Fakülteler / Faculties
Permanent URI for this communityhttps://hdl.handle.net/11727/1395
Browse
6 results
Search Results
Item Categorization Of Alzheimer's Disease Stages Using Deep Learning Approaches With Mcnemar's Test(Başkent Üniversitesi Mühendislik Fakültesi, 2024-03-13) Sener, Begum; Acici, Koray; Sumer, EmreEarly diagnosis is crucial in Alzheimer's disease both clinically and for preventing the rapid progression of the disease. Early diagnosis with awareness studies of the disease is of great importance in terms of controlling the disease at an early stage. Additionally, early detection can reduce treatment costs associated with the disease. A study has been carried out on this subject to have the great importance of detecting Alzheimer's disease at a mild stage and being able to grade the disease correctly. This study's dataset consisting of MRI images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) was split into training and testing sets, and deep learning -based approaches were used to obtain results. The dataset consists of three classes: Alzheimer's disease (AD), Cognitive Normal (CN), and Mild Cognitive Impairment (MCI). The achieved results showed an accuracy of 98.94% for CN vs AD in the one vs one (1 vs 1) classification with the EfficientNetB0 model and 99.58% for AD vs CNMCI in the one vs All (1 vs All) classification with AlexNet model. In addition, in the study, an accuracy of 98.42% was obtained with the EfficientNet121 model in MCI vs CN classification. These results indicate the significant potential for mild stage Alzheimer's disease detection of Alzheimer's disease. Early detection of the disease in the mild stage is a critical factor in preventing the progression of Alzheimer's disease. In addition, a variant of the non -parametric statistical McNemar's Test was applied to determine the statistical significance of the results obtained in the study. Statistical significance of 1 vs 1 and 1 vs all classifications were obtained for EfficientNetB0, DenseNet, and AlexNet models.Item Cerliponase Alfa Decreases Aβ Load And Alters Autophagy- Related Pathways In Mouse Hippocampal Neurons Exposed To Faβ1-42(LIFE SCIENCES, 2024-11-15) Kose, Selma; Cinar, Elif; Akyel, Hilal; Cakir-Aktas, Canan; Tel, Banu Cahide; Karatas, Hulya; Kelicen-Ugur, PelinExtracellular aggregation of amyloid-beta (A beta) in the brain plays a central role in the onset and progression of Alzheimer's disease (AD). Moreover, intraneuronal accumulation of A beta via oligomer internalization might play an important role in the progression of AD. Deficient autophagy, which is a lysosomal degradation process, occurs during the early stages of AD. Tripeptidyl peptidase-1 (TPP1) functions as a lysosomal enzyme, and TPP1 gene mutations are associated with type 2 late infantile neuronal ceroid lipofuscinosis (LINCL). Nevertheless, there is little information about the role of TPP1 in the pathogenesis of AD; therefore, the present study aimed to measure the decrease in intraneuronal A beta accumulation by a recombinant analog of the TPP1 enzyme, cerliponase alfa (CER) (Brineura (R)), and to determine whether autophagy pathways play a role in this decrease. In this study, endogenous A beta accumulation was induced by fA beta(1-42) (a toxic fragment of full-length A beta) exposure, and mouse hippocampal neuronal cells (HT-22) were treated with CER (human recombinant rhTPP1 1 mg mL-1). Soluble A beta, TPP1, and the proteins involved in autophagy, including mammalian target of rapamycin (p-mTOR/ mTOR), p62/sequestosome-1 (p62/SQSTM1), and microtubule-associated protein 1 A/1B-light chain 3 (LC3), were evaluated using western blotting. The sirtuin-1, beclin-1, and Atg5 genes were also studied using RT-PCR. A beta and TPP1 localizations were observed via immunocytochemistry. CER reduced the A beta load in HT-22 cells by inducing TPP1 expression and converting pro-TPP1 into the mature form. Furthermore, exposure to CER and fA beta(1-42) induced the autophagy-regulatory/related pathways in HT-22 cells and exposure to CER alone increased sirtuin-1 activity. Based on the present findings, we suggest that augmentation of TPP1 with enzyme replacement therapy may be a potential therapeutic option for the treatment of AD.Item The Relationship Between the Degree of Cognitive Impairment and Retinal Nerve Fiber Layer Thickness(2015) Oktem, Ece Ozdemir; Derle, Eda; Kibaroglu, Seda; Oktem, Caglar; Akkoyun, Imren; Can, Ufuk; 0000-0002-2860-7424; 0000-0003-2122-1016; 0000-0001-8689-417X; 0000-0002-3964-268X; 25575807; AAK-7713-2021; AAI-8830-2021; AAJ-2999-2021; AAJ-2956-2021The goal of the present study is to investigate the relationship between the degree of cognitive impairment and retinal nerve fiber layer (RNFL) thickness which is measured by the optical coherence tomography (OCT). Thirty-five patients with Alzheimer's disease (AD), 35 patients with mild cognitive impairment (MCI), and 35 healthy volunteers, between the ages of 60-87, who were examined in the neurology outpatient clinic among 2012-2013 were prospectively involved in our study. Mini mental state examination (MMSE) test, montreal cognitive assessment (MOCA), and also neuropsychological test batteries were used for the neurocognitive evaluation. RNFL thickness was measured by the OCT technique and the differences among groups were studied. The relationship between RNFL thickness and MMSE scores with demographic characteristics was investigated. RNFL thickness was significantly lower in AD and MCI groups compared with the control group (p < 0.01). No significant differences of RNFL were found between the MCI and the AD groups (p > 0.05). Significant correlation was found between MMSE scores and the RNFL values (p < 0.05). Significant thinning in RNFL along with age was detected (p < 0.05). In our study, it is thought that retinal nerve fiber degeneration and central nervous system degeneration may be concurrent according to the thinning of RNFL measured by OCT in AD and MCI groups. RNFL measurement may also be useful for early diagnosis and evaluation of the disease progression. Further studies are needed to optimize the utility of this method as an ocular biomarker in AD.Item PET Imaging in Neurology: Alzheimer's and Parkinson's Diseases(2015) Sarikaya, Ismet; 0000-0002-1087-580X; 25920047; G-7881-2015PET studies play an important role in the early detection of Alzheimer's and Parkinson's diseases (AD and PD). Fluorine-18 fluorodeoxyglucose (F-18-FDG) PET imaging of regional cerebral glucose metabolism and PET amyloid imaging are the two major PET studies for AD. F-18-FDG PET is highly sensitive for the early diagnosis of AD, in predicting conversion from mild cognitive impairment to AD, and in differentiating AD from other dementias. PET amyloid imaging is positive in the majority of patients with AD. Negative amyloid PET reduces the likelihood of AD. The main limitations of PET amyloid imaging is its high positivity in the normal elderly population and in other medical conditions with amyloid pathologies. Various PET tracers are available to assess motor and cognitive dysfunctions in PD. PET tracers targeting presynaptic dopaminergic function (F-18-DOPA, radiolabeled PET tracers assessing the availability of dopamine transporters and vesicular monoamine transporters) and postsynaptic dopamine receptors are used to assess motor dysfunction in PD. PET tracers, particularly dopamine transporters, are highly sensitive in the early diagnosis of PD. Uptake of PET tracers in the striatum is inversely correlated with disease severity. PET is valuable in differentiating PD from other movement disorders. PET studies, particularly F-18-FDG PET, help to evaluate cortical metabolism in PD patients with cognitive dysfunction and dementia.Item A novel electroencephalography based approach for Alzheimer's disease and mild cognitive impairment detection(2021) Oltu, Burcu; Aksahin, Mehmet Feyzi; Kibaroglu, Seda; 0000-0002-3964-268X; AAJ-2956-2021Background and objective: Alzheimer's disease (AD) is characterized by cognitive, behavioral and intellectual deficits. The term mild cognitive impairment (MCI) is used to describe individuals whose cognitive impairment departing from their expectations for the age that does not interfere with daily activities. To diagnose these disorders, a combination of time-consuming, expensive tests that has difficulties for the target population are evaluated, moreover, the evaluation may yield subjective results. In the presented study, a novel methodology is developed for the automatic detection of AD and MCI using EEG signals. Methods: This study analyzed the EEGs of 35 subjects (16 MCI, 8 AD, 11 healthy control) with the developed algorithm. The algorithm consists of 3 methods for analysis, discrete wavelet transform(DWT), power spectral density (PSD) and coherence. In the first approach, DWT is applied to the signals to obtain major EEG sub-bands, afterward, PSD of each sub-band is calculated using Burg's method. In the second approach, interhemispheric coherence values are calculated. The variance and amplitude summation of each sub-bands' PSD and the amplitude summation of the coherence values corresponding to the major sub-bands are determined as features. Bagged Trees is selected as a classifier among the other tested classification algorithms. Data set is used to train the classifier with 5-fold cross-validation. Results: As a result, accuracy, sensitivity, and specificity of 96.5%, 96.21%, 97.96% are achieved respectively. Conclusion: In this study, we have investigated whether EEG can provide efficient clues about the neuropathology of Alzheimer's Disease and mild cognitive impairment for early and accurate diagnosis. Accordingly, a decision support system that produces reproducible and objective results with high accuracy is developed.Item Examination of IL-1 beta level as an inflammasome marker in Alzheimer's disease(2019) Bulut, Onur; Tanburoglu, Anil; Boluk, Gulsah; Demir, Nurhak; Eren, Erden; Vurgun, Ufuk; Genc, Sermin; Yener, GorsevObjective: Interleukin (IL)-1 beta is believed to be responsible for the neurotoxicity of amyloid plaques in Alzheimer's disease (AD). In the present study, serum levels of IL-1 beta, and correlations with clinical features and neuropsychiatric test results were examined. Methods: Thirty-eight patients with AD and 38 healthy control patients were included in the study. Serum IL-1 beta levels in patients with AD and control were analyzed using enzyme-linked immunosorbent assay method. The Mini-Mental Test Score (MMSE) and Geriatric Depression Scale (GDS) were administered to both the patient and control groups. Furthermore, the clinical dementia rating, detailed neuropsychological test battery, and neuropsychiatric inventory were administered to the AD group. It was determined that the serum IL-1 beta measurements of the patient and control groups were not statistically different, and IL-1 beta measurements in the patient group were not correlated with the MMSE and GDS. Results: The relationship of IL-1 beta measurements in the patient group with other clinical data was not significant. Among the patients' neuropsychological tests, a moderately, significant negative correlation was found only between the clock drawing test and visual learning score and serum IL-1 beta levels. Conclusion: Our study is in agreement with other studies in which no significant difference was found between patients with AD and healthy controls in terms of serum IL-1 beta levels, but the moderately negative correlation obtained with the clock drawing test and visual learning score indicates a weak relation. This result may indicate that stronger relations will be determined in large-scale studies involving larger numbers of patients.