further analysis indicated that directional deformation results of current study ranged from 0.0000629m to 0.001033m, with higher deformation associated with heavier loads and lower lifting angles. Despite reduced stress at higher angles, improper lifting techniques still posed risks. This result indicates the importance of minimizing the distance between the body and the lifted weight, as well as maintaining proper lifting posture as essential strategies for reducing compressive load on the lumbar spine and preventing injures. This study also highlights that heavier loads and upright posture increase compressive force, particularly in the L4-L5 region, posing a higher risk of long term injuries. To mitigate these risks, a proper lifting technique, ergonomic intervention and work place safety protocols that reduce compressive stress on the lumbar spine should be implemented. Reducing manual lifting needs, incorporating mechanical aids, and scheduling rest breaks can mit igate the risks. These measures are crucial for alleviating lumbar spine stress and preventing long term injuries, such as disc herniation.
  • No Thumbnail Available
    Item
    SVM Based Detection and Classification of Breast Abnormalities in Mammography Images
    (Addis Ababa University, 2024-11) Rahel Beyene Shewa; Dawit Assefa Haile
    Breast cancer is the second leading cause of death among females. Digital mammography is the most effective screening technique for early detection of breast cancer and other abnormalities. However, interpreting digital mammograms can be challenging due to the small differences in attenuation among various soft tissue structures in the female breast. This results in low-quality X-ray images, high background noise, and artifacts, making diagnosis difficult. Therefore, it is essential to develop an effective computer-aided diagnosis system to improve the detection and classification of abnormalities in mammogram images. The proposed Support Vector Machine (SVM)-based mammography image detection and classification method involves four stages: preprocessing, segmentation, feature extraction, and classification. During preprocessing, the images undergo denoising with median and winner filters, pectoral muscle removal using the seeded region grow algorithm, background removal through morphological operations, and image enhancement with range contrast adjustment and Contrast Limited Adaptive Histogram Equalization (CLAHE). Segmentation is performed using global thresholding. In the feature extraction stage, 24 features were calculated from locally computed Gray Co-occurrence Matrices (GLCM). Finally, SVM was employed to classify the mammogram images. The study utilized 274 mammograms, of which 102 were abnormal-samples (malignant or benign) and 172 were normal images taken from control subjects. Of these, 80% were used for training and 20% for testing the SVM classification model. Based on the performance metrics, the system has an 84.82% probability of detecting abnormalities in patients breast tumor with positive predictive value (PPV) of 94.06%. It correctly classifies mammogram images as normal in 96.3% of patients without breast tumor (specificity = 96.3%), with an overall accuracy of 91.6% with negative predictive value (NPV) of 90.17%. Among the various feature combinations, dissimilarity and inverse difference normalized features provided the highest AUC value of 0.92.