arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.03751cs.CVcs.AI
收藏

基于改进ResNet34网络的脑肿瘤分类方法研究

Research on Brain Tumor Classification Method Based on Improved ResNet34 Network

University of Southampton(南安普顿大学);University of Science and Technology of China(中国科学技术大学);San Francisco Bay University(旧金山湾大学);The Hong Kong University of Science and Technology(香港科技大学)

Yufeng Li, Wenchao Zhao, Bo Dang, Weimin Wang

AI总结:

本文提出基于改进ResNet34网络的脑肿瘤分类模型,通过多尺度特征提取和通道注意力机制提升分类准确率至98.8%,参数量减少至原模型的80%。

摘要:

以前,放射学中的图像解读严重依赖于人工方法。然而,手动分类脑肿瘤医学图像既耗时又费力。即使使用浅层卷积神经网络模型,准确性也不理想。为提高脑肿瘤图像分类的效率和准确性,本文提出了一种基于改进ResNet34网络的脑肿瘤分类模型。该模型以ResNet34残差网络为骨干网络,并结合多尺度特征提取。它使用多尺度输入模块作为ResNet34网络的第一层,并使用Inception v2模块作为残差下采样层。此外,通道注意力机制模块从通道域的角度对图像的不同通道分配不同的权重,从而获得更重要的特征信息。五折交叉验证实验后的结果表明,改进网络模型的平均分类准确率约为98.8%,这不仅比ResNet34高1%,而且参数数量仅为原模型的80%。因此,改进的网络模型不仅提高了准确性,还减少了冗余,实现了参数更少、准确性更高的分类效果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑