Yazar "Tasci, Irem" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • 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
    A case of syncopal convulsions triggered by glossopharyngeal neuralgia
    (Kare Publ, 2021) Tasci, Irem; Beydilli, Ibrahim; Demir, Caner Feyzi; Balgetir, Ferhat; Gonen, Murat; Bakir, Meryem
    Syncopal convulsions and epileptic seizures are clinically hard to distinguish and differ in terms of treatment approaches. It is important to consider the cardiac arrhythmias that impair cerebral perfusion in the differential diagnosis of antiepileptic treatment-resistant convulsions. Here, we offer a 72-year-old male patient glossopharyngeal neuralgia (GN) after swallowing associated with recurrent episodes of syncopal convulsions. The patient was successfully treated with temporary pacemaker and carbamazepine. This phenomenon is noteworthy in terms of both asystole triggered by GN and syncopal convulsions which are rare in the differential diagnosis of epileptic seizures.
  • 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.
  • Küçük Resim Yok
    Öğe
    Is deep brain stimulation useful in Lance-Adams syndrome?
    (Asean Neurological Assoc, 2021) ozturk, Gulsah; Tasci, Irem; Samanci, Mustafa Yavuz; Peker, Selcuk
    Lance-Adams syndrome (LAS) is a chronic post-hypoxic myoclonus that occurs after successful cardiopulmonary resuscitation. Although many drugs are available to treat this condition, the underlying mechanism of the disease is yet to be understood. Deep brain stimulation (DBS) has been attempted and proven to be partially successful in treating LAS in several cases. Here, we present a 40-year-old woman who developed myoclonus subsequent to cardiopulmonary arrest (CPA) that occurred after her first cesarean delivery at the age of 26 years. The patient underwent implantation of bilateral globus pallidus interna (GPi)-DBS about 14 years after disease onset. Regarding Unified Myoclonus Rating Scale (UMRS), 8% and 20% improvements were observed in action and resting myoclonus, respectively, with high-frequency stimulation as a result of the 3-year follow-up study. In this case, neuromodulation therapy applied 14 years after hypoxia-causing LAS was not sufficiently beneficial.
  • Küçük Resim Yok
    Öğe
    TRP Channels in Tension-Type Headache: A Pilot Study
    (Turkish Neurological Soc, 2021) Gemici, Yagmur Inalkac; Tasci, Irem; Durmu, Kubra; Koc, Ahmet
    Tension-type headache (TTH) affects many individuals worldwide. Although the exact pathogenesis of TTH remains unclear, central, and peripheral mechanisms are considered to play a role in TTH 1. This pilot study aimed to investigate the role of transient receptor potential (TRP) channels in the development or chronic inflammation in TTH and to discuss the findings in the light of literature. This pilot study included a patient group comprising three patients with episodic TTH and three patients with chronic TTH (CTTH) aged 18-40 years with no comorbidities and a control group of three patients with no headache. Peripheral blood samples were obtained from all the participants, and both RNA and cDNA were isolated on the same day. The mRNA levels of pain-related TRP channels [TRPA1, TRP vanilloid-1 (TRPV1), TRPV3, TRPV4, TRPM3, and TRPM8] were measured by reverse transcriptase (RT)-quantititave polymerase chain reaction method and were normalized with the levels of glyceraldehyde 3-phosphate dehydrogenase (GAPDH) transcript. Results were analyzed using statistical methods. All three groups were comparable with regard to demographic characteristics. No significant difference was found among the groups with regard to the mRNA levels of the TRP channels normalized by GAPDH, whereas the TRPM8 expression levels were not significantly lower in the CTTH group than in other groups (p = 0.066). This study revealed that TRPM8 is likely to have a role in the pathogenesis of TTH, and this role of TRPM8 may be investigated by further studies.