arXiv:2511.08663v1 Announce Type: cross 
Abstract: Now that disease-modifying therapies for Alzheimer disease have been approved by regulatory agencies, the early, objective, and accurate clinical diagnosis of AD based on the lowest-cost measurement modalities possible has become an increasingly urgent need. In this study, we propose a novel feature extraction method using persistent homology to analyze structural MRI of the brain. This approach converts topological features into powerful feature vectors through Betti functions. By integrating these feature vectors with a simple machine learning model like XGBoost, we achieve a computationally efficient machine learning model. Our model outperforms state-of-the-art deep learning models in both binary and three-class classification tasks for ADNI 3D MRI disease diagnosis. Using 10-fold cross-validation, our model achieved an average accuracy of 97.43 percent and sensitivity of 99.09 percent for binary classification. For three-class classification, it achieved an average accuracy of 95.47 percent and sensitivity of 94.98 percent. Unlike many deep learning models, our approach does not require data augmentation or extensive preprocessing, making it particularly suitable for smaller datasets. Topological features differ significantly from those commonly extracted using convolutional filters and other deep learning machinery. Because it provides an entirely different type of information from machine learning models, it has the potential to combine topological features with other models later on.

تم تطوير طريقة جديدة لتصنيف مرض الزهايمر باستخدام صور الرنين المغناطيسي ثلاثية الأبعاد، مستفيدة من علم الطوبولوجيا المستمر لاستخراج الميزات. حقق هذا النهج دقة مثيرة للإعجاب بلغت 97.43% في التصنيف الثنائي و95.47% في التصنيف ثلاثي الفئات، متفوقًا على النماذج الحالية للتعلم العميق. تجعل كفاءة الطريقة وملاءمتها لمجموعات البيانات الأصغر منها تقدمًا مهمًا في التشخيص المبكر لمرض الزهايمر.

Se ha desarrollado un nuevo método para clasificar la enfermedad de Alzheimer utilizando imágenes de resonancia magnética 3D, aprovechando la homología persistente para la extracción de características. Este enfoque logró una impresionante precisión del 97.43% en la clasificación binaria y del 95.47% en la clasificación de tres clases, superando a los modelos de aprendizaje profundo existentes. La eficiencia del método y su idoneidad para conjuntos de datos más pequeños lo convierten en un avance significativo en el diagnóstico temprano del Alzheimer.

Une nouvelle méthode de classification de la maladie d'Alzheimer utilisant des images IRM 3D a été développée, s'appuyant sur l'homologie persistante pour l'extraction de caractéristiques. Cette approche a atteint une précision impressionnante de 97,43 % en classification binaire et de 95,47 % en classification à trois classes, surpassant les modèles d'apprentissage profond existants. L'efficacité de la méthode et sa pertinence pour des ensembles de données plus petits en font une avancée significative dans le diagnostic précoce de la maladie d'Alzheimer.

A novel method for classifying Alzheimer's disease using 3D MRI images has been developed, leveraging persistent homology for feature extraction. This approach achieved an impressive accuracy of 97.43% in binary classification and 95.47% in three-class classification, outperforming existing deep learning models. The method's efficiency and suitability for smaller datasets make it a significant advancement in early Alzheimer's diagnosis.

3D-TDA - Topological feature extraction from 3D images for Alzheimer's disease classification

One More Thing in AI – Your Shortcut to AI Mastery

3D-TDA - Topological feature extraction from 3D images for Alzheimer's disease classification

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Deptho.ai

Attentive AI

Thinkability

Brainactive

Ready to build your own newsroom?