Predictive Study of Breast Cancer Pathological Images Based on DenseNet201

Han Yang; Miao Zhuang; Sun Yue; Guo Jinxing; Chen Guangxin; Gao Mingze

您当前的位置：

首页 >

文章列表页 >

Predictive Study of Breast Cancer Pathological Images Based on DenseNet201

更新时间：2024-05-31

- Predictive Study of Breast Cancer Pathological Images Based on DenseNet201
- New Generation of Information Technology Pages: 1-6(2024)
- 作者机构：
  
  1.牡丹江医学院医学影像学院，黑龙江牡丹江，157011
  2.牡丹江医学院基础医学院，黑龙江牡丹江，157011
  3.牡丹江医学院附属红旗医院，黑龙江牡丹江，157011
- 作者简介：
- 基金信息：
- DOI：
  CLC： R195
- Published Online：31 May 2024，
扫描看全文
韩杨,苗壮,孙悦等.基于DenseNet201的乳腺癌病理图像的预测研究[J].新一代信息技术,

Han Yang,Miao Zhuang,Sun Yue,et al.Predictive Study of Breast Cancer Pathological Images Based on DenseNet201[J].New Generation of Information Technology,
韩杨,苗壮,孙悦等.基于DenseNet201的乳腺癌病理图像的预测研究[J].新一代信息技术, DOI：10.3969/j.issn.2096-6091.XXXX.XX.001.

Han Yang,Miao Zhuang,Sun Yue,et al.Predictive Study of Breast Cancer Pathological Images Based on DenseNet201[J].New Generation of Information Technology, DOI：10.3969/j.issn.2096-6091.XXXX.XX.001.

摘要

目的

利用DenseNet201网络构建乳腺病理图像分类预测模型。

方法

数据集包括162个乳腺癌标本，其中使用DenseNet121进行实验对比。

结果

DenseNet201相较于DenseNet121在乳腺癌检测上表现更出色，通过20个训练epochs，整体准确性达82%，未患有浸润性导管癌类别精确度90%、召回率84%，F1分数为0.87。患有浸润性导管癌类别精确度66%、召回率77%，F1分数为0.71。相比其他DenseNet网络，DenseNet201在准确率上提高了5%左右。

结论

DenseNet201在处理大规模乳腺癌图像数据集时，具备更强大的特征提取能力，能更好地适应复杂的数据模式和关系，从而提高了乳腺癌检测的准确性和效率。

Abstract

This study takes breast cancer as the object. Through image processing and deep learning technology

DenseNet201 network is used to analyze and classify breast pathological images. The dataset included 162 breast cancer specimens

of which DenseNet121 was used for experimental comparison. Experimental results showed that DenseNet201 performed better in breast cancer detection than DenseNet121. Through 20 training epochs

the overall accuracy reached 82%

the accuracy of category without invasive ductal carcinoma was 90%

the recall rate was 84%

and the F1 score was 0.87. With invasive ductal carcinoma category accuracy of 66%

recall rate of 77%

F1 score of 0.71. Compared to other DenseNet networks

DenseNet201 improves accuracy by about 5%. When processing large-scale breast cancer image data sets

DenseNet201 has more powerful feature extraction capabilities and can better adapt to complex data patterns and relationships

thus improving the accuracy and efficiency of breast cancer detection.

关键词

乳腺癌DenseNet病理图像深度学习

Keywords

breast cancerDenseNetPathological imageDeep learning

references

Burstein H J, Curigliano G, Thürlimann B, et al. Customizing local and systemic therapies for women with early breast cancer: the St. Gallen International Consensus Guidelines for treatment of early breast cancer 2021[J]. Annals of oncology, 2021, 32(10): 1216-1235.

Wilkinson L, Gathani T. Understanding breast cancer as a global health concern[J]. The British Journal of Radiology, 2022, 95(1130): 20211033.

Katsura C, Ogunmwonyi I, Kankam H K N, et al. Breast cancer: presentation, investigation and management[J]. British Journal of Hospital Medicine, 2022, 83(2): 1-7.

Elston C W, Ellis I O, Pinder S E. Pathological prognostic factors in breast cancer[J]. Critical reviews in oncology/hematology, 1999, 31(3): 209-223.

Udupa J K, Herman G T. Medical image reconstruction, processing, visualization, and analysis: the MIPG perspective[J]. IEEE Transactions on Medical Imaging, 2002, 21(4): 281-295.

Cserni G, Amendoeira I, Apostolikas N, et al. Pathological work-up of sentinel lymph nodes in breast cancer. Review of current data to be considered for the formulation of guidelines[J]. European Journal of Cancer, 2003, 39(12): 1654-1667.

Zhang Y, **a K R, Li C Y, et al. Review of breast cancer pathologigcal image processing[J]. BioMed research international, 2021, 2021: 1-7.

Zhu Y, Newsam S. Densenet for dense flow[C]//2017 IEEE international conference on image processing (ICIP). IEEE, 2017: 790-794.

Al-Masni M A, Al-Antari M A, Park J M, et al. Simultaneous detection and classification of breast masses in digital mammograms via a deep learning YOLO-based CAD system[J]. Computer methods and programs in biomedicine, 2018, 157: 85-94.

Stollmayer R, Budai B K, Tóth A, et al. Diagnosis of focal liver lesions with deep learning-based multi-channel analysis of hepatocyte-specific contrast-enhanced magnetic resonance imaging[J]. World Journal of Gastroenterology, 2021, 27(35): 5978.

刘金平,吴娟娟,张荣,等.基于结构重参数化与多尺度深度监督的COVID-19胸部CT图像自动分割[J].电子学报,2023,51(05):1163-1171.

谢娟英,张凯云. SOSNet:一种非对称编码器-解码器结构的非小细胞肺癌CT图像分割模型[J]. 电子学报:1-15.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Microscopic Displacement Image Classification Based on Deep Learning

Research on Classification of Medicinal Plant Leaves Based on Improved CNN

DenseNet Model Based on Transfer Learning in Plant Leaf Pest Classification

A study of the joint framework for real-world super-resolution -semantic segmentation

Related Author

TENG Qi-zhi

GONG Jian

HE Xiao-hai

WANG Man-long

LIANG Xin

ZHAI Feng-guo

SUN Yan-bin

LIU Yi

Related Institution

Chengdu Xitu Technology Co. Ltd

College of Electronics and Information Engineering, Sichuan University

Mudanjiang Medical College

Affiliated Hongqi Hospital, Mudanjiang Medical College

Mudan River Medical College

⁰