TNF: Tri-branch Neural Fusion for Multimodal Medical Data Classification
This addresses classification challenges in medical imaging and tabular data, but appears incremental as it builds on existing fusion and ensemble techniques.
The paper tackles the problem of label inconsistency in multimodal medical data classification by proposing a Tri-branch Neural Fusion (TNF) approach, which uses a tri-branch framework with ensemble integration to improve accuracy over traditional methods.
This paper presents a Tri-branch Neural Fusion (TNF) approach designed for classifying multimodal medical images and tabular data. It also introduces two solutions to address the challenge of label inconsistency in multimodal classification. Traditional methods in multi-modality medical data classification often rely on single-label approaches, typically merging features from two distinct input modalities. This becomes problematic when features are mutually exclusive or labels differ across modalities, leading to reduced accuracy. To overcome this, our TNF approach implements a tri-branch framework that manages three separate outputs: one for image modality, another for tabular modality, and a third hybrid output that fuses both image and tabular data. The final decision is made through an ensemble method that integrates likelihoods from all three branches. We validate the effectiveness of TNF through extensive experiments, which illustrate its superiority over traditional fusion and ensemble methods in various convolutional neural networks and transformer-based architectures across multiple datasets.