设为首页 联系我们 加入收藏

当前位置: 网站首页 期刊分类目录 2025年第2期 正文

基于移动倒置瓶颈和迁移学习的乳腺癌组织病理图像二值分类

作者:时间:2025-05-02点击数:


全文下载20.pdf


文章编号: 1672-6987202502-0150-09 DOI 10.16351/j.1672-6987.2025.02.020


臧敏a 曹源a 丰艳a* 于彬ab*青岛科技大学  a. 信息科学技术学院; b. 数据科学学院, 山东 青岛 266061

摘要: 乳腺癌是全球女性患病率最高的癌症组织病理学诊断被认为是诊断乳腺癌的最佳方法然而组织病理学图像的复杂程度和病理学家的知识储备会影响诊断结果的准确性为了解决以上问题同时协助临床医生诊断疾病本工作提出了一种新颖的乳腺癌组织病理图像预测模型称为双信息流移动倒置瓶颈卷积神经网络DMBC-Net首先利用深度可分离卷积坐标注意力和跳跃连接构成DMBC模块该模块为DMBC-Net的基础模块可以在扩大感受野的同时获得具有更多有效信息的特征映射其次ImageNetBACH数据集的基础上利用二次迁移学习训练和优化模型参数最后该模型在公开的BreaKHis数据集进行了验证40100200400倍放大倍数的影响下分类准确率分别达到97.86%96.10%98.00%97.70%DMBC-Net与其他先进模型比较实验结果表明DMBC-Net具有优秀的预测能力


关键词: 乳腺癌 组织病理图像 移动倒置瓶颈 迁移学习 坐标注意力


中图分类号: TP 391.4        文献标志码: A


引用格式: 臧敏 曹源 丰艳 . 基于移动倒置瓶颈和迁移学习的乳腺癌组织病理图像二值分类J. 青岛科技大学学报自然科学版 2025 462 150-158.


ZANG Min CAO Yuan FENG Yan et al. Binary classification of breast cancer histopathological images based on mobile inverted bottleneck and transfer learningJ. Journal of Qingdao University of Science and TechnologyNatural Science Edition 2025 462 150-158.

Binary Classification of Breast Cancer Histopathological Images Based on Mobile Inverted Bottleneck and Transfer Learning

ZANG Mina CAO Yuana FENG Yana YU Binaba. College of Information Science and Technologyb. College of Data ScienceQingdao University of Science and TechnologyQingdao 266061China

Abstract Breast cancer is the most common cancer in women worldwideand histopathological diagnosis is considered the best way to diagnose breast cancer. Howeverthe complexity of histopathological images and the knowledge reserve of pathologists can affect the accuracy of diagnostic results. In order to solve the above problems and assist clinicians in diagnosing diseasesthis paper proposed a novel model for predicting histopathological images of breast cancercalled dual-mobile inverted bottleneck convolutional neural network DMBC-Net. Firsta DMBC module is formed using depthwise separable convolutioncoordinate attentionand skip connections. This module is the basic module of DMBC-Netwhich can obtain feature mapping with more effective information while expanding the receptive field. Thensecondary transfer learning is used to train and optimize model parameters based on the ImageNet and BACH datasets. FinallyDMBC-Net is verified on the public BreaKHis dataset. Under the influence of 40100200 and 400 magnificationsthe classification accuracy reached 97.86%96.10%98.00% and 97.70% respectively. Comparing DMBC-Net with other advanced modelsthe experimental results show that DMBC-Net has excellent prediction ability.


Key words breast cancerhistopathological imagesmobile inverted bottlenecktransfer learningcoordinate attention

收稿日期: 2024-10-17

基金项目: 国家自然科学基金项目62172248;山东省自然科学基金项目ZR2021MF098.

作者简介: 臧敏1998—,女,硕士研究生.     * 通信联系人.



Copyright © 2011-2017 青岛科技大学学报 (自然科学版)