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.
Abstract:Deep learning models have revolutionized the field of medical image analysis, offering significant promise for improved diagnostics and patient care. However, their performance can be misleadingly optimistic due to a hidden pitfall called 'data leakage'. In this study, we investigate data leakage in 3D medical imaging, specifically using 3D Convolutional Neural Networks (CNNs) for brain MRI analysis. While 3D CNNs appear less prone to leakage than 2D counterparts, improper data splitting during cross-validation (CV) can still pose issues, especially with longitudinal imaging data containing repeated scans from the same subject. We explore the impact of different data splitting strategies on model performance for longitudinal brain MRI analysis and identify potential data leakage concerns. GradCAM visualization helps reveal shortcuts in CNN models caused by identity confounding, where the model learns to identify subjects along with diagnostic features. Our findings, consistent with prior research, underscore the importance of subject-wise splitting and evaluating our model further on hold-out data from different subjects to ensure the integrity and reliability of deep learning models in medical image analysis.