随着医学图像分析技术的不断进步,乳腺癌的早期诊断逐渐成为研究的热点之一。先进的图像处理算法和人工智能技术的应用,使得从复杂的医学图像中提取关键信息变得更加高效和准确。针对乳腺癌组织病理学图像分类问题,本文提出了一种基于小波变换与支持向量机(WT-SVM)相结合的分类算法。首先,利用小波变换对乳腺癌图像进行多尺度特征提取,捕捉图像的局部细节和全局结构信息;然后,采用支持向量机对提取的特征进行分类,以实现良性和恶性乳腺癌图像的精确识别。实验结果表明,WT-SVM算法在BreakHis数据集上的分类性能优于传统SVM算法,具有较高的准确率、精确率、召回率和F1值。该算法能够有效提高乳腺癌组织病理图像的分类精度,并表现出良好的鲁棒性和泛化能力。本文的研究为乳腺癌的早期诊断提供了一种高效、精准的技术方案,具有广泛的应用前景。With the continuous advancement of medical image analysis technology, early diagnosis of breast cancer has gradually become one of the research hotspots. The application of advanced image processing algorithms and artificial intelligence technology has made it more efficient and accurate to extract key information from complex medical images. Aiming at the problem of breast cancer histopathology image classification, this paper proposes a classification algorithm based on wavelet transform combined with support vector machine (WT-SVM). First, wavelet transform is used to extract multi-scale features of breast cancer images to capture local details and global structural information of the image;then, support vector machine is used to classify the extracted features to achieve accurate recognition of benign and malignant breast cancer images. Experimental results show that the classification performance of WT-SVM algorithm on BreakHis dataset is better than that of traditional SVM algorithm, with higher accuracy, precision, re
