用少量参数将CT预训练模型高效适配到MRI ADHD诊断，性能达新高。
Cross-Modal Fine-Tuning of 3D Convolutional Foundation Models for ADHD Classification with Low-Rank Adaptation
- 3D卷积核分解为低秩更新，仅用164万参数实现高效微调。
- 在公开MRI数据集上达71.9%准确率和0.716的AUC，超越现有方法。
- 首次实现跨模态（CT→MRI）基础模型迁移，适合医疗影像研究者。
儿童注意缺陷多动障碍（ADHD）的早期诊断对教育与心理健康改善至关重要。然而，由于症状异质性强且与其他疾病重叠，基于神经影像数据的诊断仍具挑战性。为此，我们提出一种新型参数高效的迁移学习方法，将大规模3D卷积基础模型（在CT图像上预训练）适配至基于MRI的ADHD分类任务。方法通过将3D卷积核分解为2D低秩更新，引入3D LoRA，显著减少可训练参数量。在公开扩散MRI数据库上的五折交叉验证中，该策略达到最优性能：一个模型变体实现71.9%准确率，另一变体取得0.716的AUC。两者均仅使用164万可训练参数（比全微调模型少113倍以上）。本研究是首个成功实现跨模态（CT→MRI）基础模型迁移的神经影像工作，建立了新的ADHD分类基准，同时大幅提升效率。
原文摘要 · Abstract (English)
Early diagnosis of attention-deficit/hyperactivity disorder (ADHD) in children plays a crucial role in improving outcomes in education and mental health. Diagnosing ADHD using neuroimaging data, however, remains challenging due to heterogeneous presentations and overlapping symptoms with other conditions. To address this, we propose a novel parameter-efficient transfer learning approach that adapts a large-scale 3D convolutional foundation model, pre-trained on CT images, to an MRI-based ADHD classification task. Our method introduces Low-Rank Adaptation (LoRA) in 3D by factorizing 3D convolutional kernels into 2D low-rank updates, dramatically reducing trainable parameters while achieving superior performance. In a five-fold cross-validated evaluation on a public diffusion MRI database, our 3D LoRA fine-tuning strategy achieved state-of-the-art results, with one model variant reaching 71.9% accuracy and another attaining an AUC of 0.716. Both variants use only 1.64 million trainable parameters (over 113x fewer than a fully fine-tuned foundation model). Our results represent one of the first successful cross-modal (CT-to-MRI) adaptations of a foundation model in neuroimaging, establishing a new benchmark for ADHD classification while greatly improving efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。