2023 · 12 citations · 12 references
MedicineNeurologyDiagnostic ImagingDiagnostic RadiologyMachine LearningBrain ImagingComputer-aided DiagnosisDecision TreesMagnetic Resonance ImagingMedical Image AnalysisMedical ImagingAlzheimer's Disease DiagnosisClassification AccuracyClassification Accuracy AnalysisClassification Accuracy AssessmentImage Plane AnalysisMachine Learning In NeuroimagingMagnetic Resonance Image FeaturesTree-based Representation
While most contemporary algorithms typically utilize MRI data from a single plane, this study highlights the importance of incorporating multiplanar MRI features for enhanced performance. Specifically, tree-based machine learning algorithms were employed to compare the accuracy of individual plane analysis versus a multiplanar approach using the popular ADNI dataset. The results unequivocally demonstrate that the multiplanar approach consistently outperforms any single plane analysis in terms of classification accuracy for any given algorithm. These findings provide evidence-based results supporting the integration of multiplanar MRI features to achieve improved performance in MRI-based classification tasks. A significant improvement in accuracy of 8–10% is achieved by the utilization of multiplanar MRI features as against the single plane.
12
The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods
Clifford R. Jack, Matt A. Bernstein, Nick C. Fox et al. · Journal of Magnetic Resonance Imaging · 2008 · 4.4K citations · Full text
Medicine, Neurology, Neuroscience +17
Do Better ImageNet Models Transfer Better?
Simon Kornblith, Jonathon Shlens, Quoc V. Le · 2019 · 1.3K citations
Multimodal deep learning models for early detection of Alzheimer’s disease stage
Janani Venugopalan, Tong Li, Hamid Reza Hassanzadeh et al. · Scientific Reports · 2021 · 699 citations · Full text