Automated classification of breast MRI background parenchymal enhancement using deep learning and thresholding segmentation method

MA Mingming; ZHANG Yaofeng; WANG Xiangpeng; ZHANG Xiaodong; QIN Naishan; WANG Xiaoying

doi:10.19732/j.cnki.2096-6210.2021.05.003

您当前的位置：

首页 >

文章列表页 >

Automated classification of breast MRI background parenchymal enhancement using deep learning and thresholding segmentation method

更新时间：2025-12-15

- Automated classification of breast MRI background parenchymal enhancement using deep learning and thresholding segmentation method
- Vol. 30, Issue 5, Pages: 332-338(2021)
- 作者机构：
  
  1. 北京大学第一医院医学影像科,北京,100034
  2. 北京赛迈特锐医学科技有限公司,北京,100011
- 作者简介：
- 基金信息：
- DOI：10.19732/j.cnki.2096-6210.2021.05.003
  CLC：
- Published Online：28 October 2021，
  
  Published：28 October 2021
- 稿件说明：
移动端阅览
马明明,张耀峰,王祥鹏,等. 基于深度学习和阈值分割方法对乳腺MRI中背景实质强化自动分类的研究[J]. 肿瘤影像学, 2021, 30(5): 332-338 https://doi.

org/10.19732/j.cnki.2096-6210.2021.05.003
马明明,张耀峰,王祥鹏,等. 基于深度学习和阈值分割方法对乳腺MRI中背景实质强化自动分类的研究[J]. 肿瘤影像学, 2021, 30(5): 332-338 https://doi. DOI： 10.19732/j.cnki.2096-6210.2021.05.003.

org/10.19732/j.cnki.2096-6210.2021.05.003 DOI：

摘要

目的：

探讨基于深度学习和阈值分割方法对乳腺磁共振成像（magnetic resonance imaging，MRI）背景实质强化（background parenchymal enhancement，BPE）自动分类的可行性。

方法：

回顾并分析2010年1月2018年10月北京大学第一医院行乳腺MRI检查的547例乳腺癌患者的影像学资料。由2名高年资放射科医师共同评估，依据乳腺影像报告和数据系统（Breast Imaging Reporting and Data System，BI-RADS）对健侧乳腺的BPE进行人工BPE的4分类作为金标准。先用训练好的深度学习U-Net 3D模型分割乳腺纤维腺体组织（fibroglandular tissue，FGT）区域，分割效果的评价指标为Dice相似性系数（Dice similarity coefficient，DSC）。再利用阈值分割技术获取BPE区域，计算BPE体积与FGT体积的比值得到自动BPE分类，并生成到结构化报告中。将自动BPE分类与人工BPE分类进行比较，以混淆矩阵进行效能分析，计算总准确度、F1值和Kappa值。

结果：

U-Net 3D模型对547个数据FGT分割的平均DSC为0.902。通过阈值分割技术计算得到自动BPE分类结果的整体准确度为0.95（95% CI：0.88~0.93），宏平均F1为0.84，微平均F1为0.90，Kappa为0.81（95% CI：0.76~0.86）。

结论：

基于深度学习和阈值分割技术对乳腺MRI背景强化的自动化分类是可行的，有潜在的临床应用价值。

Abstract

Objective：

To explore the feasibility of automatic classification of breast magnetic resonance imaging (MRI) background parenchymal enhancement (BPE) based on deep learning and thresholding segmentation.

Methods:

Breast MRI dataof 547 breast cancer patients were r

etrospectively collected from January 2010 to October 2018 in Peking University First Hospital. According to the Breast Imaging Reporting and Data System (BI-RADS)

each image was classified into four categories by two senior radiologists

which was used as the reference standard. Three steps were performed to acquire the BPE category automatically. Firstly

the region of fibroglandular tissue (FGT) was segmented by using a U-Net 3D model. The Dice similarity coefficient (DSC) was used to evaluate the efficacy of the model. Secondly

the region of BPE was segmented by the thresholding technology. Thirdly

the ratio of the BPE volume to the FGT volume was calculated and the BPE category was obtained. The BPE category was automatically input into the structured report. The multi-class confusion matrix was used to analyze the performance of the calculated BPE

with the metrics of accuracy

F1 score

and Kappa.

Results:

The average DSC of the U-Net model was 0.902. The Macro accuracy

F1 Macro

F1 Micro

and Kappa was 0.95 (95% CI: 0.88-0.93)

0.84

0.90

and 0.81 (95% CI: 0.76-0.86)

respectively.

Conclusion:

The automated classification of breast MRI background parenchymal enhancement is feasible and has potential clinical application value.

关键词

Keywords

references

Views

1431

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Value of deep learning ultrasound radiomics in predicting axillary lymph node metastasis of breast cancer

Deep learning model based on two-dimensional ultrasound images for preoperative prediction of breast cancer lymphovascular invasion: a human-machine comparison study

Prediction of sentinel lymph node metastasis in breast cancer using multiparametric MRI radiomics and machine learning models

The progress of breast MRI in evaluating breast conservation therapy and ipsilateral breast tumor recurrence

Prediction value of breast MRI in ipsilateral breast tumor recurrence after breast-conserving surgery and distant metastasis following secondary surgery

Related Author

Jiaojiao HU

Xiaohong FU

Yan SHEN

Xiaoqing YU

Qingqing CHEN

Su HU

Jinyu LAI

Lichang ZHONG

Related Institution

Department of Radiology, The First Affiliated Hospital of Soochow University

Department of Ultrasound, Gongli Hospital, Shanghai Pudong New Area

Institute of Medical Imaging, Soochow University

Department of Ultrasound in Medicine, Sixth People’s Hospital Affiliated to Medical College of Shanghai Jiao Tong University

Department of Radiology, Ma’anshan People’s Hospital, Ma’anshan

AI问答

⁰