GL-ICNN: An End-To-End Interpretable Convolutional Neural Network for the Diagnosis and Prediction of Alzheimer's Disease

IEEE International Symposium on Biomedical Imaging (ISBI), pp. 1–5

Abstract

Deep learning methods based on Convolutional Neural Networks (CNNs) have shown large potential to improve early and accurate diagnosis of Alzheimer's disease (AD) dementia based on imaging data. However, these methods have yet to be widely adopted in clinical practice, possibly due to the limited interpretability of deep learning models. The Explainable Boosting Machine (EBM) is a glass-box model but cannot learn features directly from input imaging data. In this study, we propose a novel interpretable model that combines CNNs and EBMs for the diagnosis and prediction of AD. We develop an innovative training strategy that alternatingly trains the CNN component as a feature extractor and the EBM component as the output block to form an end-to-end model. The model takes imaging data as input and provides both predictions and interpretable feature importance measures. We validated the proposed model on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and the Health-RI Parelsnoer Neurode- generative Diseases Biobank (PND) as an external testing set. The proposed model achieved an area-under-the-curve (AUC) of 0.956 for AD and control classification, and 0.694 for the prediction of conversion of mild cognitive impairment (MCI) to AD on the ADNI cohort. The proposed model is a glass- box model that achieves a comparable performance with other state-of-the-art black-box models. Our code is available at: https://anonymous.4open.science/r/GL-ICNN.

Authors 11

1. Wenjie Kang

   Erasmus MC

   Affiliation as printed

   Erasmus MC,Biomedical Imaging Group Rotterdam,NL

2. Lize Corrine Jiskoot

   Erasmus MC

   Affiliation as printed

   Erasmus MC,NL

3. Peter Paul De Deyn

   University Medical Center Groningen

   Affiliation as printed

   University Medical Center Groningen,NL

4. Geert Jan Biessels

   University Medical Center Utrecht

   Affiliation as printed

   University Medical Center Utrecht,NL

5. Huiberdina L. Koek

   University Medical Center Utrecht

   Affiliation as printed

   University Medical Center Utrecht,NL

6. Jurgen A.H.R. Claassen

   Radboud University Medical Center

   Affiliation as printed

   Radboud University Medical Center,NL

7. Huub A. M. Middelkoop Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center,NL

8. Wiesje M. van der Flier

   Amsterdam University Medical Centers

   Affiliation as printed

   Amsterdam University Medical Center,NL

9. Willemijn J. Jansen

   Maastricht University Medical Centre · Maastricht University

   Affiliation as printed

   Maastricht University Medical Center,NL

10. Stefan Klein

    Erasmus MC

    Affiliation as printed

    Erasmus MC,Biomedical Imaging Group Rotterdam,NL

11. Esther E. Bron

    Erasmus MC

    Affiliation as printed

    Erasmus MC,Biomedical Imaging Group Rotterdam,NL