文献速递妇产影像泌尿生殖技术与安全US

基于Transformer的超声影像组学用于卵巢肿瘤新型多任务自动分割与分类

Transformer-based ultrasound radiomics for novel multi-task automated segmentation and classification of ovarian tumors.
PubMed 文献 · Abdom Radiol (NY) · 2025-11-18

本研究为多中心回顾性研究,纳入4个临床中心1907例患者的超声数据,其中1364例用于模型训练与验证、543例用于外部测试,开发并评估基于Transformer模型和影像组学分析的AI流程,用于卵巢肿瘤超声图像的自动分割与多分类。SegFormer分割最准确(平均DSC>91%),TabTransformer结合互信息特征选择在所有分类任务中测试准确率最高(肿瘤类型92.7%、组织学亚型92.1%、FIGO分期92.0%),外部测试准确率均超过90%。

要点

  • SegFormer分割最准确,平均DSC>91%,高于既往U-Net类模型。
  • TabTransformer结合互信息特征选择在肿瘤类型、组织学亚型、FIGO分期分类中测试准确率最高。
  • 外部测试各任务准确率均超过90%,不同中心和成像条件间性能无差异。

核心结论

  • 所提出的流程在基于超声影像的卵巢癌自动诊断中表现出很高的准确性、泛化性和可解释性,为临床实施及未来多模态数据应用提供了有力框架。

研究设计与样本

  • 多中心回顾性研究,纳入4个临床中心1907例患者的超声数据,其中1364例用于模型训练与验证、543例用于外部测试;采用SegFormer、Swin-UNet、DPT、nnU-Net、HRFormer五种Transformer分割模型,影像组学特征(n=215)经SERA平台按IBSI指南提取,特征选择采用互信息、LASSO和递归特征消除,分类模型为TabTransformer、TabNet、MLP、XGBoost和KAN,采用五折交叉验证和外部测试,SHAP分析提供可解释性。

诊断标准与关键数值

  • 分割准确性以DSC、HD和RAVD衡量,SegFormer平均DSC>91%;分类任务测试准确率:TabTransformer(互信息特征选择)肿瘤类型92.7%、组织学亚型92.1%、FIGO分期92.0%,外部测试各任务准确率均超过90%。

临床应用与阅片要点

  • SHAP分析可展示影响分类决策的重要影像组学特征,使分类过程具有临床透明度;不同中心和成像条件间性能无差异。

局限性

  • 原文未报告局限性

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: To develop and evaluate a comprehensive AI-driven pipeline for automated segmentation and multi-class classification of ovarian tumors in ultrasound images using advanced transformer-based models and radiomic analysis.

MATERIALS AND METHODS: The study was a multi-center, retrospective study that included ultrasound data of 1,907 patients in 4 clinical centers, with 1,364 patients being used as a model training and validation and 543 as an external test. Five transformer-based segmentation models were used to outline tumour regions namely SegFormer, Swin-UNet, DPT, nnU-Net and HRFormer. Dice Similarity Coefficient (DSC), Hausdorff Distance (HD) and Relative Absolute Volume Difference (RAVD) were used to measure segmentation accuracy. Radiomic features (n = 215) were taken out through SERA platform, following the IBSI instructions. Mutual Information (MI), LASSO and Recursive Feature Elimination (RFE) were used as feature selection methods. Five models were considered to classify them: TabTransformer, TabNet, MLP, XGBoost, and KAN. Three clinically significant classification tasks, including tumour type, histological subtype, and FIGO staging, were covered. The models were checked by five-fold cross-validation and externally tested. SHAP analysis delivered interpretability.

RESULTS: SegFormer was found to be the most accurate in terms of segmentation (mean DSC > 91%), which is higher than other U-Net-based models in earlier research. To classify, the TabTransformer selected by MI had the highest test accuracies in all tasks: tumour type (92.7 per cent.), histological subtype (92.1 per cent.), and FIGO stage (92.0 per cent). The accuracy of the external tests was over 90 per cent in all the tasks. SHAP analysis demonstrated the important radiomic features that make classification decisions, which is clinically transparent. There was no difference in performance between centers and imaging conditions.

CONCLUSIONS: The suggested pipeline proves to be very accurate, general and interpretable in automated ovarian cancer diagnostics based on ultrasound imaging. It provides a powerful framework of clinical implementation and future application with multimodal data to support decisions better.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Mutee AF, Al-Hussainy AF, Ibrahim NA, et al. Transformer-based ultrasound radiomics for novel multi-task automated segmentation and classification of ovarian tumors. Abdom Radiol (NY). 2025. PMID: 41251739. doi:10.1007/s00261-025-05295-y

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。