文献速递妇产影像腹部MR

多方位磁共振成像辅助深度学习检测与分割子宫肌瘤

Deep learning assisted detection and segmentation of uterine fibroids using multi-orientation magnetic resonance imaging.
PubMed 文献 · Abdom Radiol (NY) · 2025-04-05

本研究基于三维nnU-Net框架,利用治疗前矢状位和轴位T2加权MRI开发深度学习模型,自动检测和分割子宫肌瘤。内部测试集60例中,矢状位/轴位模型检测召回率分别为74.4%/76.4%,精确率98.9%/97.9%;对≥4 cm肌瘤召回率达93.7%/95.3%。分割平均DSC内部测试集为0.789/0.804,外部测试集为0.834/0.818。

要点

  • 对≥4 cm肌瘤检测召回率达93.7%/95.3%,对FIGO 2-5型达100%。
  • 分割性能平均DSC内部测试集0.789/0.804,外部测试集0.834/0.818。

核心结论

  • 所提出的深度学习模型在自动化检测和分割子宫肌瘤方面显示出潜力,尤其是具有临床意义的肌瘤。

研究设计与样本

  • 回顾性收集治疗前矢状位和轴位T2加权MRI,基于三维nnU-Net框架构建分割模型;内部数据集299例(训练集239例,内部测试集60例),外部数据集45例;评估检测效能并按大小和位置进行亚组分析。

诊断标准与关键数值

  • 内部测试集矢状位/轴位T2WI模型检测肌瘤召回率74.4%/76.4%,精确率98.9%/97.9%。
  • 对≥4 cm肌瘤,矢状位/轴位模型召回率93.7%/95.3%。
  • FIGO 2-5型召回率100%/100%,FIGO 0/1/2型(黏膜下)73.3%/78.6%,FIGO 5/6/7型(浆膜下)80.3%/81.9%。
  • 内部测试集分割平均DSC 0.789/0.804,HD95 9.996/10.855 mm,ASD 2.035/2.115 mm。
  • 外部测试集分割平均DSC 0.834/0.818,HD95 9.971/11.874 mm,ASD 2.031/2.273 mm。

临床应用与阅片要点

  • 模型对FIGO 2-5型肌瘤检测召回率达100%,阅片时可参考其高敏感提示。
  • 对黏膜下(FIGO 0/1/2型)肌瘤召回率约73.3%-78.6%,仍需人工仔细复核。

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

PURPOSE: To develop deep learning models for automated detection and segmentation of uterine fibroids using multi-orientation MRI.

METHODS: Pre-treatment sagittal and axial T2-weighted MRI scans acquired from patients diagnosed with uterine fibroids were collected. The proposed segmentation models were constructed based on the three-dimensional nnU-Net framework. Fibroid detection efficacy was assessed, with subgroup analyses by size and location. The segmentation performance was evaluated using Dice similarity coefficients (DSCs), 95% Hausdorff distance (HD95), and average surface distance (ASD).

RESULTS: The internal dataset comprised 299 patients who were divided into the training set (n = 239) and the internal test set (n = 60). The external dataset comprised 45 patients. The sagittal T2WI model and the axial T2WI model demonstrated recalls of 74.4%/76.4% and precision of 98.9%/97.9% for fibroid detection in the internal test set. The models achieved recalls of 93.7%/95.3% for fibroids ≥ 4 cm. The recalls for International Federation of Gynecology and Obstetrics (FIGO) type 2-5, FIGO types 0\1\2(submucous), fibroids FIGO types 5\6\7(subserous) were 100%/100%, 73.3%/78.6%, and 80.3%/81.9%, respectively. The proposed models demonstrated good performance in segmentation of the uterine fibroids with mean DSCs of 0.789 and 0.804, HD95s of 9.996 and 10.855 mm, and ASDs of 2.035 and 2.115 mm in the internal test set, and with mean DSCs of 0.834 and 0.818, HD95s of 9.971 and 11.874 mm, and ASDs of 2.031 and 2.273 mm in the external test set.

CONCLUSION: The proposed deep learning models showed promise as reliable methods for automating the detection and segmentation of the uterine fibroids, particularly those of clinical relevance.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Liu XY, Yuan ZL, Cong FZ, et al. Deep learning assisted detection and segmentation of uterine fibroids using multi-orientation magnetic resonance imaging. Abdom Radiol (NY). 2025. PMID: 40188260. doi:10.1007/s00261-025-04934-8

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。