Yazar "Mohammed, Ali Abdulwahhab" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    A review on medical image applications based on deep learning techniques
    (University of Portsmouth, 2024) Abdulwahhab, Ali H.; Mahmood, Noof T.; Mohammed, Ali Abdulwahhab; Myderrizi, Indrit; Al-Jumaili, Mustafa Hamid
    The integration of deep learning in medical image analysis is a transformative leap in healthcare, impacting diagnosis and treatment significantly. This scholarly review explores deep learning’s applications, revealing limitations in traditional methods while showcasing its potential. It delves into tasks like segmentation, classification, and enhancement, highlighting the pivotal roles of Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs). Specific applications, like brain tumor segmentation and COVID-19 diagnosis, are deeply analyzed using datasets like NIH Clinical Center’s Chest X-ray dataset and BraTS dataset, proving invaluable for model training. Emphasizing high-quality datasets, especially in chest X-rays and cancer imaging, the article underscores their relevance in diverse medical imaging applications. Additionally, it stresses the managerial implications in healthcare organizations, emphasizing data quality and collaborative partnerships between medical practitioners and data scientists. This review article illuminates deep learning’s expansive potential in medical image analysis, a catalyst for advancing healthcare diagnostics and treatments.
  • Küçük Resim
    Öğe
    BCI-DRONE CONTROL BASED ON THE CONCENTRATION LEVEL AND EYE BLINK SIGNALS USING A NEUROSKY HEADSET
    (University of Kufa, 2025) Mohammed, Ali Abdulwahhab; Abdulwahhab, Ali H.; Abdulaal, Alaa Hussein; Mahmood, Musaria Karim; Myderrizi, Indrit; Yassin, Riyam Ali; Abdulridha, Taha Talib; Valizadeh, Morteza
    Brain neurons activate Human movements by producing electrical bio-signals. Neuron activity is used in several technologies by operating their applications based on mind waves. The Brain-Computer Interface (BCI) technology enables a processor to connect with the brain using a signal received from the brain. This study proposes a drone controlled using EEG signals acquired by a Neurosky device based on the BCI system. Two active signals are adapted for controlling the drone motions: concentration brain signals portrayed by attention level and the eye blinks as an integer value. A dynamic classification method is implemented via a Linear Regression algorithm for attention-level code. The eye blinking generates a binary code to control the drone's motions. The accuracy of this code is improved through Artificial Neural Networks and Machine Learning techniques. These codes (attention level and eye blink codes) drive two controlling layers and manipulate nine possible drone movements. The experiment was evaluated with several users and showed high performance for the classification methods and developed algorithm. The experiment shows a 90.37% accuracy control that outperforms most existing experiments. Also, the experiment can support 16 commands, making the algorithm appropriate for various applications.
  • Küçük Resim
    Öğe
    Detection Lung Nodules Using Medical CT Images Based on Deep Learning Techniques
    (2025) Mohammed, Ali Abdulwahhab; Abdulwahhab, Ali H.; Ibraheem, Ibraheem Kasim
    Lung nodule cancer detection is a critical and complex medical challenge. Accuracy in detecting lung nodules can significantly improve patient prognosis and care. The main challenge is to develop a detection method that can accurately distinguish between benign and malignant nodules and perform effectively under various imaging conditions. The development of technology and investment in deep learning techniques in the medical field make it easy to use Positron Emission Tomography (PET) and Computed Tomography (CT). Thus, this paper presents lung cancer detection by filtering the PET-CT image, obtaining the lung region of interest (ROI), and training using Convolution neural network (CNN)-Deep learning models for defending the nodules' location. The limitation dataset composed of 220 cases with 560 nodules with fixed Hounsfield Units (HU) is used to increase the training's speed and save data. The trained models involve CNN, DCNN, 3DCNN, VGG 19, ResNet 18, Inception V1, and Inception-ResNet to detect the lung nodules. The experiment shows high-speed training with VGG 19 outperforming the rest of deep learning, it achieves accuracy, Precision, Specificity, Sensitivity, F1-Score, IoU, FP rate with standard division; 98.65 f 0.22, 98.80 f 0.15, 98.70 f 0.20, 98.55 f 0.18, 98.60 f 0.16, 0.94 f 0.03, 1.05 f 0.22, respectively. Moreover, the experiment results show an overall error rate and a standard division between f 0.04 to f 0.54 distributed over the calculation terms.
  • [ X ]
    Öğe
    Detection of epileptic seizure using EEG signals analysis based on deep learning techniques
    (Elsevier, 2024) Abdulwahhab, Ali H.; Abdulaal, Alaa Hussein; Thary Al-Ghrairi, Assad H.; Mohammed, Ali Abdulwahhab; Valizadeh, Morteza
    The brain neurons' electrical activities represented by Electroencephalogram (EEG) signals are the most common data for diagnosing Epilepsy seizure, which is considered a chronic nervous disorder that cannot be controlled medically using surgical operation or medications with more than 40 % of Epilepsy seizure case. With the progress and development of artificial intelligence and deep learning techniques, it becomes possible to detect these seizures over the observation of the non-stationary-dynamic EEG signals, which contain important information about the mental state of patients. This paper provides a concerted deep machine learning model consisting of two simultaneous techniques detecting the activity of epileptic seizures using EEG signals. The time-frequency image of EEG waves and EEG raw waves are used as input components for the convolution neural network (CNN) and recurrent neural network (RNN) with long- and short-term memory (LSTM). Two processing signal methods have been used, Short-Time Fourier Transform (STFT) and Continuous Wavelet Transformation (CWT), have been used for generating spectrogram and scalogram images with sizes of 77 × 75 and 32 × 32, respectively. The experimental results showed a detection accuracy of 99.57 %, 99.57 % using CWT Scalograms, and 99.26 %, 97.12 % using STFT spectrograms as CNN input for the Bonn University dataset and the CHB-MIT dataset, respectively. Thus, the proposed models provide the ability to detect epileptic seizures with high success compared to previous studies.