Differential diagnosis of mass lesions in digital breast tomosynthesis based on radiomics

尤　超; 郑惠中; 姜婷婷; 简嘉豪; 范　明; 厉力华; 吴　炅; 顾雅佳; 彭卫军

doi:10.19401/j.cnki.1007-3639.2021.12.003

您当前的位置：

首页 >

文章列表页 >

Differential diagnosis of mass lesions in digital breast tomosynthesis based on radiomics

更新时间：2025-12-31

- Differential diagnosis of mass lesions in digital breast tomosynthesis based on radiomics
- China Oncology Vol. 31, Issue 12, Pages: 1162-1167(2021)
- 作者机构：
  
  1. 复旦大学附属肿瘤医院放射诊断科，复旦大学上海医学院肿瘤学系,上海,200032
  2. 杭州电子科技大学生物医学工程与仪器研究所,浙江,杭州,310018
  3. 复旦大学附属肿瘤医院乳腺外科，复旦大学上海医学院肿瘤学系,上海,200032
- 作者简介：
- 基金信息：
- DOI：10.19401/j.cnki.1007-3639.2021.12.003
  CLC：
- Published Online：07 January 2022，
  
  Published：07 January 2021
- 稿件说明：
移动端阅览
尤　超, 郑惠中, 姜婷婷, 简嘉豪, 范　明, 厉力华, 吴　炅, 顾雅佳, 彭卫军 . 基于影像组学对数字化乳腺断层摄影中肿块病变的鉴别诊断研究[J]. 中国癌症杂志, 2021, 31(12): 1162-1167.

尤　超, 郑惠中, 姜婷婷, et al. Differential diagnosis of mass lesions in digital breast tomosynthesis based on radiomics[J]. China Oncology, 2021, 31(12): 1162-1167.
尤　超, 郑惠中, 姜婷婷, 简嘉豪, 范　明, 厉力华, 吴　炅, 顾雅佳, 彭卫军 . 基于影像组学对数字化乳腺断层摄影中肿块病变的鉴别诊断研究[J]. 中国癌症杂志, 2021, 31(12): 1162-1167. DOI： 10.19401/j.cnki.1007-3639.2021.12.003.

尤　超, 郑惠中, 姜婷婷, et al. Differential diagnosis of mass lesions in digital breast tomosynthesis based on radiomics[J]. China Oncology, 2021, 31(12): 1162-1167. DOI： 10.19401/j.cnki.1007-3639.2021.12.003.

摘要

背景与目的：数字乳腺体层合成（digital breast tomosynthesis，DBT）可提高病灶的检出率，目前已应用于乳腺癌筛查及人群诊断。针对DBT三维图像，探讨应用影像组学对乳腺肿块病变的鉴别诊断价值。方法：回顾并分析2019年4月—2020年8月于复旦大学附属肿瘤医院行DBT检查并经手术后理学检查证实的患者资料，选取DBT表现为肿块征象的143例女性患者入组。对所有患者基于肿块病灶的三维图像提取影像组学特征，采用Lasso logistic回归模型进行特征降维及筛选以建立影像组学标签。采用逻辑回归（logistic regression，LR）、支持向量机（support vector machine，SVM）以及梯度提升决策树（gradient boosting decision tree，GBDT）3种算法建立模型。以受试者工作特征（receiver operating characteristic，ROC）曲线评价影像组学标签对肿块良恶性的诊断效能。结果：经病理学检查证实的144个病灶中，良性病灶65个，恶性病灶79个，按8∶2比例划分为训练集与测试集。基于不同数目特征的分类器算法，LR、SVM和GBDT的最佳特征数目分别为20、24和32。GBDT模型表现效果最佳，在测试集上取得了0.91的AUC值。结论：基于影像组学的GBDT模型由于其集成学习的优势，可以有效鉴别DBT中肿块病变的良恶性。

Abstract

Background and purpose: Digital breast tomosynthesis (DBT) has been applied to breast cancer screening and diagnosis population

which can improve the breast cancer detection. The purpose of this study was to evaluate the differential diagnosis of breast mass lesions based on DBT images. Methods: In the retrospective study

we analyzed the patients undergoing DBT examination in Fudan University Shanghai Cancer Center between April 2019 and August 2020

who were confirmed by surgery and pathology. Finally

a total of 143 female patients showing mass signs were enrolled in this study. Radiomics features were extracted from 3D images of DBT based on mass lesions

and Lasso logistic regression model was used for feature dimension reduction and screening to establish radiomics labels. The model was built by logistic regression (LR)

support vector machine (SVM) and gradient boosting decision tree (GBDT) algorithms. Receiver operating characteristic (ROC) was used to evaluate the diagnostic efficacy of radiomic labels for benign and malignant breast tumors. Results: Among 144 lesions confirmed by pathology

65 were benign and 79 were malignant. It was divided into training set and test set according to the ratio of 8∶2. Based on the classifier algorithm with different number features

the optimal numbers of features of LR

SVM and GBDT were 20

24 and 32 respectively. The GBDT model achieved an area under curve (AUC) value of 0.91 on the test set. Conclusion: Due to the advantages of integrated learning

GBDT model based on radiomics could effectively distinguish benign from malignant breast lesions in DBT.

关键词

Keywords

references

Views

2248

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Guidelines for breast cancer diagnosis and treatment by China Anti-Cancer Association (2026 edition)

Exploration of the efficacy and safety of indocyanine green in the evaluation and localization of breast cancer surgical margins: a single-center, observational cohort study

Research progress and prospects of MRI in predicting lymph node status in breast cancer

MRI-based radiomics and deep learning model construction: non-invasive differentiation of molecular subtypes in primary intracranial diffuse large B-cell lymphoma

Artificial intelligence in gastric cancer diagnosis, treatment and prognostic prediction: current application and future perspective

Related Author

The Society of Breast Cancer China Anti-Cancer Association

Breast Oncology Group of the Oncology Branch of the Chinese Medical Association

Gang LÜ

Guangqing WANG

Yan ZHENG

Qin TANG

Fei CHEN

Xudong YU

Related Institution

Department of Thyroid and Breast Surgery, The Fourth Affiliated Hospital of Anhui Medical University (Affiliated Chaohu Hospital)

Pathology Department, The Fourth Affiliated Hospital of Anhui Medical University (Affiliated Chaohu Hospital)

General Practice, Hefei First People’s Hospital

Department of Breast Surgery, Fudan University Shanghai Cancer Center, Department of Oncology, Shanghai Medical College, Fudan University

Department of Radiology, Huashan Hospital, Fudan University

AI问答

⁰