Lite-FBCN: Lightweight Fast Bilinear Convolutional Network for Brain Disease Classification from MRI Image

TL;DR

Lite-FBCN is a lightweight, efficient bilinear convolutional network that improves brain disease classification accuracy from MRI scans while reducing computational complexity, suitable for real-time clinical applications.

Contribution

It introduces a single-network bilinear model with a channel reducer layer, outperforming existing models in accuracy and efficiency for MRI-based brain disease classification.

Findings

Achieves 98.10% accuracy in cross-validation

Outperforms baseline CNNs and existing bilinear models

Offers a favorable trade-off between performance and computational cost

Abstract

Achieving high accuracy with computational efficiency in brain disease classification from Magnetic Resonance Imaging (MRI) scans is challenging, particularly when both coarse and fine-grained distinctions are crucial. Current deep learning methods often struggle to balance accuracy with computational demands. We propose Lite-FBCN, a novel Lightweight Fast Bilinear Convolutional Network designed to address this issue. Unlike traditional dual-network bilinear models, Lite-FBCN utilizes a single-network architecture, significantly reducing computational load. Lite-FBCN leverages lightweight, pre-trained CNNs fine-tuned to extract relevant features and incorporates a channel reducer layer before bilinear pooling, minimizing feature map dimensionality and resulting in a compact bilinear vector. Extensive evaluations on cross-validation and hold-out data demonstrate that Lite-FBCN not only surpasses baseline CNNs but also outperforms existing bilinear models. Lite-FBCN with MobileNetV1 attains 98.10% accuracy in cross-validation and 69.37% on hold-out data (a 3% improvement over the baseline). UMAP visualizations further confirm its effectiveness in distinguishing closely related brain disease classes. Moreover, its optimal trade-off between performance and computational efficiency positions Lite-FBCN as a promising solution for enhancing diagnostic capabilities in resource-constrained and or real-time clinical environments.