Systematic Integration of Attention Modules into CNNs for Accurate and Generalizable Medical Image Diagnosis

2025/09/02 by Zahid Ullah, Ullah, Zahid, Minki Hong +5
Neuroscience · #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2509.05343

openalex publication_date 2025/09/02 · openalex created_date 2025/10/11 · openalex updated_date 2026/07/28

Abstract

Deep learning has become a powerful tool for medical image analysis; however, conventional Convolutional Neural Networks (CNNs) often fail to capture the fine-grained and complex features critical for accurate diagnosis. To address this limitation, we systematically integrate attention mechanisms into five widely adopted CNN architectures, namely, VGG16, ResNet18, InceptionV3, DenseNet121, and EfficientNetB5, to enhance their ability to focus on salient regions and improve discriminative performance. Specifically, each baseline model is augmented with either a Squeeze and Excitation block or a hybrid Convolutional Block Attention Module, allowing adaptive recalibration of channel and spatial feature representations. The proposed models are evaluated on two distinct medical imaging datasets, a brain tumor MRI dataset comprising multiple tumor subtypes, and a Products of Conception histopathological dataset containing four tissue categories. Experimental results demonstrate that attention augmented CNNs consistently outperform baseline architectures across all metrics. In particular, EfficientNetB5 with hybrid attention achieves the highest overall performance, delivering substantial gains on both datasets. Beyond improved classification accuracy, attention mechanisms enhance feature localization, leading to better generalization across heterogeneous imaging modalities. This work contributes a systematic comparative framework for embedding attention modules in diverse CNN architectures and rigorously assesses their impact across multiple medical imaging tasks. The findings provide practical insights for the development of robust, interpretable, and clinically applicable deep learning based decision support systems.

Citations

• Hybrid Ensemble Approaches: Optimal Deep Feature Fusion and Hyperparameter-Tuned Classifier Ensembling for Enhanced Brain Tumor Classification
• Hierarchical Deep Feature Fusion and Ensemble Learning for Enhanced Brain Tumor MRI Classification
• Improved EATFormer: A Vision Transformer for Medical Image Classification
• Image Data Augmentation for Deep Learning: A Survey
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning
• CBAM: Convolutional Block Attention Module
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Squeeze-and-Excitation Networks
• Densely Connected Convolutional Networks
• Deep Residual Learning for Image Recognition
• Rethinking the Inception Architecture for Computer Vision
• Going Deeper with Convolutions
• Very Deep Convolutional Networks for Large-Scale Image Recognition

Related

• Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images
• Comparative Analysis of Resource-Efficient CNN Architectures for Brain Tumor Classification
• MRI-Based Brain Tumor Detection through an Explainable EfficientNetV2 and MLP-Mixer-Attention Architecture
• A4-Unet: Deformable Multi-Scale Attention Network for Brain Tumor Segmentation
• A Novel Global Spatial Attention Mechanism in Convolutional Neural Network for Medical Image Classification