对比增强乳腺X线摄影影像组学:多厂商数据集模型准确性与分割技术比较
本研究基于Hologic与GE设备的对比增强乳腺X线摄影图像,对269个强化肿块病灶提取纹理特征并构建良恶性分类模型。椭球ROI分割模型准确率高于徒手ROI(0.947 vs 0.914,AUC 0.974 vs 0.86,p<0.05)。CC位模型特异度最高(0.962),MLO位及CC+MLO位模型敏感度较高(0.954,p<0.05);同时使用两个体位准确率提升有限,可能不值得增加工作量。
要点
- 椭球ROI分割构建的影像组学模型良恶性分类准确率高于徒手ROI分割。
- CC位模型特异度最高(0.962),MLO位及CC+MLO位模型敏感度较高(0.954)。
- 同时分割CC与MLO两个体位对准确率提升有限,可能不必增加工作量。
核心结论
- 基于多厂商对比增强乳腺X线摄影数据集可构建高准确率的影像组学良恶性分类模型,椭球ROI分割准确率最高。
- 同时使用CC与MLO两个体位带来的准确率提升有限,可能不足以抵消增加的工作量。
研究设计与样本
- 研究纳入269个强化肿块病灶(238例患者),使用Hologic与GE设备采集的对比增强乳腺X线摄影图像。
- 采用MaZda分析软件提取纹理特征,分别以徒手ROI和椭球ROI分割病灶,构建良恶性分类模型,并按ROI和乳腺摄影体位进行亚组分析。
诊断标准与关键数值
- 椭球ROI分割模型与徒手ROI分割模型比较:准确率0.947 vs 0.914,AUC 0.974 vs 0.86,p<0.05。
- 各体位模型准确率0.947–0.955,AUC 0.985–0.987,组间AUC无差异。
- CC位模型特异度最高为0.962;MLO位及CC+MLO位模型敏感度较高为0.954,p<0.05。
临床应用与阅片要点
- 在对比增强乳腺X线摄影影像组学分析中,优先采用椭球ROI分割以提高良恶性分类准确率。
- 可考虑仅使用单一CC位或MLO位图像建模以减少分割工作量,两体位联合的准确率提升有限。
局限性
- 原文未明确报告研究是否为单中心或回顾性设计等具体局限。
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
OBJECTIVE: Radiomic analysis of contrast-enhanced mammographic (CEM) images is an emerging field. The aims of this study were to build classification models to distinguish benign and malignant lesions using a multivendor data set and compare segmentation techniques.
METHODS: CEM images were acquired using Hologic and GE equipment. Textural features were extracted using MaZda analysis software. Lesions were segmented with freehand region of interest (ROI) and ellipsoid_ROI. Benign/Malignant classification models were built using extracted textural features. Subset analysis according to ROI and mammographic view was performed.
RESULTS: 269 enhancing mass lesions (238 patients) were included. Oversampling mitigated benign/malignant imbalance. Diagnostic accuracy of all models was high (>0.9). Segmentation with ellipsoid_ROI produced a more accurate model than with FH_ROI, accuracy:0.947 vs 0.914, AUC:0.974 vs 0.86, p < 0.05. Regarding mammographic view all models were highly accurate (0.947-0.955) with no difference in AUC (0.985-0.987). The CC-view model had the greatest specificity:0.962, the MLO-view and CC + MLO view models had higher sensitivity:0.954, p < 0.05.
CONCLUSIONS: Accurate radiomics models can be built using a real-life multivendor data set segmentation with ellipsoid-ROI produces the highest level of accuracy. The marginal increase in accuracy using both mammographic views, may not justify the increased workload.
ADVANCES IN KNOWLEDGE: Radiomic modelling can be successfully applied to a multivendor CEM data set, ellipsoid_ROI is an accurate segmentation technique and it may be unnecessary to segment both CEM views. These results will help further developments aimed at producing a widely accessible radiomics model for clinical use.
引用
- Savaridas, Agrawal, Fagbamigbe, et al. Radiomic analysis in contrast-enhanced mammography using a multivendor data set: accuracy of models according to segmentation techniques. Br J Radiol. 2023. PMID: 36802982. doi:10.1259/bjr.20220980
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。