AI and Neurological Rare & Neuroimmune Diseases ── Hereditary neurodegeneration ── 2026-10-21

1 Hereditary neurodegeneration papers. Lead: MACHINE LEARNING AND CONVOLUTIONAL TRANSFORMER NEURAL NETWORK FRAMEWORK FOR AUTOMATED HUNTINGTON'S BRAIN DISEASE DETECTION FROM MRI

Journals covered and how papers are chosen: see the index

Hereditary neurodegenerative diseases: treatment, trials and AI

MACHINE LEARNING AND CONVOLUTIONAL TRANSFORMER NEURAL NETWORK FRAMEWORK FOR AUTOMATED HUNTINGTON'S BRAIN DISEASE DETECTION FROM MRI
Acta Innovations · 2026-10-18 · Evidence: Preclinical (methodological development, pending clinical validation)
Abstract
Huntington's disease (HD) is a progressive neurodegenerative disorder characterized by motor dysfunction, cognitive decline, and psychiatric abnormalities. Magnetic resonance imaging (MRI) provides valuable structural information for identifying disease-associated brain changes, particularly in the striatum and associated subcortical regions. However, conventional image-analysis methods may inadequately capture complex spatial relationships and subtle anatomical variations. This paper presents a machine learning and convolutional transformer neural network framework for automated Huntington's disease detection from brain MRI. The proposed architecture integrates convolutional feature extraction, transformer-based global context modeling, and machine learning classification to identify discriminative neuroanatomical patterns. Image preprocessing, intensity normalization, anatomical region analysis, and class-imbalance management are incorporated into the processing pipeline. Model performance is assessed using accuracy, sensitivity, specificity, F1-score, receiver operating characteristic area under the curve, and explainability measures. The framework also incorporates model interpretation and patient-level validation to support transparent assessment. The proposed approach establishes a methodological foundation for automated MRI-based Huntington's disease screening, subject to independent clinical validation and rigorous evaluation across heterogeneous imaging datasets.
Journal IF-equivalent: 0.1 (OpenAlex 2-year mean citedness, value as of 2026-10-20, retrieved 2026-10-21; not the official Clarivate IF)
Reference: [No authors listed]. MACHINE LEARNING AND CONVOLUTIONAL TRANSFORMER NEURAL NETWORK FRAMEWORK FOR AUTOMATED HUNTINGTON'S BRAIN DISEASE DETECTION FROM MRI. ACTA. 2026 Oct 18;63(2s). doi:10.62441/actainnovations.vi.1902.
Checked: Abstract only

← Back to this issue