基于深度学习在眼眶CT图像中全自动分割眼球进行体积量化
研究提出基于深度学习的卷积神经网络(MRes-UNET2D)自动预测眼眶CT图像中的眼球轮廓并量化体积,在80例无眼球损伤受试者的轴位CT上训练,在两个测试队列中与人工标注比较,Dice达0.95,体积误差5.3%,模型与真实值中位体积无显著差异(P=.72),模型Dice(0.95)接近人类观察者间一致性(Dice=0.94)。
要点
- MRes-UNET2D在眼眶CT上自动分割眼球轮廓,测试队列平均Dice为0.95、精确率96%、召回率95%。
- 平均95% Hausdorff距离仅1.5 mm,眼球体积估计误差5.3%。
- 模型与真实值中位眼球体积无统计学显著差异(P=.72),模型Dice=0.95接近人类观察者间Dice=0.94。
核心结论
- 基于深度学习的MRes-UNET2D可快速预测眼眶CT图像中的眼球轮廓并量化体积,在多种采集参数下能可靠检测和量化眼球体积。
研究设计与样本
- 研究使用基于深度学习的卷积神经网络MRes-UNET2D,在80例无影像或临床眼球损伤表现的受试者轴位CT图像上训练。
- 预测的眼球轮廓和体积估计在两个不同测试队列中与经验丰富的观察者手工标注进行比较。
- 第一测试队列n=18,第二测试队列n=9,后者由1名神经放射科医生和2名住院医师独立标记眼球轮廓。
关键影像表现/征象
- 模型预测的眼球轮廓与手工标注高度一致,第一测试队列平均Dice为0.95。
- 第一测试队列平均精确率为96%,平均召回率为95%。
- 第一测试队列平均95% Hausdorff距离仅1.5 mm。
- 第一测试队列眼球体积估计误差为5.3%。
- 模型与真实值的中位眼球体积估计无统计学显著差异(P=.72)。
诊断标准与关键数值
- 第一测试队列(n=18)平均Dice为0.95、精确率96%、召回率95%,平均95% Hausdorff距离1.5 mm,眼球体积估计误差5.3%。
- 模型与真实值中位眼球体积估计无统计学显著差异(P=.72)。
- 第二测试队列(n=9)中MRes-UNET2D的Dice为0.95,接近人类观察者间变异Dice=0.94。
- 在3例已知眼球损伤受试者中展示了眼球间体积差作为创伤定量标记的效用。
临床应用与阅片要点
- 原文结论指出,MRes-UNET2D预测快速,可在多种采集参数下可靠检测和量化眼眶CT图像中的眼球体积。
- 原文在3例已知眼球损伤受试者中展示了眼球间体积差作为创伤定量标记的效用,作者未据此给出临床推荐。
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 AND PURPOSE: Fast and accurate quantification of globe volumes in the event of an ocular trauma can provide clinicians with valuable diagnostic information. In this work, an automated workflow using a deep learning-based convolutional neural network is proposed for prediction of globe contours and their subsequent volume quantification in CT images of the orbits.
MATERIALS AND METHODS: An automated workflow using a deep learning -based convolutional neural network is proposed for prediction of globe contours in CT images of the orbits. The network, 2D Modified Residual UNET (MRes-UNET2D), was trained on axial CT images from 80 subjects with no imaging or clinical findings of globe injuries. The predicted globe contours and volume estimates were compared with manual annotations by experienced observers on 2 different test cohorts.
RESULTS: On the first test cohort (n = 18), the average Dice, precision, and recall scores were 0.95, 96%, and 95%, respectively. The average 95% Hausdorff distance was only 1.5 mm, with a 5.3% error in globe volume estimates. No statistically significant differences (P = .72) were observed in the median globe volume estimates from our model and the ground truth. On the second test cohort (n = 9) in which a neuroradiologist and 2 residents independently marked the globe contours, MRes-UNET2D (Dice = 0.95) approached human interobserver variability (Dice = 0.94). We also demonstrated the utility of inter-globe volume difference as a quantitative marker for trauma in 3 subjects with known globe injuries.
CONCLUSIONS: We showed that with fast prediction times, we can reliably detect and quantify globe volumes in CT images of the orbits across a variety of acquisition parameters.
引用
- Umapathy L, Winegar B, MacKinnon L, et al. Fully Automated Segmentation of Globes for Volume Quantification in CT Images of Orbits using Deep Learning. AJNR Am J Neuroradiol. 2020. PMID: 32439637. doi:10.3174/ajnr.A6538
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。