Browsing by Author "Darici, Muazzez Buket"

Now showing 1 - 4 of 4

Citation - WoS: 1
Citation - Scopus: 1
Age Classification by WGAN Brain MR Image Augmentation
(IEEE, 2024) Yaman, Batuhan; Yilmaz, Ozge Zeynep; Darici, Muazzez Buket; Ozmen, Atilla
Medical image augmentation plays a crucial role in enhancing the performance of Artificial Intelligence (AI) applications in medical sciences. Augmenting medical images is important for solving data scarcity, increasing data diversity, enhancing robustness and reliability of model and improving training and test results that can be done in medical sciences. In this work we show that Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) can be used for increasing the performance of data classification. To achieve that, we have augmented healthy brain MR images by using WGAN and updated the dataset. The results give that when dataset augmented by WGAN-GP is used as input for CNN-based model to solve age classification problem, accuracy of this model increases to 98,37% from 95,14%. It can be concluded that the purposed WGAN-based brain MR image augmentation method enhances the performance of image classification.
Brain Age Estimation From Mri Images Using 2d-Cnn Instead of 3d-Cnn
(2021) Gezer, Murat; Yıldırım, Şüheda; Darici, Muazzez Buket
Human Brain Age has become a popular aging biomarker and is used to detect differences among healthy individuals. Because of the specific changes in the human brain with aging, it is possible to estimate patients’ brain ages from their brain images. Due to developments of the ability of CNN in classification and regression from images, in this study, one of the most popular state of the art models, the DenseNet model, is utilized to estimate human brain ages using transfer learning. Since this process requires high memory load with 3D-CNN, 2D-CNN is preferred for the task of Brain Age Estimation (BAE). In this study, some experiments are carried out to reduce the number of computations while preserving the total performance. With this aim, center slices of each three brain planes are used as the inputs of the DenseNet model, and different optimizers such as Adam, Adamax and Adagrad are used for each model. The dataset is selected from the IXI (Information Extraction from Images) MRI data repository. The MAE evaluation metric is used for each model with different input set to evaluate performance. The best achieved Mean Absolute Error (MAE) is 6.3 with the input set which consisted of center slices of the sagittal plane of brain scan and the Adamax parameter.
Citation - Scopus: 4
A Comparative Study on Denoising from Facial Images Using Convolutional Autoencoder
(Gazi Univ, 2023) Darici, Muazzez Buket; Erdem, Zeki
Denoising is one of the most important preprocesses in image processing. Noises in images can prevent extracting some important information stored in images. Therefore, before some implementations such as image classification, segmentation, etc., image denoising is a necessity to obtain good results. The purpose of this study is to compare the deep learning techniques and traditional techniques on denoising facial images considering two different types of noise (Gaussian and Salt&Pepper). Gaussian, Median, and Mean filters have been specified as traditional methods. For deep learning methods, deep convolutional denoising autoencoders (CDAE) structured on three different optimizers have been proposed. Both accuracy metrics and computational times have been considered to evaluate the denoising performance of proposed autoencoders, and traditional methods. The utilized standard evaluation metrics are the peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM). It has been observed that overall, while the traditional methods gave results in shorter times in terms of computation times, the autoencoders performed better concerning the evaluation metrics. The CDAE based on the Adam optimizer has been shown the best results in terms of PSNR and SSIM metrics on removing both types of noise.
Citation - WoS: 10
Performance Analysis of Combination of Cnn-Based Models With Adaboost Algorithm To Diagnose Covid-19 Disease
(Gazi Univ, 2023) Darici, Muazzez Buket
At the end of 2019, Covid-19, which is a new form of Coronavirus, has spread widely all over the world. With the increasing daily cases of this disease, fast, reliable, and automatic detection systems have been more crucial. Therefore, this study proposes a new technique that combines the machine learning algorithm of Adaboost with Convolutional Neural Networks (CNN) to classify Chest X-Ray images. Basic CNN algorithm and pretrained ResNet-152 have been used separately to obtain features of the Adaboost algorithm from Chest X-Ray images. Several learning rates and the number of estimators have been used to compare these two different feature extraction methods on the Adaboost algorithm. These techniques have been applied to the dataset, which contains Chest X-Ray images labeled as Normal, Viral Pneumonia, and Covid-19. Since the used dataset is unbalanced between classes SMOTE method has been used to make the number of images of classes balance. This study shows that proposed CNN as a feature extractor on the Adaboost algorithm(learning rate of 0.1 and 25 estimators) provides higher classification performance with 94.5% accuracy, 93% precision, 94% recall, and 93% F1-score.