文献速递乳腺MR

基于多参数MRI的乳腺病灶全自动影像组学分类研究

Fully automatic classification of breast lesions on multi-parameter MRI using a radiomics model with minimal number of stable, interpretable features.
PubMed 文献 · Radiol Med · 2023-01-20

本研究纳入222个经组织病理学证实的乳腺病灶及其BI-RADS评分,随机分为训练集(159例)和测试集(63例),另收集50个病灶作为外部验证集。基于nnUNet自动分割病灶ROI,从DWI、T2WI和DCE药代动力学参数图中提取影像组学特征,构建SVM和LR模型。仅用三个特征(ADC、T2WI、DCE动力学参数图)的影像组学模型测试集AUC为0.946,外部验证集AUC为0.842,高于BI-RADS评分(AUC 0.872)。影像组学联合BI-RADS的联合模型测试集AUC最高达0.975,敏感度0.920,特异度0.923。

要点

  • 三特征影像组学模型可自动分类乳腺病灶,测试集AUC 0.946,外部验证AUC 0.842。
  • 联合BI-RADS评分后诊断效能提升至AUC 0.975,敏感度0.920,特异度0.923。
  • 自动分割模型测试集Dice系数0.831,可支持全自动CAD流程。

核心结论

  • 三个影像组学特征可构建全自动影像组学流程,改善乳腺病灶诊断并减少不必要的活检,尤其与BI-RADS评分联合使用时效果更佳。

研究设计与样本

  • 回顾性研究纳入222个组织病理学证实的乳腺病灶及BI-RADS评分,随机分为训练集159例和测试集63例,另收集50个病灶作为外部验证集。
  • 训练nnUNet模型自动分割病灶ROI,从DWI、T2WI和DCE药代动力学参数图中提取影像组学特征。
  • 基于序列组合使用SVM和LR建模,计算Dice系数和AUC评估分割与分类性能,并用DCA评估临床效用。

诊断标准与关键数值

  • 分割模型测试集Dice系数0.831。
  • 三特征影像组学模型测试集AUC 0.946 [0.883-0.990],外部验证集AUC 0.842 [0.6856-0.998]。
  • BI-RADS评分AUC 0.872 [0.752-0.975]。
  • 影像组学评分联合BI-RADS评分的联合模型测试集AUC最高0.975 [0.935-1.000],敏感度0.920,特异度0.923。

临床应用与阅片要点

  • 可基于ADC图、T2WI和DCE动力学参数图提取的三个稳定、可解释特征构建自动分类模型辅助乳腺病灶诊断。
  • 影像组学评分与BI-RADS评分联合使用可提高诊断效能,有助于减少不必要的活检。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: To build an automatic computer-aided diagnosis (CAD) pipeline based on multiparametric magnetic resonance imaging (mpMRI) and explore the role of different imaging features in the classification of breast cancer.

MATERIALS AND METHODS: A total of 222 histopathology-confirmed breast lesions, together with their BI-RADS scores, were included in the analysis. The cohort was randomly split into training (159) and test (63) cohorts, and another 50 lesions were collected as an external cohort. An nnUNet-based lesion segmentation model was trained to automatically segment lesion ROI, from which radiomics features were extracted for diffusion-weighted imaging (DWI), T2-weighted imaging (T2WI), and contrast-enhanced (DCE) pharmacokinetic parametric maps. Models based on combinations of sequences were built using support vector machine (SVM) and logistic regression (LR). Also, the performance of these sequence combinations and BI-RADS scores were compared. The Dice coefficient and AUC were calculated to evaluate the segmentation and classification results. Decision curve analysis (DCA) was used to assess clinical utility.

RESULTS: The segmentation model achieved a Dice coefficient of 0.831 in the test cohort. The radiomics model used only three features from diffusion coefficient (ADC) images, T2WI, and DCE-derived kinetic mapping, and achieved an AUC of 0.946 [0.883-0.990], AUC of 0.842 [0.6856-0.998] in the external cohort, which was higher than the BI-RADS score with an AUC of 0.872 [0.752-0.975]. The joint model using both radiomics score and BI-RADS score achieved the highest test AUC of 0.975 [0.935-1.000], with a sensitivity of 0.920 and a specificity of 0.923.

CONCLUSION: Three radiomics features can be used to construct an automatic radiomics-based pipeline to improve the diagnosis of breast lesions and reduce unnecessary biopsies, especially when using jointly with BI-RADS scores.

来源:Radiol Med,查看原文。版权归原作者所有。

引用

  1. Zhang, Zhan, Zhang, et al. Fully automatic classification of breast lesions on multi-parameter MRI using a radiomics model with minimal number of stable, interpretable features. Radiol Med. 2023. PMID: 36670236. doi:10.1007/s11547-023-01594-w

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。