Güler Mustafa, Sart Gamze, Algorabi Ömer, Adıguzel Tuylu Ayse Nur, Türkan Yusuf Sait
Engineering Sciences Department, Engineering Faculty, Istanbul University-Cerrahpasa, Istanbul 34320, Türkiye.
Department of Educational Sciences, Hasan Ali Yucel Faculty of Education, Istanbul University-Cerrahpasa, Istanbul 34500, Türkiye.
Diagnostics (Basel). 2025 Jul 10;15(14):1751. doi: 10.3390/diagnostics15141751.
In recent years, there has been a significant increase in the number of women with breast cancer. Breast cancer prediction is defined as a medical data analysis and image processing problem. Experts may need artificial intelligence technologies to distinguish between benign and malignant tumors in order to make decisions. When the studies in the literature are examined, it can be seen that applications of deep learning algorithms in the field of medicine have achieved very successful results. In this study, 11 different deep learning algorithms (Vanilla, ResNet50, ResNet152, VGG16, DenseNet152, MobileNetv2, EfficientB1, NasNet, DenseNet201, ensemble, and Tuned Model) were used. Images of pathological specimens from breast biopsies consisting of two classes, benign and malignant, were used for classification analysis. To limit the computational time and speed up the analysis process, 10,000 images, 6172 IDC-negative and 3828 IDC-positive, were selected. Of the images, 80% were used for training, 10% were used for validation, and 10% were used for testing the trained model. The results demonstrate that DenseNet201 achieved the highest classification accuracy of 89.4%, with a precision of 88.2%, a recall of 84.1%, an F1 score of 86.1%, and an AUC score of 95.8%. In conclusion, this study highlights the potential of deep learning algorithms in breast cancer classification. Future research should focus on integrating multi-modal imaging data, refining ensemble learning methodologies, and expanding dataset diversity to further improve the classification accuracy and real-world clinical applicability.
近年来，乳腺癌女性患者的数量显著增加。乳腺癌预测被定义为一个医学数据分析和图像处理问题。专家们可能需要人工智能技术来区分良性和恶性肿瘤以便做出决策。当审视文献中的研究时，可以看到深度学习算法在医学领域的应用已经取得了非常成功的成果。在本研究中，使用了11种不同的深度学习算法（原始模型、ResNet50、ResNet152、VGG16、DenseNet152、MobileNetv2、EfficientB1、NasNet、DenseNet201、集成模型和调优模型）。由良性和恶性两类组成的乳腺活检病理标本图像被用于分类分析。为了限制计算时间并加快分析过程，选择了10000张图像，其中6172张IDC阴性图像和3828张IDC阳性图像。在这些图像中，80%用于训练，10%用于验证，10%用于测试训练好的模型。结果表明，DenseNet201实现了最高分类准确率89.4%，精确率为88.2%，召回率为84.1%，F1分数为86.1%，AUC分数为95.8%。总之，本研究突出了深度学习算法在乳腺癌分类中的潜力。未来的研究应集中在整合多模态成像数据、完善集成学习方法以及扩大数据集多样性，以进一步提高分类准确率和实际临床适用性。
