文献速递乳腺技术与安全US

联合影像组学与自编码器在超声图像上鉴别乳腺肿瘤良恶性

Combining Radiomics and Autoencoders to Distinguish Benign and Malignant Breast Tumors on US Images.
PubMed 文献 · Radiology · 2024-01-01

本研究回顾性分析2018年4月至2024年1月共1619张乳腺肿瘤B模式超声图像,训练nnU-Net进行病灶分割,并联合经典影像组学与自编码器特征构建机器学习分类模型。最佳模型基于肿瘤边界框的23个混合特征,在外部验证集上鉴别良恶性的AUC为0.90,敏感度81%、特异度87%,与人类读者及病理/随访确诊诊断之间未发现差异证据。

要点

  • 基于肿瘤边界框的23个混合特征模型在外部验证集鉴别乳腺肿瘤良恶性的AUC为0.90(95%CI: 0.83, 0.97)。
  • 该模型敏感度81%(46/57;95%CI: 70, 91),特异度87%(39/45;95%CI: 77, 87)。
  • 模型与人类读者在肿瘤分类上未发现差异证据(AUC 0.90 vs 0.83,P=.55;0.90 vs 0.82,P=.45)。

核心结论

  • 通过混合肿瘤边界框的经典影像组学与自编码器特征,可构建精确且具备实时能力的超声乳腺肿瘤分类模型。

研究设计与样本

  • 回顾性分析2018年4月至2024年1月共1619张乳腺肿瘤B模式超声图像。
  • 开发集来自1191例女性患者(平均年龄61岁±14),外部验证集来自50例(平均年龄55岁±15)。
  • 开发集分为分割训练与测试(179与419次检查)及分类训练与测试(503与90次检查)。
  • 采用nnU-Net训练病灶分割,从肿瘤分割区、边界框和全图提取经典影像组学、自编码器或两者混合特征,经特征选择生成影像组学签名并训练机器学习算法。
  • 以病理组织学或随访确诊诊断为参考标准,采用AUC、敏感度和特异度评价模型。

诊断标准与关键数值

  • nnU-Net在数据集1测试集分割中位Dice评分0.90(IQR 0.84-0.93;P=.01),数据集2为0.89(IQR 0.80-0.92;P=.001)。
  • 最佳模型基于肿瘤边界框的23个混合特征,AUC 0.90(95%CI: 0.83, 0.97),敏感度81%(46/57;95%CI: 70, 91),特异度87%(39/45;95%CI: 77, 87)。
  • 模型与人类读者分类比较:AUC 0.90(95%CI: 0.83, 0.97)vs 0.83(95%CI: 0.76, 0.90),P=.55;0.90 vs 0.82(95%CI: 0.75, 0.90),P=.45。
  • 模型与病理/随访确诊诊断比较:AUC 0.90(95%CI: 0.83, 0.97)vs 1.00(95%CI: 1.00, 1.00),P=.10。

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

Background US is clinically established for breast imaging, but its diagnostic performance depends on operator experience. Computer-assisted (real-time) image analysis may help in overcoming this limitation. Purpose To develop precise real-time-capable US-based breast tumor categorization by combining classic radiomics and autoencoder-based features from automatically localized lesions. Materials and Methods A total of 1619 B-mode US images of breast tumors were retrospectively analyzed between April 2018 and January 2024. nnU-Net was trained for lesion segmentation. Features were extracted from tumor segments, bounding boxes, and whole images using either classic radiomics, autoencoder, or both. Feature selection was performed to generate radiomics signatures, which were used to train machine learning algorithms for tumor categorization. Models were evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity and were statistically compared with histopathologically or follow-up-confirmed diagnosis. Results The model was developed on 1191 (mean age, 61 years ± 14 [SD]) female patients and externally validated on 50 (mean age, 55 years ± 15]). The development data set was divided into two parts: testing and training lesion segmentation (419 and 179 examinations) and lesion categorization (503 and 90 examinations). nnU-Net demonstrated precision and reproducibility in lesion segmentation in test set of data set 1 (median Dice score [DS]: 0.90 [IQR, 0.84-0.93]; P = .01) and data set 2 (median DS: 0.89 [IQR, 0.80-0.92]; P = .001). The best model, trained with 23 mixed features from tumor bounding boxes, achieved an AUC of 0.90 (95% CI: 0.83, 0.97), sensitivity of 81% (46 of 57; 95% CI: 70, 91), and specificity of 87% (39 of 45; 95% CI: 77, 87). No evidence of difference was found between model and human readers (AUC = 0.90 [95% CI: 0.83, 0.97] vs 0.83 [95% CI: 0.76, 0.90]; P = .55 and 0.90 vs 0.82 [95% CI: 0.75, 0.90]; P = .45) in tumor classification or between model and histopathologically or follow-up-confirmed diagnosis (AUC = 0.90 [95% CI: 0.83, 0.97] vs 1.00 [95% CI: 1.00,1.00]; P = .10). Conclusion Precise real-time US-based breast tumor categorization was developed by mixing classic radiomics and autoencoder-based features from tumor bounding boxes. ClinicalTrials.gov identifier: NCT04976257 Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Bahl in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Magnuska ZA, Roy R, Palmowski M, et al. Combining Radiomics and Autoencoders to Distinguish Benign and Malignant Breast Tumors on US Images. Radiology. 2024. PMID: 39254446. doi:10.1148/radiol.232554

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。