文献速递头颈部肿瘤放疗放疗物理与技术

基于磁共振成像的新型半监督学习框架在鼻咽癌大体肿瘤体积自动勾画中的验证

Automatic Delineation of Gross Tumor Volume Based on Magnetic Resonance Imaging by Performing a Novel Semisupervised Learning Framework in Nasopharyngeal Carcinoma.
PubMed 文献 · Int J Radiat Oncol Biol Phys · 2022-04-03

本研究验证了一种新型半监督学习框架在鼻咽癌大体肿瘤体积(GTV)勾画中的准确性和临床价值。258例磁共振数据分为训练180例、验证20例、测试58例,模型生成轮廓与真实轮廓的平均DSC在GTVnx为0.83、GTVnd为0.80。9名专家对模型轮廓的平均修正度在GTVnx有19例(95%)低于10%,在GTVnd有16例(80%)低于10%;6名低年资肿瘤医生借助模型后,GTVnx和GTVnd的平均修正度分别从25.63%降至7.75%和从21.38%降至14.44%,勾画效率提高超过60%。

要点

  • 模型生成轮廓与真实轮廓的平均DSC在GTVnx为0.83、GTVnd为0.80。
  • T1-2与T3-4患者DSC无显著差异(0.81 vs 0.83;P = .223)。
  • 借助模型,低年资医生GTVnx平均修正度从25.63%降至7.75%,GTVnd从21.38%降至14.44%,效率提高超过60%。

核心结论

  • 所提出的基于半监督学习的模型对鼻咽癌GTV勾画显示出高准确性,具有临床适用性,可帮助低年资肿瘤医生提高GTV勾画准确性并节省勾画时间。

研究设计与样本

  • 258例磁共振数据集分为训练组180例、验证组20例和测试组58例。
  • 鼻咽GTV(GTVnx)和淋巴结GTV(GTVnd)的真实轮廓由2名经验丰富的放射肿瘤医生手动勾画。
  • 使用20%(36例)标注图像和80%(144例)未标注图像训练模型,为测试组患者生成模型轮廓。
  • 邀请9名经验丰富的专家对测试组中随机选取的20例患者的模型生成GTV进行修正。
  • 要求6名低年资肿瘤医生对测试组中随机选取的12例患者分别在不借助和借助模型辅助两种模式下勾画GTV,并比较修正度。

主要发现

  • 模型生成轮廓与真实轮廓相比,GTVnx和GTVnd的平均DSC分别为0.83和0.80。
  • T1-2与T3-4患者之间DSC无显著差异(0.81 vs 0.83;P = .223)。
  • N1-2与N3患者之间DSC无显著差异(0.80 vs 0.79;P = .807)。
  • 专家修正中,GTVnx平均修正度低于10%的患者有19例(95%),GTVnd有16例(80%)。
  • 借助模型辅助,低年资医生对GTVnx的平均修正度从25.63%降至7.75%,对GTVnd从21.38%降至14.44%,同时勾画效率提高超过60%。

关键数值与推荐

  • 采用Dice相似系数(DSC)量化模型准确性,GTVnx平均DSC为0.83,GTVnd为0.80。
  • T1-2与T3-4患者DSC分别为0.81和0.83(P = .223),N1-2与N3患者DSC分别为0.80和0.79(P = .807)。
  • 专家修正中GTVnx平均修正度低于10%的患者比例为19例(95%),GTVnd为16例(80%)。
  • 低年资医生不借助模型与借助模型时,GTVnx平均修正度分别为25.63%和7.75%,GTVnd分别为21.38%和14.44%。

临床怎么用

  • 原文结论认为该模型具有临床适用性,可帮助低年资肿瘤医生提高GTV勾画准确性并节省勾画时间。

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)。

原文

PURPOSE: We aimed to validate the accuracy and clinical value of a novel semisupervised learning framework for gross tumor volume (GTV) delineation in nasopharyngeal carcinoma. METHODS AND MATERIALS: Two hundred fifty-eight patients with magnetic resonance imaging data sets were divided into training (n = 180), validation (n = 20), and testing (n = 58) cohorts. Ground truth contours of nasopharynx GTV (GTVnx) and node GTV (GTVnd) were manually delineated by 2 experienced radiation oncologists. Twenty percent (n = 36) labeled and 80% (n = 144) unlabeled images were used to train the model, producing model-generated contours for patients from the testing cohort. Nine experienced experts were invited to revise model-generated GTV in 20 randomly selected patients from the testing cohort. Six junior oncologists were asked to delineate GTV in 12 randomly selected patients from the testing cohort without and with the assistance of the model, and revision degrees were compared under these 2 modes. The Dice similarity coefficient (DSC) was used to quantify the accuracy of the model. RESULTS: The model-generated contours showed a high accuracy compared with ground truth contours, with an average DSC score of 0.83 and 0.80 for GTVnx and GTVnd, respectively. There was no significant difference in DSC score between T1-2 and T3-4 patients (0.81 vs 0.83; P = .223), or between N1-2 and N3 patients (0.80 vs 0.79; P = .807). The mean revision degree was lower than 10% in 19 (95%) patients for GTVnx and in 16 (80%) patients for GTVnd. With assistance of the model, the mean revision degree for GTVnx and GTVnd by junior oncologists was reduced from 25.63% to 7.75% and from 21.38% to 14.44%, respectively. Meanwhile, the delineating efficiency was improved by over 60%. CONCLUSIONS: The proposed semisupervised learning-based model showed a high accuracy for delineating GTV of nasopharyngeal carcinoma. It was clinically applicable and could assist junior oncologists to improve GTV contouring accuracy and save contouring time.

来源:Int J Radiat Oncol Biol Phys,查看原文。版权归原作者所有。

引用

  1. Liao W, He J, Luo X, et al. Automatic Delineation of Gross Tumor Volume Based on Magnetic Resonance Imaging by Performing a Novel Semisupervised Learning Framework in Nasopharyngeal Carcinoma. Int J Radiat Oncol Biol Phys. 2022. PMID: 35381322. doi:10.1016/j.ijrobp.2022.03.031

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。