Yazar "Tasci, Burak" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    An Accurate Multiple Sclerosis Detection Model Based on Exemplar Multiple Parameters Local Phase Quantization: ExMPLPQ
    (Mdpi, 2022) Macin, Gulay; Tasci, Burak; Tasci, Irem; Faust, Oliver; Barua, Prabal Datta; Dogan, Sengul; Tuncer, Turker
    Multiple sclerosis (MS) is a chronic demyelinating condition characterized by plaques in the white matter of the central nervous system that can be detected using magnetic resonance imaging (MRI). Many deep learning models for automated MS detection based on MRI have been presented in the literature. We developed a computationally lightweight machine learning model for MS diagnosis using a novel handcrafted feature engineering approach. The study dataset comprised axial and sagittal brain MRI images that were prospectively acquired from 72 MS and 59 healthy subjects who attended the Ozal University Medical Faculty in 2021. The dataset was divided into three study subsets: axial images only (n = 1652), sagittal images only (n = 1775), and combined axial and sagittal images (n = 3427) of both MS and healthy classes. All images were resized to 224 x 224. Subsequently, the features were generated with a fixed-size patch-based (exemplar) feature extraction model based on local phase quantization (LPQ) with three-parameter settings. The resulting exemplar multiple parameters LPQ (ExMPLPQ) features were concatenated to form a large final feature vector. The top discriminative features were selected using iterative neighborhood component analysis (INCA). Finally, a k-nearest neighbor (kNN) algorithm, Fine kNN, was deployed to perform binary classification of the brain images into MS vs. healthy classes. The ExMPLPQ-based model attained 98.37%, 97.75%, and 98.22% binary classification accuracy rates for axial, sagittal, and hybrid datasets, respectively, using Fine kNN with 10-fold cross-validation. Furthermore, our model outperformed 19 established pre-trained deep learning models that were trained and tested with the same data. Unlike deep models, the ExMPLPQ-based model is computationally lightweight yet highly accurate. It has the potential to be implemented as an automated diagnostic tool to screen brain MRIs for white matter lesions in suspected MS patients.
  • Küçük Resim Yok
    Öğe
    Deep feature extraction based brain image classification model using preprocessed images: PDRNet
    (Elsevier Sci Ltd, 2022) Tasci, Burak; Tasci, Irem
    Background: Stroke is a neurological condition that occurs when cerebral vessels become blocked and have reduced blood flow. This research proposes a hybrid deep feature-based feature engineering model to achieve high classification performance. Materials and method: In this research, three brain magnetic resonance image datasets were used to test the proposed model. A deep feature engineering model has been proposed to deploy the raw MRI and four pre-processing algorithms: GradCAM, histogram-matching, canny edge detection, and Locally Interpretable Model-Agnostic Explanations(LIME). The deep features have been extracted using Resnet101 and DenseNet201 pre-trained convolutional neural networks (CNN). Thus, this model is titled preprocessing based DenseNet and ResNet (PDRNet). The iterative neighborhood component analysis (INCA) function selects the most suitable features. These features are trained and validated using support vector machine (SVM) classifiers. Iterative Majority Voting (IMV) has been applied to the results obtained from the SVM. The best classification result has been selected by deploying IMV. Results: Our proposed PDRNet achieved a classification accuracy of 97.56% for Dataset 1, 99.32% for Dataset 2, and 99.16% for Dataset 3. The success of the presented model is demonstrated using these calculated accuracies. Conclusions: Our proposed hybrid deep feature model was tested on two datasets with two and four classes. It has also been compared to other state-of-art deep learning-based models, and our model performs better. These results and findings clearly demonstrate the success of the introduced hybrid deep feature engineering method.