Using interpretable deep learning radiomics model to diagnose and predict progression of early AD disease spectrum: a preliminary [¹⁸F]FDG PET study

In this study, we propose an interpretable deep learning radiomics (IDLR) model based on [¹⁸F]FDG PET images to diagnose the clinical spectrum of Alzheimer’s disease (AD) and predict the progression from mild cognitive impairment (MCI) to AD.

This multicentre study included 1962 subjects from two ethnically diverse, independent cohorts (a Caucasian cohort from ADNI and an Asian cohort merged from two hospitals in China). The IDLR model involved feature extraction, feature selection, and classification/prediction. We evaluated the IDLR model’s ability to distinguish between subjects with different cognitive statuses and MCI trajectories (sMCI and pMCI) and compared results with radiomic and deep learning (DL) models. A Cox model tested the IDLR signature’s predictive capability for MCI to AD progression. Correlation analyses identified critical IDLR features and verified their clinical diagnostic value.

The IDLR model achieved the best classification results for subjects with different cognitive statuses as well as in those with MCI with distinct trajectories, with an accuracy of 76.51% [72.88%, 79.60%], (95% confidence interval, CI) while those of radiomic and DL models were 69.13% [66.28%, 73.12%] and 73.89% [68.99%, 77.89%], respectively. According to the Cox model, the hazard ratio (HR) of the IDLR model was 1.465 (95% CI: 1.236–1.737, p < 0.001). Moreover, three crucial IDLR features were significantly different across cognitive stages and were significantly correlated with cognitive scale scores (p < 0.01).

Preliminary results demonstrated that the IDLR model based on [¹⁸F]FDG PET images enhanced accuracy in diagnosing the clinical spectrum of AD.

Question The study addresses the lack of interpretability in existing DL classification models for diagnosing the AD spectrum.

Findings The proposed interpretable DL radiomics model, using radiomics-supervised DL features, enhances interpretability from traditional DL models and improves classification accuracy.

Clinical relevance The IDLR model interprets DL features through radiomics supervision, potentially advancing the application of DL in clinical classification tasks.