Cross-Modal Fine-Tuning of 3D Convolutional Foundation Models for ADHD Classification with Low-Rank Adaptation
This addresses the challenge of diagnosing ADHD from neuroimaging data, which is important for children's education and mental health outcomes, though it appears to be an incremental advance in parameter-efficient transfer learning.
The paper tackled ADHD classification from MRI data by adapting a CT-trained 3D convolutional foundation model using a novel 3D Low-Rank Adaptation method, achieving state-of-the-art results with 71.9% accuracy and 0.716 AUC while using 113x fewer trainable parameters than full fine-tuning.
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.