Pneumonia is a bacterial infection caused people of all ages with mild to severe inflammation of the lung tissue. The best known and most common clinical method for the diagnosis of pneumonia is chest X-ray imaging. But the diagnosis of pneumonia from chest Xray images is a difficult task, even for specialist radiologists. In developing countries, this lung disease becomes one of the deadliest among children under the age of 5 and causing 15% of deaths recorded annually. Therefore, in this study, firstly the presence of the disease was tried to be determined using chest X-ray dataset. In addition, using the bacterial and viral pneumonia classes which are two different types of pneumonia, multi class classification which consists of viral pneumonia, bacterial pneumonia and healthy has been done. Since the used dataset does not have a balanced distribution among all classes, SMOTE (Synthetic Minority Over-sampling Technique) method has been used to deal with imbalanced dataset. CNN model and models in Ensemble Learning have been created from scratch instead of using weights of pre-trained networks to see the effectiveness of CNN weights on medical data. For each classification problem, two different deep learning methods which are CNN and ensemble learning have been used and 95% average accuracy has been obtained for each model, for binary classification and 78% and 75% average accuracy has been obtained for each model respectively for multi class classification problem.

No abstract

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.

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.

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