文献速递腹部MRCT

基于深度学习的非增强T1-Vibe Dixon肝脏MRI自动肝段体积比定量

Automated liver segmental volume ratio quantification on non-contrast T1-Vibe Dixon liver MRI using deep learning.
PubMed 文献 · Eur J Radiol · 2023-08-14

研究用200例非增强3 mm T1-Vibe Dixon肝脏MRI,由专家逐层手动标注Couinaud肝段及门静脉、肝静脉,以卷积神经网络分割肝段并计算肝段体积比(LSVR),结果与专家手动LSVR及CT计算的LSVR比较,自动LSVR与手动MRI LSVR(Spearman r=0.97,p<0.001)及CT LSVR(r=0.95,p<0.001)均显著相关。

要点

  • 卷积神经网络分割Couinaud I-VIII段平均Dice评分0.770±0.03,范围0.726±0.13(IVb段)至0.810±0.09(V段)。
  • 模型未见过的MRI自动LSVR均值0.32±0.14,手动LSVR 0.33±0.15,平均绝对误差0.02。
  • 自动LSVR与手动MRI LSVR(r=0.97)及CT LSVR(r=0.95)均显著相关(p<0.001)。

核心结论

  • 卷积神经网络可基于非增强T1-Vibe Dixon序列实现肝脏各段体积的准确自动定量并计算LSVR。

研究设计与样本

  • 研究纳入200例肝脏MRI非增强3 mm T1-Vibe Dixon序列,由专家逐层手动标注Couinaud肝段并单独标注门静脉和肝静脉,其中170例用于训练卷积神经网络、30例用于评估;在30例6个月内同时有CT和MRI的患者中,将自动LSVR与专家手动LSVR及CT计算的LSVR比较。

诊断标准与关键数值

  • LSVR计算为肝段I-III体积除以肝段IV-VIII体积,体积不含肝血管;卷积神经网络分割Couinaud I-VIII段平均Dice评分0.770±0.03,范围0.726±0.13(IVb段)至0.810±0.09(V段);模型未见MRI自动LSVR均值0.32±0.14,手动LSVR 0.33±0.15,平均绝对误差0.02;CT来源LSVR 0.35±0.14,平均绝对误差0.04;自动LSVR与手动MRI LSVR Spearman r=0.97(p<0.001),与CT LSVR Spearman r=0.95(p<0.001)。

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 evaluate the effectiveness of automated liver segmental volume quantification and calculation of the liver segmental volume ratio (LSVR) on a non-contrast T1-vibe Dixon liver MRI sequence using a deep learning segmentation pipeline.

METHOD: A dataset of 200 liver MRI with a non-contrast 3 mm T1-vibe Dixon sequence was manually labeledslice-by-sliceby an expert for Couinaud liver segments, while portal and hepatic veins were labeled separately. A convolutional neural networkwas trainedusing 170 liver MRI for training and 30 for evaluation. Liver segmental volumes without liver vessels were retrieved and LSVR was calculated as the liver segmental volumes I-III divided by the liver segmental volumes IV-VIII. LSVR was compared with the expert manual LSVR calculation and the LSVR calculated on CT scans in 30 patients with CT and MRI within 6 months.

RESULTS: Theconvolutional neural networkclassified the Couinaud segments I-VIII with an average Dice score of 0.770 ± 0.03, ranging between 0.726 ± 0.13 (segment IVb) and 0.810 ± 0.09 (segment V). The calculated mean LSVR with liver MRI unseen by the model was 0.32 ± 0.14, as compared with manually quantified LSVR of 0.33 ± 0.15, resulting in a mean absolute error (MAE) of 0.02. A comparable LSVR of 0.35 ± 0.14 with a MAE of 0.04 resulted with the LSRV retrieved from the CT scans. The automated LSVR showed significant correlation with the manual MRI LSVR (Spearman r = 0.97, p < 0.001) and CT LSVR (Spearman r = 0.95, p < 0.001).

CONCLUSIONS: A convolutional neural network allowed for accurate automated liver segmental volume quantification and calculation of LSVR based on a non-contrast T1-vibe Dixon sequence.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zbinden L, Catucci D, Suter Y, et al. Automated liver segmental volume ratio quantification on non-contrast T1-Vibe Dixon liver MRI using deep learning. Eur J Radiol. 2023. PMID: 37690351. doi:10.1016/j.ejrad.2023.111047

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。