Enhanced ADHD detection: Frequency information embedded in a visual-language framework

This paper presents the Frequency-Integrated Visual-Language Network (FIVLNet), a deep learning (DL) framework tailored to improve the diagnostic accuracy for Attention Deficit Hyperactivity Disorder (ADHD) using magnetic resonance imaging (MRI) scans. Traditional DL approaches in ADHD diagnosis often overlook the sequential dependencies of MRI images or fail to adequately capture their complex structural details, resulting in suboptimal classification accuracy. To address this, the proposed FIVLNet synergistically integrates both high and low-frequency data from MRI images, based on the Convolutional Neural Network (CNN) and the cross-attention mechanism, subsequently achieving more comprehensive representations of the MRI images. Furthermore, in order to enrich the model's learning capacity, textual embeddings from Contrastive Language-Image Pre-training (CLIP) are introduced to provide additional modalities of information. FIVLNet also preserves a lightweight architecture, which necessitates a smaller number of learnable parameters compared to existing models.