Hyperparameter Tuning of the Proposed Model.

Breast cancer is highlighted in recent research as one of the most prevalent types of cancer. Timely identification is essential for enhancing patient results and decreasing fatality rates. Utilizing computer-assisted detection and diagnosis early on may greatly improve the chances of recovery by accurately predicting outcomes and developing suitable treatment plans. Grading breast cancer properly, especially evaluating nuclear atypia, is difficult owing to faults and inconsistencies in slide preparation and the intricate nature of tissue patterns. This work explores the capability of deep learning to extract characteristics from histopathology photos of breast cancer. The research introduces a new method called SMOTE-based Convolutional Neural Network (CNN) technology to detect areas impacted by Invasive Ductal Carcinoma (IDC) in whole slide pictures. The trials used a dataset of 162 individuals with IDC, split into training (113 photos) and testing (49 images) groups. Every model was subjected to individual testing. The SMO_CNN model we developed demonstrated exceptional testing and training accuracies of 98.95% and 99.20% respectively, surpassing CNN, VGG19, and ResNet50 models. The results highlight the effectiveness of the created model in properly detecting IDC-affected tissue areas, showing great promise for improving breast cancer diagnosis and treatment planning. We surpassing other models as such, CNN, VGG19, ResNet50.

乳腺癌在近年研究中被列为最为高发的癌症类型之一。及时确诊对于改善患者预后、降低病死率至关重要。早期采用计算机辅助检测与诊断技术，可通过精准预测病情转归并制定适宜治疗方案，大幅提升患者康复几率。对乳腺癌进行精准分级，尤其是评估核异型性，由于玻片制备过程中的误差与不一致性，以及组织形态的复杂性而颇具挑战。本研究探讨了深度学习从乳腺癌组织病理图像中提取特征的能力。本研究提出一种基于SMOTE的卷积神经网络（Convolutional Neural Network, CNN）技术，用于在全玻片图像中识别受浸润性导管癌（Invasive Ductal Carcinoma, IDC）累及的区域。本试验采用包含162例IDC患者的数据集，将其划分为训练集（113张图像）与测试集（49张图像），并对所有模型开展独立测试。本研究构建的SMO_CNN模型分别实现了99.20%的训练准确率与98.95%的测试准确率，性能优于传统CNN、VGG19及ResNet50模型。研究结果证实了所提模型在精准识别IDC累及组织区域方面的有效性，为优化乳腺癌诊断与治疗方案提供了极具潜力的技术路径。本模型的性能优于CNN、VGG19及ResNet50等同类模型。