文献速递泌尿生殖与妇科肿瘤放疗放疗物理与技术

深度学习在前列腺癌放疗MRI尿路危及器官分割中的几何评估

Geometric evaluation of a deep learning method for segmentation of urinary OARs on magnetic resonance imaging for prostate cancer radiotherapy.
PubMed 文献 · Clin Transl Radiat Oncol · 2025-12-05

本研究提出基于nnU-Net的深度学习模型,用于前列腺癌放疗中MRI上尿路危及器官(如前列腺内尿道和膀胱三角)的分割,并在三个多中心数据集上训练和验证。结果显示大器官如膀胱分割效果好(平均DSC约0.95),而尿路危及器官分割的DSC在0.50至0.68之间,需进一步评估剂量学影响。

要点

  • nnU-Net模型在多中心MRI数据集上分割尿路危及器官,总体平均DSC为0.88。
  • 膀胱等大器官分割效果好(平均DSC约0.95),尿路危及器官DSC为0.50–0.68。
  • 尿路危及器官表面距离为1.0–1.3 mm,但Hausdorff距离达4.0–10.3 mm。

核心结论

  • 本研究首次提出基于nnU-Net的深度学习模型用于尿路危及器官分割,可应用于多种图像数据集。
  • 尿路危及器官的自动分割几何精度中等,需进一步评估剂量学影响。

研究设计与样本

  • 多中心研究,训练和验证三个MRI数据集,两个来自MR-linac设备(Unity® Elekta和MRIdian® Viewray),一个来自PROSTATEx数据库(MAGNETOM® Trio和Skyra Siemens)。
  • 使用卷积神经网络nnU-Net进行图像分割,共分析265例MRI。

主要发现

  • 所有尿路结构的平均DSC为0.88。
  • 自动分割模型对靶区和膀胱等大器官有效,膀胱平均DSC约0.95。
  • 尿路危及器官的平均DSC在0.50至0.68之间。
  • 尿路危及器官的Hausdorff距离在4.0 mm至10.3 mm之间,提示患者间解剖变异导致局部不匹配。
  • 尿路危及器官的表面距离在1.0 mm至1.3 mm之间,提示所有器官整体表面相关性良好。

临床怎么用

  • 该模型可用于前列腺癌放疗MRI上尿路危及器官的自动分割,但需注意其几何精度中等。
  • 临床应用中应关注尿路危及器官分割的局部不匹配,必要时进行人工校正。

局限性

  • 需进一步评估这些分割变异在不同临床场景下的剂量学影响。

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)。

原文

INTRODUCTION: While urinary organs at risk (OARs) such as the intraprostatic urethra and the bladder trigone are increasingly recognized as associated with severe genitourinary toxicity, their delineation in clinical practice is time consuming and probably associated with a large interobserver variability. The aim of this study was to propose a magnetic resonance (MR) deep learning segmentation of urinary OARs for prostate cancer (PCa) radiotherapy (RT), based on a validated atlas. MATERIAL AND METHODS: In this multicentric study, a convolutional neural network (CNN) for image segmentation (nnU-Net) was trained and validated on three image datasets. Two datasets came from MR-linac devices (Unity®, Elekta and MRIdian®, Viewray), and one dataset came from the PROSTATEx database (MAGNETOM® Trio and Skyra, Siemens). Evaluation of the deep learning segmentation was performed using dice score coefficients (DSC), surface distance (SD) and Hausdorff distance. RESULTS: A total of 265 MRI were analyzed. The mean DSC for all urinary structures was 0.88. The automatic segmentation model proved to be effective in the segmentation of the target volume and large OARs such as the bladder (mean DSC ranging of 0.95). Regarding urinary OARs, the mean DSC ranged between 0.50 and 0.68. The Hausdorff distance ranged between 4.0 mm to 10.3 mm for urinary OARs, highlighting local mismatches caused by large anatomical variations between patients. However, the SD ranged between 1.0 mm and 1.3 mm for urinary OARs, highlighting an overall good surface correlation for all organs. CONCLUSION: This multicentric study is the first to propose a nnU-Net deep learning model for the delineation of urinary OARs, that can be applied to various image dataset. Further work is needed to assess the dosimetric impact of such variations, in various clinical scenarios.

来源:Clin Transl Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Le Guévelou J, Castro M, Texier B, et al. Geometric evaluation of a deep learning method for segmentation of urinary OARs on magnetic resonance imaging for prostate cancer radiotherapy. Clin Transl Radiat Oncol. 2025. PMID: 41458146. doi:10.1016/j.ctro.2025.101091

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。