Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans

Lisa Anita De Santi, Jörg Schlötterer, Michael Scheschenja, Joel Wessendorf, Meike Nauta, Vincenzo Positano, Christin Seifert

TL;DR

The paper tackles the challenge of diagnosing Alzheimer's disease from structural MRI with interpretable AI. It introduces PIPNet3D, a 3D part-prototype network that learns a small set of semantically meaningful prototypes and uses a sparse decision layer to classify scans into AD or CN, providing VOI-based explanations. To ensure clinical relevance, the authors propose new functionally grounded metrics (Prototype Brain Entropy and Prototype Localization Consistency) and conduct domain-expert evaluations with radiologists, demonstrating that the prototypes align with medical knowledge and can be pruned for compactness without sacrificing accuracy. Empirically, PIPNet3D achieves performance on par with black-box baselines while offering interpretable reasoning, supporting its potential for trusted AI-assisted neuroimaging in high-stakes settings.

Abstract

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.

PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans

TL;DR

The paper tackles the challenge of diagnosing Alzheimer's disease from structural MRI with interpretable AI. It introduces PIPNet3D, a 3D part-prototype network that learns a small set of semantically meaningful prototypes and uses a sparse decision layer to classify scans into AD or CN, providing VOI-based explanations. To ensure clinical relevance, the authors propose new functionally grounded metrics (Prototype Brain Entropy and Prototype Localization Consistency) and conduct domain-expert evaluations with radiologists, demonstrating that the prototypes align with medical knowledge and can be pruned for compactness without sacrificing accuracy. Empirically, PIPNet3D achieves performance on par with black-box baselines while offering interpretable reasoning, supporting its potential for trusted AI-assisted neuroimaging in high-stakes settings.

Abstract

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.
Paper Structure (10 sections, 2 equations, 2 figures, 2 tables)

This paper contains 10 sections, 2 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. PIPNet3D
  4. Neuroimaging Prototypes Explanation Quality
  5. Functionally Grounded Evaluation.
  6. Evaluation with Experts
  7. Evaluation
  8. Predictive Performance
  9. Interpretability
  10. Conclusion

Figures (2)

  • Figure 1: Overview of PiPNet3D. 3D prototypes are learned through a CNN backbone. Representations are optimized through a contrastive pre-training step. A linear sparse decision layer computes the predictions based on prototype (VOI) activations.
  • Figure 2: Example of local and global explanation (LE and GE). The GE shows all the learned prototypes. The LE shows the model's reasoning for one particular patient.