# A Surface-based Multimodal Framework for Multitask Analysis in Alzheimer's Disease Source: [A Surface-based Multimodal Framework for Multitask Analysis in Alzheimer's Disease]() Collection index: [llms.txt]() Data updated: 2026-06-17T05:00:14.085Z Authors: Shuo Huang, Jianwei Zhang, Lujia Zhong, Jiaxin Yue, Yihao Xia, Xinkai Wang, Yonggang Shi Published: 2026-06-14T09:15:39.000Z ## Abstract Alzheimer's Disease (AD) is a progressive neurodegenerative disorder, and longitudinal analysis is critical for early detection and effective intervention. Developing models capable of multimodal and multitask analysis enables a more comprehensive understanding of AD progression. However, multimodal learning remains challenged by cross-modal misalignment, non-Euclidean surface representations of cortical data, and limited data availability in small-sample clinical settings. In this work, we propose an augmented spherical data-driven multimodal framework for multitask AD analysis. A spherical diffusion model is first trained to generate paired cortical thickness and Tau PET Standardized Uptake Value Ratio (SUVR) data, enabling structurally consistent multimodal augmentation on cortical surfaces while preserving anatomical correspondence. The augmented data are subsequently used to train a contrastive learning model that learns aligned and fused cross-modal representations. This design strengthens multimodal integration and encourages more balanced representation learning. The learned imaging features are further integrated with tabular cognitive assessments and demographic variables, and processed using an in-context learning model to perform both classification and regression tasks without task-specific fine-tuning. Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset ($n = 802$) demonstrate consistent performance improvements across five diagnostic and longitudinal tasks, outperforming six baseline models. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Three-class Classification (CN/MCI/AD) on ADNI 129-subject (test)](): Three-class classification (CN/MCI/AD); ADNI 129-subject (test); Accuracy: 67.44. - [Longitudinal MoCA score prediction on ADNI (1-year follow-up)](): Longitudinal MoCA score prediction; ADNI (1-year follow-up); R2: 0.5556. - [Progressing data detection (ΔMoCA \< 0) on MCI and AD subjects 1-year cohort (test)](): Progressing data detection (ΔMoCA \< 0); MCI and AD subjects 1-year cohort (test); Accuracy: 64.52. - [Longitudinal MoCA score prediction on ADNI (2-year follow-up)](): Longitudinal MoCA score prediction; ADNI (2-year follow-up); R2: 0.7835. - [Progression Detection (ΔMoCA \< 0) on MCI and AD subjects 2-year cohort (test)](): Progressing data detection (ΔMoCA \< 0); MCI and AD subjects 2-year cohort (test); Accuracy: 71.43. ## Original sources and implementation [Original paper]() [PDF]()