Brain-Adapter: Enhancing Neurological Disorder Analysis with Adapter-Tuning Multimodal Large Language Models

TL;DR

This paper introduces Brain-Adapter, a novel multimodal large language model approach that enhances neurological disorder analysis by integrating 3D medical images and text, improving diagnosis accuracy efficiently.

Contribution

It proposes a lightweight adapter with contrastive learning to effectively incorporate multimodal data into pre-trained models for better neurological disorder diagnosis.

Findings

Significantly improved diagnosis accuracy with multimodal data integration

Efficient training with fewer parameters using the adapter layer

Effective alignment of multimodal data in a unified representation space

Abstract

Understanding brain disorders is crucial for accurate clinical diagnosis and treatment. Recent advances in Multimodal Large Language Models (MLLMs) offer a promising approach to interpreting medical images with the support of text descriptions. However, previous research has primarily focused on 2D medical images, leaving richer spatial information of 3D images under-explored, and single-modality-based methods are limited by overlooking the critical clinical information contained in other modalities. To address this issue, this paper proposes Brain-Adapter, a novel approach that incorporates an extra bottleneck layer to learn new knowledge and instill it into the original pre-trained knowledge. The major idea is to incorporate a lightweight bottleneck layer to train fewer parameters while capturing essential information and utilize a Contrastive Language-Image Pre-training (CLIP) strategy to align multimodal data within a unified representation space. Extensive experiments demonstrated the effectiveness of our approach in integrating multimodal data to significantly improve the diagnosis accuracy without high computational costs, highlighting the potential to enhance real-world diagnostic workflows.