Browsing by Author "Darici,M.B."

Now showing 1 - 3 of 3

Citation Count: 0
Comprehensive Analysis of Image Registration Techniques on Brain MR Images
(Institute of Electrical and Electronics Engineers Inc., 2023) Darici,M.B.; Ozmen,A.
Medical image registration is an important preprocess of image-guided systems. Since image registration brings the images to the same coordinate system of the specified reference image, image registration should not be neglected to be able to make accurate comparisons between results obtained from medical images. Basically, registration is an optimization problem. The parameters of the specified transformation algorithm are optimized based on specified functions and parameters of registration. In this study, T1-weighted structural 3D brain MR images on IXI dataset have been registered into reference image by the affine transformation in the proposed registration method. During experiments, the effects of several parameters and functions on registration performance have been investigated with different preprocessing techniques applied to brain MR images. After several experiments, the most successful outcome of various experiments was achieved by using Powell optimization function along with Linear Interpolation, when applying Median Filter with CLAHE to images in the suggested registration method. The NCC was used to compare the registration results. The study's results demonstrate that the proposed registration method outperformed the widely-used registration tool SPM8 with mean NCC of -0.753. © 2023 IEEE.
Citation Count: 1
Improving Diabetic Retinopathy Detection Using Patchwise Cnn With Bigru Model
(Institute of Electrical and Electronics Engineers Inc., 2023) Darici,M.B.; Yigit,G.
This study addresses Diabetic Retinopathy (DR), a diabetes complication that can lead to vision loss if not promptly diagnosed and treated. Recent advances in deep learning have shown promising results in detecting DR from retinal images. The study introduces a novel patch-based CNN-biGRU model for DR detection. The proposed model extracts patches from retinal images employing a sliding window strategy and then uses a Convolutional Neural Network (CNN) architecture to extract features from each patch. The features extracted from each patch are then concatenated, and a 4-layer bidirectional Gated Recurrent Unit (biGRU) is applied to predict the whole image. We assessed the proposed model on a publicly available dataset named APTOS 2019 Blindness Detection and achieved an accuracy of 73.5%, outperforming existing state-of-the-art approaches. The given patch-based CNN model can improve the accuracy of DR detection and aims to assist ophthalmologists in making more accurate diagnoses. © 2023 IEEE.
Citation Count: 0
A Siamese Network-Based Approach for Autism Spectrum Disorder Detection With Dual Architecture
(Institute of Electrical and Electronics Engineers Inc., 2023) Yigit,G.; Darici,M.B.
Autism Spectrum Disorder (ASD) is a sophisticated neuro-developmental condition impacting numerous children. Early detection of ASD is crucial to implement suitable treatments to improve the daily activities of people with ASD. This paper introduces a system for ASD detection using facial images. The proposed model presents a unique system inspired by Siamese networks. Unlike traditional Siamese networks focusing on input pairs, our model leverages architectural pairs for feature combinations. During training, we combine features learned from different or the same architectures. This enables information transfer and improves the model's capture of comprehensive patterns. Experimental results on the 2940 facial images dataset demonstrate the effectiveness of our system, which exhibits improved accuracy compared to using individual architectures. When (ResNet50, VGG16) architecture pairs are employed in the proposed approach, the highest performance is obtained with an accuracy of 78.57%. Leveraging the strengths of multiple architectures, our model provides a comprehensive and robust representation of input data, leading to improved performance. © 2023 IEEE.