文献速递泌尿生殖妇产影像MR

基于基础分割模型与多模态分析的MRI卵巢病变分类:一项多中心研究

MRI-based Ovarian Lesion Classification via a Foundation Segmentation Model and Multimodal Analysis: A Multicenter Study.
PubMed 文献 · Radiology · 2025-01-01

本研究回顾性分析原发机构及两家外部机构的多参数MRI数据集,采用SAM自动分割卵巢病变,并训练DenseNet-121深度学习模型结合影像与临床数据进行良恶性分类。模型内部测试AUC为0.85,外部数据集AUC为0.79,与放射科医师主观评估及O-RADS MRI分类性能相当(AUC 0.84-0.93,所有P > .05),且SAM分割较手动分割每病变节省4分钟。

要点

  • SAM辅助分割Dice系数0.86-0.88,较手动分割每病变减少4分钟处理时间。
  • DL模型内部测试AUC 0.85(95% CI: 0.85, 0.85),外部数据集AUC 0.79(95% CI: 0.79, 0.79和0.78, 0.79)。
  • DL模型与放射科医师(AUC 0.84-0.93)分类性能相当,所有P > .05。

核心结论

  • 整合SAM与深度学习分类的流程可准确、高效地在MRI上鉴别卵巢病变良恶性,减少分割时间且分类性能与放射科医师相当。

研究设计与样本

  • 回顾性研究,原发机构A(美国)534个病变来自448名女性(平均年龄52岁±15),外部机构B(美国)58个病变来自55名女性(平均年龄51岁±19),外部机构C(台湾)29个病变来自29名女性(平均年龄49岁±10);使用Meta的Segment Anything Model(SAM)自动分割,DenseNet-121深度学习模型结合影像与临床数据训练并外部验证。

诊断标准与关键数值

  • SAM辅助分割Dice系数0.86-0.88;DL分类模型内部测试AUC 0.85(95% CI: 0.85, 0.85),外部数据集AUC 0.79(95% CI: 0.79, 0.79和0.78, 0.79);放射科医师使用O-RADS MRI及主观评估分类良恶性,AUC 0.84-0.93,DL模型与医师间所有P > .05。

临床应用与阅片要点

  • 作者指出该流程可减少分割时间并在MRI上区分卵巢病变良恶性,分类性能与放射科医师相当。

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

Background Artificial intelligence may enhance diagnostic accuracy in classifying ovarian lesions on MRI scans; however, its applicability across diverse datasets is uncertain. Purpose To develop an efficient, generalizable pipeline for MRI-based ovarian lesion characterization. Materials and Methods In this retrospective study, multiparametric MRI datasets of patients with ovarian lesions from a primary institution (January 2008 to January 2019) and two external institutions (January 2010 to October 2020) were analyzed. Lesions were automatically segmented using Meta's Segment Anything Model (SAM). A DenseNet-121 deep learning (DL) model incorporating both imaging and clinical data was then trained and validated externally for ovarian lesion classification. Lesions were evaluated by radiologists using the Ovarian-Adnexal Reporting and Data System for MRI and subjective assessment, classifying them as benign or malignant. The classification performances of the DL model and radiologists were compared using the DeLong test. Results The primary dataset included 534 lesions from 448 women (mean age, 52 years ± 15 [SD]) from institution A (United States), whereas the external datasets included 58 lesions from 55 women (mean age, 51 years ± 19) from institution B (United States) and 29 lesions from 29 women (mean age, 49 years ± 10) from institution C (Taiwan). SAM-assisted segmentation had a Dice coefficient of 0.86-0.88, reducing the processing time per lesion by 4 minutes compared with manual segmentation. The DL classification model achieved an area under the receiver operating characteristic curve (AUC) of 0.85 (95% CI: 0.85, 0.85) on the internal test and 0.79 (95% CI: 0.79, 0.79 and 0.78, 0.79) across both external datasets with SAM-segmented images, comparable with the radiologists' performance (AUC: 0.84-0.93; all P > .05). Conclusion These results describe an accurate, efficient pipeline that integrates SAM with DL-based classification for differentiating malignant from benign ovarian lesions on MRI scans. It reduced segmentation time and achieved classification performance comparable with that of radiologists. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Bhayana and Wang in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Hsu WC, Wang Y, Wu YF, et al. MRI-based Ovarian Lesion Classification via a Foundation Segmentation Model and Multimodal Analysis: A Multicenter Study. Radiology. 2025. PMID: 40762846. doi:10.1148/radiol.243412

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。