Research on Brain Tumor Classification Method Based on Improved ResNet34 Network

2025-12-03

AI Summary

To address the time-consuming manual annotation and insufficient accuracy of shallow CNNs in brain tumor medical image classification, this paper proposes an enhanced ResNet34 model. The method integrates multi-scale input, an Inception v2–inspired residual downsampling module, and a channel-wise attention mechanism into the backbone network, synergistically strengthening multi-granularity feature representation and focus on discriminative regions. It balances model compactness and discriminative power by optimizing feature reuse and selection while preserving architectural simplicity. Under five-fold cross-validation, the proposed model achieves a mean classification accuracy of 98.8%, outperforming standard ResNet34 by 1.0 percentage point while reducing parameter count by 20%, thereby significantly improving the accuracy–efficiency trade-off. The core contribution lies in a unified modeling framework that jointly incorporates multi-scale perception, efficient downsampling, and attention-guided feature learning.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Previously, image interpretation in radiology relied heavily on manual methods. However, manual classification of brain tumor medical images is time-consuming and labor-intensive. Even with shallow convolutional neural network models, the accuracy is not ideal. To improve the efficiency and accuracy of brain tumor image classification, this paper proposes a brain tumor classification model based on an improved ResNet34 network. This model uses the ResNet34 residual network as the backbone network and incorporates multi-scale feature extraction. It uses a multi-scale input module as the first layer of the ResNet34 network and an Inception v2 module as the residual downsampling layer. Furthermore, a channel attention mechanism module assigns different weights to different channels of the image from a channel domain perspective, obtaining more important feature information. The results after a five-fold crossover experiment show that the average classification accuracy of the improved network model is approximately 98.8%, which is not only 1% higher than ResNet34, but also only 80% of the number of parameters of the original model. Therefore, the improved network model not only improves accuracy but also reduces clutter, achieving a classification effect with fewer parameters and higher accuracy.

Problem

• Improving brain tumor image classification accuracy
• Reducing model parameters for efficiency
• Enhancing feature extraction with attention mechanisms

Innovation

• Improved ResNet34 with multi-scale feature extraction
• Inception v2 module for residual downsampling layer
• Channel attention mechanism for weighting important features