Papers by Dr Hanaa Mohsin Al Abboodi Al Abboodi

Review of Eye Diseases Detection and Classification Using Deep Learning Techniques
Bio web of conferences/BIO web of conferences, 2024
Automated diagnosis of eye diseases using machine and deep learning models has become increasingl... more Automated diagnosis of eye diseases using machine and deep learning models has become increasingly popular. Glaucoma, cataracts, diabetic retinopathy, Myopia, and age-related macular degeneration are common eye diseases that can cause severe damage. It is crucial to detect eye diseases early to prevent any potentially serious consequences. Early detection of eye disease is vital for effective treatment. Doing in-depth reading to identify any potential signs of eye disease is highly recommended. This paper will review all machine learning models built to detect and classify eye diseases in addition to helping grasp all limitations and challenges in this field. Recognizing eye diseases is a difficult task that typically requires several years of medical experience. This research is to be conducted to serve as a starting point for finding the most versatile solution. This research aims to review eye disease classification using deep learning models, including VGG16, ResNet, and Inception. The general classification model consists of these steps: The first step is to collect the globally obtainable datasets for the eye disease and pre-process them to ensure the generalization of experiments. The goal is to train the model to recognize disease symptoms instead of tweaking the outcomes for a specific dataset section. With the successful deployment of deep learning techniques for image classification and object recognition, research is now directed towards deep learning techniques instead of traditional handcrafted methods. One possible solution for the eye diseases classification challenge is to use a pre-trained deep CNN model for representation and feature extraction. This solution can be followed by classifier methods, such as support vector machines (SVM), multilayer perceptron (MLP), etc. It has been detected that CNN-based methods learned on large-scale marked datasets can be used for eye disease classification tasks with limited training datasets.
Bulletin of Electrical Engineering and Informatics, Jan 31, 2024

TEM Journal
Radiological diagnostics are undeniably crucial in everyday healthcare. CT scans can sometimes pr... more Radiological diagnostics are undeniably crucial in everyday healthcare. CT scans can sometimes provide misleading clues and delay successive treatment due to artifacts caused by reflected radiation from metallic implants. This work successfully segments multiple organs containing metal implants and discards artifacts using a combination of non-rigid transformations, Scribbles-based segmentation, and a pre-trained auto segmentation model (DynaUnet -Pretrained-Model). The presented transfer learning model combined the benefits of an interactive environment and reduced computational and processing-time costs. The transfer learning model proved high auto segmentation performance for multi-organs with metal implants' presence by decreasing metal artefact's impact on the segmentation process and the achieved segmentation accuracies between 0.9998 for the spleen and 0.9829 for the stomach.

International Journal of Intelligent Engineering and Systems, Oct 30, 2023
The acoustic features extracted from the speech-signal are a critical challenge for implementing ... more The acoustic features extracted from the speech-signal are a critical challenge for implementing an accurate speaker identification system. In this paper, two-dimension discrete multi-wavelet transform (2D-DMWT) in conjunction with the deep learning neural networks are proposed for speaker identification. The DMWT is based on a vital sampling scheme preprocessing that uses the filter invented by Geronimo, Hardian, and Massopust, which is call GHM. The system proposed involves firstly preprocessing in which the speech-signal is resampled into 16kHz. Then, the speech-signal is divided to five different durations: 0.5 sec., 1 sec., 2 sec., 3 sec., and 5 sec. In this paper, each duration is tested separately. Second, 2D-DMWT is employed to obtain discriminant features from the speech-signal and reduce speech-signal dimensions in the feature's selection phase. Finally, neural network algorithm based on convolution neural network (CNN) is used for classification. The system proposed is tested using four databases: SALU-AC, ELSDSR, TIMIT, and RAVDESS. These databases include various speech variances, such as age, gender, etc. The results obtained by the proposed system are 95.86%, 96.59%, 89.90%, and 89.83% for 0.5sec of the SALU-AC, ELSDSR, RAVDESS, and TIMIT databases, respectively. For 1sec, the SALU-AC, ELSDSR, RAVDESS, and TIMIT databases obtained 96.30%, 97.31%, 96.05%, and 93.59%, respectively. The SALU-AC, ELSDSR, RAVDESS, and TIMIT databases achieved 96.63%, 97.76%, 96.12%, and 95.90%, respectively, over the 2sec time duration. During the time duration of 3sec, the SALU-AC, ELSDSR, and RAVDESS databases obtained 97.04%, 98%, and 97.96%, respectively. For 5sec, the SALU-AC, and ELSDSR databases attained 97.56%, and 98.30%, respectively. The results accomplished by the proposed system are outperformed those results discussed in the previous works based on the same databases.
Journal of Physics: Conference Series, 2021
View the article online for updates and enhancements. You may also like Computed tomography super... more View the article online for updates and enhancements. You may also like Computed tomography super-resolution using deep convolutional neural network Junyoung Park, Donghwi Hwang, Kyeong Yun Kim et al. Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

BIO Web of Conferences 97, 2024
Automated diagnosis of eye diseases using machine and deep learning models has become increasingl... more Automated diagnosis of eye diseases using machine and deep learning models has become increasingly popular. Glaucoma, cataracts, diabetic retinopathy, Myopia, and age-related macular degeneration are common eye diseases that can cause severe damage. It is crucial to detect eye diseases early to prevent any potentially serious consequences. Early detection of eye disease is vital for effective treatment. Doing in-depth reading to identify any potential signs of eye disease is highly recommended. This paper will review all machine learning models built to detect and classify eye diseases in addition to helping grasp all limitations and challenges in this field. Recognizing eye diseases is a difficult task that typically requires several years of medical experience. This research is to be conducted to serve as a starting point for finding the most versatile solution. This research aims to review eye disease classification using deep learning models, including VGG16, ResNet, and Inception. The general classification model consists of these steps: The first step is to collect the globally obtainable datasets for the eye disease and pre-process them to ensure the generalization of experiments. The goal is to train the model to recognize disease symptoms instead of tweaking the outcomes for a specific dataset section. With the successful deployment of deep learning techniques for image classification and object recognition, research is now directed towards deep learning techniques instead of traditional handcrafted methods. One possible solution for the eye diseases classification challenge is to use a pre-trained deep CNN model for representation and feature extraction. This solution can be followed by classifier methods, such as support vector machines (SVM), multilayer perceptron (MLP), etc. It has been detected that CNN-based methods learned on large-scale marked datasets can be used for eye disease classification tasks with limited training datasets.

IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES, 2021
In a number of applications, artificial neural networks, including pattern recognition, control, ... more In a number of applications, artificial neural networks, including pattern recognition, control, robotics and Bioinformatics, are employed as effective computing techniques. Researchers were motivated to develop neural artificial networks by studying the biological brain because of their wider application. Recently, notable progress was made in neurological analysis, revealing novel biological neuronal properties. Currently, new technologies will capture time changes in depth in the interior activity of the brain and make the relationship between brain activity and the perception of a given input clearer. This fresh information has a diode to the Spiking Neural Network (SNN), a replacement style that dependably draws more biological features to increase the process skills. This article briefly reviews neural spiking networks as a third generation of neural networks and its evolutionary algorithms in some areas of use. Also, this work presents a literary evaluation of SNN's progressive learning algorithms with single and multiple spikes. Deep neural spiking networks have been studied for booting and difficulties and potential have been identified within the SNN area. Kewords-Spiking Neural Networks, third generation of neural networks, learning in SNN, Spiking neuron models.

International Journal of Intelligent Engineering and Systems, 2023
The acoustic features extracted from the speech-signal are a critical challenge for implementing ... more The acoustic features extracted from the speech-signal are a critical challenge for implementing an accurate speaker identification system. In this paper, two-dimension discrete multi-wavelet transform (2D-DMWT) in conjunction with the deep learning neural networks are proposed for speaker identification. The DMWT is based on a vital sampling scheme preprocessing that uses the filter invented by Geronimo, Hardian, and Massopust, which is call GHM. The system proposed involves firstly preprocessing in which the speech-signal is resampled into 16kHz. Then, the speech-signal is divided to five different durations: 0.5 sec., 1 sec., 2 sec., 3 sec., and 5 sec. In this paper, each duration is tested separately. Second, 2D-DMWT is employed to obtain discriminant features from the speech-signal and reduce speech-signal dimensions in the feature's selection phase. Finally, neural network algorithm based on convolution neural network (CNN) is used for classification. The system proposed is tested using four databases: SALU-AC, ELSDSR, TIMIT, and RAVDESS. These databases include various speech variances, such as age, gender, etc. The results obtained by the proposed system are 95.86%, 96.59%, 89.90%, and 89.83% for 0.5sec of the SALU-AC, ELSDSR, RAVDESS, and TIMIT databases, respectively. For 1sec, the SALU-AC, ELSDSR, RAVDESS, and TIMIT databases obtained 96.30%, 97.31%, 96.05%, and 93.59%, respectively. The SALU-AC, ELSDSR, RAVDESS, and TIMIT databases achieved 96.63%, 97.76%, 96.12%, and 95.90%, respectively, over the 2sec time duration. During the time duration of 3sec, the SALU-AC, ELSDSR, and RAVDESS databases obtained 97.04%, 98%, and 97.96%, respectively. For 5sec, the SALU-AC, and ELSDSR databases attained 97.56%, and 98.30%, respectively. The results accomplished by the proposed system are outperformed those results discussed in the previous works based on the same databases.

Computer Engineering and Intelligent Systems, 2013
A spatial database is a database that is optimized to store and query data that represents object... more A spatial database is a database that is optimized to store and query data that represents objects defined in a geometric space. A spatial preference query ranks objects based on the qualities of features in their spatial neighborhood. For example, using a real estate agency database of flats for lease, a customer may want to rank the flats with respect to the appropriateness of their location, defined after aggregating the qualities of other features (e.g., restaurants, cafes, hospital, market, etc.) within their spatial neighborhood. Such a neighborhood concept can be specified by the user via different functions. It can be an explicit circular region within a given distance from the flat. Another intuitive definition is to assign higher weights to the features based on their proximity to the flat. In this paper, we formally define spatial preference queries and propose appropriate indexing techniques and search algorithms for them. Extensive evaluation of our methods on both real and synthetic data reveals that an optimized branch-and-bound solution is efficient and robust with respect to different parameters.

TEM Journa, 2023
Radiological diagnostics are undeniably crucial in everyday healthcare. CT scans can sometimes pr... more Radiological diagnostics are undeniably crucial in everyday healthcare. CT scans can sometimes provide misleading clues and delay successive treatment due to artifacts caused by reflected radiation from metallic implants. This work successfully segments multiple organs containing metal implants and discards artifacts using a combination of non-rigid transformations, Scribblesbased segmentation, and a pre-trained auto segmentation model (DynaUnet-Pretrained-Model). The presented transfer learning model combined the benefits of an interactive environment and reduced computational and processing-time costs. The transfer learning model proved high auto segmentation performance for multi-organs with metal implants' presence by decreasing metal artefact's impact on the segmentation process and the achieved segmentation accuracies between 0.9998 for the spleen and 0.9829 for the stomach.

International Journal of Intelligent Engineering and Systems, 2024
The research presents a new technique for segmenting brain tumors using the UNet framework enhanc... more The research presents a new technique for segmenting brain tumors using the UNet framework enhanced with an attention mechanism. By incorporating attention processes that selectively emphasize prominent aspects while recording comprehensive contextual information, our strategy overcomes the challenges of brain tumor delineation. The suggested UNet-attention model is intended to outperform traditional segmentation techniques regarding precision and clinical applicability. Integrating spatial and channel attention processes into the UNet design is one of our study's significant achievements. The spatial attention mechanism's focus improves the capacity of the model to differentiate the mechanism's tumor and non-tumor areas. Also, incorporating contextual clues from multi-scale hierarchies allows for a thorough comprehension of visual properties. The discrete wavelet transform has been applied as a feature extraction method to enhance the model performance regarding time and memory consumption. A wide range of datasets is evaluated in-depth, proving our UNet-attention model's superiority. Advanced deep learning is made possible by combining attention processes and contextual data to delineate tumors precisely and clinically. Many evaluation criteria involving dice scores, accuracy, mean IoU, sensitivity, specificity, and Hausdorff distance have been applied to evaluate our model performance in different aspects. The model attained a dice coefficient of 0.9971. The model's specificity of 0.9988 is particularly noteworthy, demonstrating its exceptional ability to identify regions without tumors accurately. The model also achieved 0.9986 accuracies, 0.9142 mean IoU, Hausdorff distance (mm) 3.48. These evaluation values were obtained for applying our model on flair images from BraTS 2020.

Medical Image Denoising using Adaptive Spatial Domain Schemes with Additive Noise
Journal of University of Babylon, 2016
Image denoising is one of the most significant tasks in medical image processing due to the signi... more Image denoising is one of the most significant tasks in medical image processing due to the significant information obtained by these images related to the human body or the tissues of the body’s organs. So, many methods have been proposed for removing the noise that affects the medical images. In this research a new algorithm has been proposed for denoisning medical images work in spatial domain. A new algorithm depends on the idea that combine between characteristic of different filters which work in spatial domain with adaptive sizes of windows for reaching to the acceptance results in remove noise from medical images. This algorithm called Adaptive Window Wiener Filter (AWWF). Two types of medical images and noise that corrupt these medical image used in this research. The first type is Poisson noise which corrupts X-ray medical images and the second type is Rician noise which corrupts MRI medical images. The algorithm begins with using a median filter on a noisy image to get th...
Uploads
Papers by Dr Hanaa Mohsin Al Abboodi Al Abboodi