Topluluk öğrenme yöntemleri ile beyin MR görüntüleri üzerinden alzheimer tespiti
Küçük Resim Yok
Tarih
2025
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Bursa Teknik Üniversitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Alzheimer hastalığı, dünya genelinde milyonlarca kişiyi etkileyen, yavaş ilerleyen ve bireyin bilişsel, davranışsal ve motor becerilerini ciddi biçimde bozan nörodejeneratif bir hastalıktır. Demansın en yaygın türü olan Alzheimer, sinir hücrelerinin ve sinapsların hasar görmesi veya ölmesi sonucunda gelişir; bu durum hafıza, dil ve karar verme gibi temel bilişsel işlevlerde gerilemeye yol açar. Hastalığın erken evrelerinde görülen unutkanlık ve dikkat bozukluğu gibi belirtiler, genellikle yaşa bağlı değişikliklerle karıştırıldığı için erken teşhis güçleşmektedir. Alzheimer'ın patolojik temellerini, beyinde biriken beta-amiloid plakları ve tau proteinleri oluşturmaktadır. Bu birikimler sinir hücrelerine zarar vererek, beyin dokusunda küçülmelere ve yapısal deformasyonlara neden olmaktadır. Bu yapısal değişimlerin tespitinde Manyetik Rezonans Görüntüleme (MR) önemli rol oynamaktadır. Ancak erken evrelerdeki ince değişimler klasik görüntüleme yorumlarıyla fark edilemeyecek kadar belirsiz olabildiğinden, geleneksel yöntemler çoğu zaman yetersiz kalmaktadır. Ayrıca bu yöntemlerin uzman yorumuna dayalı olması, süreci subjektif ve zaman alıcı hale getirmektedir. Son yıllarda Yapay Zeka (YZ) ve özellikle Derin Öğrenme (Deep Learning) tabanlı yaklaşımlar, tıbbi görüntü analizinde büyük başarılar elde etmiştir. Görsel örüntü tanımada yüksek performans gösteren Evrişimli Sinir Ağları (Convolutional Neural Networks – CNN), Alzheimer evrelerinin sınıflandırılmasında yaygın biçimde kullanılmaktadır. Bununla birlikte, tek bir CNN modelinin sınırlılıklarını aşmak amacıyla farklı mimarilerin güçlü yönlerini birleştiren Topluluk Öğrenmesi (Ensemble Learning) yöntemleri tercih edilmektedir. Bu çalışmada, bu yaklaşımlardan yığınlama (stacking) yöntemi kullanılmıştır. Araştırmada, Kaggle platformunda yer alan ve Alzheimer'ın dört evresini (Alzheimer Olmayan, Çok Hafif, Hafif ve Orta Derecede Alzheimer) içeren açık erişimli MR veri seti kullanılmıştır. Veri seti dengeli şekilde eğitim, doğrulama ve test kümelerine ayrılmıştır. Önceden büyük veri kümelerinde eğitilmiş AlexNet, DenseNet, ResNet, GoogleNet, EfficientNet, MobileNet ve VGG16 modelleri, transfer öğrenme yöntemiyle yeniden eğitilmiş ve performansları doğruluk, F1 skoru, AUC-ROC ve log-loss metrikleriyle karşılaştırılmıştır. Elde edilen model çıktıları, yığınlama yöntemiyle birleştirilerek genel başarımı artıran bir meta model oluşturulmuştur. Modelin karar verme süreçlerini açıklamak amacıyla Grad-CAM (Gradient-weighted Class Activation Mapping) yöntemi uygulanmıştır. Grad-CAM haritaları, modellerin Alzheimer'a özgü beyin bölgelerine özellikle hipokampüs ve temporal lob odaklandığını göstermiştir. Bu bulgu, modelin yalnızca istatistiksel değil, aynı zamanda nörolojik olarak anlamlı kararlar verebildiğini kanıtlamaktadır. xviii Sonuçlar, transfer öğrenme kullanılan CNN modellerinin sıfırdan eğitilen modellere göre daha başarılı olduğunu; topluluk öğrenmesinin ise bireysel CNN mimarilerinden daha yüksek doğruluk sunduğunu ortaya koymuştur. Geliştirilen sistem, Alzheimer teşhisinde yaklaşık %98 doğruluk oranına ulaşarak, tıbbi görüntüleme tabanlı karar destek sistemleri için güvenilir ve açıklanabilir bir araç olduğunu göstermiştir. Bu çalışma hem teknik performans hem de klinik uygulanabilirlik açısından Alzheimer teşhisine yenilikçi bir katkı sağlamaktadır.
Alzheimer's disease is a progressive neurodegenerative disorder that affects millions of people worldwide, gradually impairing an individual's cognitive, behavioral, and motor abilities. As the most common form of dementia, it develops due to the damage or death of neurons and synapses in the central nervous system, leading to a decline in essential cognitive functions such as memory, language, and decision-making. In the early stages, symptoms such as forgetfulness, inattention, and confusion are often mistaken for age-related or psychological conditions, making timely and accurate diagnosis difficult. The disease is characterized by the abnormal accumulation of beta amyloid plaques and tau proteins in the brain, which damage nerve cells and lead to structural shrinkage and tissue degeneration. Magnetic Resonance Imaging (MRI) plays a critical role in detecting these structural changes by monitoring reductions in brain volume, tissue atrophy, and degeneration in specific regions. However, in the early stages of Alzheimer's, such changes are often subtle and ambiguous, making classical image-based assessment methods insufficient. Moreover, traditional diagnostic procedures are time-consuming, costly, and subjective, as they depend heavily on expert interpretation. In recent years, Artificial Intelligence (AI), particularly Deep Learning-based approaches, has demonstrated remarkable success in medical imaging analysis. Convolutional Neural Networks (CNNs), known for their high capability in learning spatial patterns from images, have been effectively utilized in classifying Alzheimer's stages. To overcome the limitations of individual models and enhance overall performance, Ensemble Learning techniques that combine the strengths of multiple CNN architectures have gained increasing attention. In this study, the stacking ensemble method was employed to integrate outputs from several CNN models through a meta-learner to improve generalization and diagnostic accuracy. The experiments utilized an open-access MRI dataset from Kaggle, representing four stages of Alzheimer's disease (Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented). The dataset was balanced across training, validation, and test sets. Pre-trained CNN architectures AlexNet, DenseNet, ResNet, GoogleNet, EfficientNet, MobileNet, and VGG16 were fine-tuned through transfer learning. Each model's performance was evaluated using accuracy, F1-score, AUC-ROC, and log loss metrics. Their outputs were subsequently combined into a meta model using stacking to enhance classification performance. To further increase the interpretability and transparency of the decision-making process, the Grad-CAM (Gradient-weighted Class Activation Mapping) technique was applied. Grad-CAM visualizations revealed that the models primarily focused on Alzheimer-related brain regions such as the hippocampus and temporal lobes, xx demonstrating that the system produces decisions that are not only statistically sound but also neurologically meaningful. The results indicated that CNN models employing transfer learning outperformed models trained from scratch, while the ensemble approach achieved higher accuracy compared to individual CNN architectures. The proposed system achieved approximately 98% classification accuracy, confirming its potential as a reliable and explainable decision support tool for medical image analysis. In conclusion, the study offers an innovative contribution to the early diagnosis of Alzheimer's disease, combining technical robustness with clinical applicability.
Alzheimer's disease is a progressive neurodegenerative disorder that affects millions of people worldwide, gradually impairing an individual's cognitive, behavioral, and motor abilities. As the most common form of dementia, it develops due to the damage or death of neurons and synapses in the central nervous system, leading to a decline in essential cognitive functions such as memory, language, and decision-making. In the early stages, symptoms such as forgetfulness, inattention, and confusion are often mistaken for age-related or psychological conditions, making timely and accurate diagnosis difficult. The disease is characterized by the abnormal accumulation of beta amyloid plaques and tau proteins in the brain, which damage nerve cells and lead to structural shrinkage and tissue degeneration. Magnetic Resonance Imaging (MRI) plays a critical role in detecting these structural changes by monitoring reductions in brain volume, tissue atrophy, and degeneration in specific regions. However, in the early stages of Alzheimer's, such changes are often subtle and ambiguous, making classical image-based assessment methods insufficient. Moreover, traditional diagnostic procedures are time-consuming, costly, and subjective, as they depend heavily on expert interpretation. In recent years, Artificial Intelligence (AI), particularly Deep Learning-based approaches, has demonstrated remarkable success in medical imaging analysis. Convolutional Neural Networks (CNNs), known for their high capability in learning spatial patterns from images, have been effectively utilized in classifying Alzheimer's stages. To overcome the limitations of individual models and enhance overall performance, Ensemble Learning techniques that combine the strengths of multiple CNN architectures have gained increasing attention. In this study, the stacking ensemble method was employed to integrate outputs from several CNN models through a meta-learner to improve generalization and diagnostic accuracy. The experiments utilized an open-access MRI dataset from Kaggle, representing four stages of Alzheimer's disease (Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented). The dataset was balanced across training, validation, and test sets. Pre-trained CNN architectures AlexNet, DenseNet, ResNet, GoogleNet, EfficientNet, MobileNet, and VGG16 were fine-tuned through transfer learning. Each model's performance was evaluated using accuracy, F1-score, AUC-ROC, and log loss metrics. Their outputs were subsequently combined into a meta model using stacking to enhance classification performance. To further increase the interpretability and transparency of the decision-making process, the Grad-CAM (Gradient-weighted Class Activation Mapping) technique was applied. Grad-CAM visualizations revealed that the models primarily focused on Alzheimer-related brain regions such as the hippocampus and temporal lobes, xx demonstrating that the system produces decisions that are not only statistically sound but also neurologically meaningful. The results indicated that CNN models employing transfer learning outperformed models trained from scratch, while the ensemble approach achieved higher accuracy compared to individual CNN architectures. The proposed system achieved approximately 98% classification accuracy, confirming its potential as a reliable and explainable decision support tool for medical image analysis. In conclusion, the study offers an innovative contribution to the early diagnosis of Alzheimer's disease, combining technical robustness with clinical applicability.
Açıklama
Anahtar Kelimeler
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Computer Engineering and Computer Science and Control ; Bilim ve Teknoloji
