PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: De Santi, Lisa Anita, Schlötterer, Jörg, Scheschenja, Michael, Wessendorf, Joel, Nauta, Meike, Positano, Vincenzo, Seifert, Christin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911964111831040
author De Santi, Lisa Anita
Schlötterer, Jörg
Scheschenja, Michael
Wessendorf, Joel
Nauta, Meike
Positano, Vincenzo
Seifert, Christin
author_facet De Santi, Lisa Anita
Schlötterer, Jörg
Scheschenja, Michael
Wessendorf, Joel
Nauta, Meike
Positano, Vincenzo
Seifert, Christin
contents Information from neuroimaging examinations 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 learned fully unsupervised, and combined with a simple-to-understand decision layer. We present PIPNet3D, a PP-NN for volumetric images. We apply PIPNet3D to the clinical diagnosis of Alzheimer's Disease from structural Magnetic Resonance Imaging (sMRI). We assess the quality of prototypes under a systematic evaluation framework, propose new functionally grounded metrics to evaluate brain prototypes and develop an evaluation scheme to assess their coherency with domain experts. Our results show that PIPNet3D is an interpretable, compact model for Alzheimer's diagnosis with its reasoning well aligned to medical domain knowledge. Notably, PIPNet3D achieves the same accuracy as its blackbox counterpart; and removing the remaining clinically irrelevant prototypes from its decision process does not decrease predictive performance.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18328
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans
De Santi, Lisa Anita
Schlötterer, Jörg
Scheschenja, Michael
Wessendorf, Joel
Nauta, Meike
Positano, Vincenzo
Seifert, Christin
Computer Vision and Pattern Recognition
Information from neuroimaging examinations 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 learned fully unsupervised, and combined with a simple-to-understand decision layer. We present PIPNet3D, a PP-NN for volumetric images. We apply PIPNet3D to the clinical diagnosis of Alzheimer's Disease from structural Magnetic Resonance Imaging (sMRI). We assess the quality of prototypes under a systematic evaluation framework, propose new functionally grounded metrics to evaluate brain prototypes and develop an evaluation scheme to assess their coherency with domain experts. Our results show that PIPNet3D is an interpretable, compact model for Alzheimer's diagnosis with its reasoning well aligned to medical domain knowledge. Notably, PIPNet3D achieves the same accuracy as its blackbox counterpart; and removing the remaining clinically irrelevant prototypes from its decision process does not decrease predictive performance.
title PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.18328