Saida Sarra Boudouh

Dr. Saida Sarra Boudouh

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 May 2024 in Signal, Image and Video Processing
Verified
Journal Article
Closed access
PDF file
MCMaroua Cheknane
Maroua Cheknane
TBTahar Bendouma
Tahar Bendouma
SBSaida Sarra Boudouh
Saida Sarra Boudouh

8 May 2022
Verified
Conference Paper
Closed access
SBSaida Sarra Boudouh
Saida Sarra Boudouh
MBMustapha Bouakkaz
Mustapha Bouakkaz
Breast cancer is the most common form of cancer among women worldwide. Mammography has become a valuable tool for detecting breast cancer. We were able to achieve the purpose of our study, which was to create an accurate Convolutional Neural Network (CNN) model that classifies mammography images into normal and abnormal using deep transfer learning and data augmentation approaches, to avoid overfitting issues with images. The Mammographic Image Analysis Society MiniMammographic Database (MiniMIAS) was used to train and test the CNN model. The shortage of abnormal images in the MiniMIAS caused a low accuracy. Because of that, 92 abnormal images were added from the Digital Database for Screening Mammography (DDSM), which leads us to great accuracy. The proposed method starts with a pre-processing step which includes several filters that eliminate any noises, background, enhances the images, and data augmentation for better training. AlexNet was modified and trained after splitting the dataset into 75%, 5%, and 20% as training, validation, and testing sets respectively. The evaluation results were not very satisfying with the MiniMIAS database with 96.87%. On the other hand with balanced data, the obtained results were very satisfying with 99.99%, and better results according to the existing models, which prove that the chosen filters in the pre-processing phase, as well as the chosen pre-trained model AlexNet, is very useful and suitable for breast tumor detection.


14 August 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
SBSaida Sarra Boudouh
Saida Sarra Boudouh
MBMustapha BOUAKKAZ
Mustapha BOUAKKAZ

9 March 2023 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
SBSaida Sarra Boudouh
Saida Sarra Boudouh
MBMustapha BOUAKKAZ
Mustapha BOUAKKAZ
Female breast cancer has now surpassed lung cancer as the most common form of cancer globally. Although several methods exist for breast cancer detection and diagnosis, mammography is the most effective and widely used technique. In this study, our purpose is to propose an accurate breast tumor detection model as the first step into cancer detection. To guarantee diversity and a larger amount of data, we collected samples from three different databases: the Mammographic Image Analysis Society MiniMammographic (MiniMIAS), the Digital Database for Screening Mammography (DDSM), and the Chinese Mammography Database (CMMD). Several filters were used in the pre-processing phase to extract the Region Of Interest (ROI), remove noise, and enhance images. Next, transfer learning, data augmentation, and Global Pooling (GAP/GMP) techniques were used to avoid imagery overfitting and to increase accuracy. To do so, seven pre-trained Convolutional Neural Networks (CNNs) were modified in several trials with different hyper-parameters to determine which ones are the most suitable for our situation and the criteria that influenced our results. The selected pre-trained CNNs were Xception, InceptionV3, ResNet101V2, ResNet50V2, ALexNet, VGG16, and VGG19. The obtained results were satisfying, especially for ResNet50V2 followed by InceptionV3 reaching the highest accuracy of 99.9%, and 99.54% respectively. Meanwhile, the remaining models achieved great results as well, proving that our approach starting from the chosen filters, databases, and pre-trained models with the fine-tuning phase and the used global pooling technique is effective for breast tumor detection. Furthermore, we also managed to determine the most suitable hyper-parameters for each model using our collected dataset.

15 March 2022
Verified
Conference Paper
Closed access
SBSaida Sarra Boudouh
Saida Sarra Boudouh
MBMustapha Bouakkaz
Mustapha Bouakkaz
Breast cancer has become the second leading cause of death among women. Mammogram images are the best and most often used method for detecting breast cancer. This study aims to build an accurate breast tumor detection model that classifies mammogram images into normal and abnormal (tumor). Transfer learning and data augmentation approaches were employed to prevent imagery overfitting problems using three pre-trained convolutional neural networks: AlexNet, VGG16, and VGG19 without trainable layers. The dataset was gathered from two different databases to ensure diversity in the images. We gathered 4000 images from each Digital Database for Screening Mammography and the Chinese Mammography Database. The obtained results were very satisfying according to the previous studies. 99.5% and 100% accuracy were obtained from AlexNet and VGG16 (with trainable layers), better than the existing breast tumour detection models. The applied filters in the pre-processing phase were effective based on the obtained results. Also, we determined that adopting a pre-trained model with trainable layers provides better results than using the model as it is without training the layers.