PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans

arXiv:2403.18328v1 Announce Type: new
Abstract: Information from neuroimaging examinations (CT, MRI) is increasingly used to support diagnoses of dementia, e.g., Alzheimer's disease. While current clinical practice is mainly based on visual inspection and feature engineering, Deep Learning approaches can be used to automate the analysis and to discover new image-biomarkers. Part-prototype neural networks (PP-NN) are an alternative to standard blackbox models, and have shown promising results in general computer vision. PP-NN's base their reasoning on prototypical image regions that are …

abstract alzheimer's analysis arxiv automate clinical cs.cv current deep learning dementia detection disease engineering feature feature engineering image information mri neuroimaging part practice scans support type visual visual inspection