确定可靠的自动脑转移分割的核心MRI序列。
Identifying core MRI sequences for reliable automatic brain metastasis segmentation.
发表日期：2023 Sep 05
作者：
Josef A Buchner, Jan C Peeken, Lucas Etzel, Ivan Ezhov, Michael Mayinger, Sebastian M Christ, Thomas B Brunner, Andrea Wittig, Björn Menze, Claus Zimmer, Bernhard Meyer, Matthias Guckenberger, Nicolaus Andratschke, Rami A El Shafie, Jürgen Debus, Susanne Rogers, Oliver Riesterer, Katrin Schulze, Horst J Feldmann, Oliver Blanck, Constantinos Zamboglou, Konstantinos Ferentinos, Angelika Bilger, Anca L Grosu, Robert Wolff, Jan S Kirschke, Kerstin A Eitz, Stephanie E Combs, Denise Bernhardt, Daniel Rueckert, Marie Piraud, Benedikt Wiestler, Florian Kofler
来源：
Best Pract Res Cl Ob
摘要：
脑肿瘤分割的许多自动化方法采用多种磁共振成像（MRI）序列。本项目的目标是比较不同输入序列的组合，以确定哪些MRI序列对于有效的自动化脑转移（BM）分割是必需的。我们分析了来自七个中心的339名患有BM的术前成像（T1加权序列±增强（T1/T1-CE），T2加权序列（T2）和T2液体衰减反转恢复（T2-FLAIR）序列）。使用所有四个序列的基线3D U-Net和六个具有可行序列组合的U-Net（T1-CE、T1、T2-FLAIR、T1-CE+T2-FLAIR、T1-CE+T1+T2-FLAIR、T1-CE+T1）训练了两个中心的239名患者，并随后在来自五个中心的100名患者的外部队列上进行了测试。仅基于T1-CE的模型在BM分割的性能上表现最佳，平均Dice相似系数（DSC）为0.96。在没有T1-CE训练的模型中，性能较差（仅T1：DSC = 0.70，仅T2-FLAIR：DSC = 0.73）。对于水肿分割，包含T1-CE和T2-FLAIR的模型表现最佳（DSC = 0.93），而其他四个没有同时包括这两个序列的模型的中位DSC为0.81-0.89。 仅使用T1-CE协议就足以进行BM分割。T1-CE和T2-FLAIR的组合对于水肿分割至关重要。缺少T1-CE或T2-FLAIR将降低性能。这些发现可能通过省略不必要的序列来改善成像程序，从而在日常临床实践中实现更快的操作，同时保证最佳的基于神经网络的目标定义。版权所有©2023 Elsevier B.V. 出版。
Many automatic approaches to brain tumor segmentation employ multiple magnetic resonance imaging (MRI) sequences. The goal of this project was to compare different combinations of input sequences to determine which MRI sequences are needed for effective automated brain metastasis (BM) segmentation.We analyzed preoperative imaging (T1-weighted sequence ± contrast-enhancement (T1/T1-CE), T2-weighted sequence (T2), and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequence) from 339 patients with BMs from seven centers. A baseline 3D U-Net with all four sequences and six U-Nets with plausible sequence combinations (T1-CE, T1, T2-FLAIR, T1-CE+T2-FLAIR, T1-CE+T1+T2-FLAIR, T1-CE+T1) were trained on 239 patients from two centers and subsequently tested on an external cohort of 100 patients from five centers.The model based on T1-CE alone achieved the best segmentation performance for BM segmentation with a median Dice similarity coefficient (DSC) of 0.96. Models trained without T1-CE performed worse (T1-only: DSC = 0.70 and T2-FLAIR-only: DSC = 0.73). For edema segmentation, models that included both T1-CE and T2-FLAIR performed best (DSC = 0.93), while the remaining four models without simultaneous inclusion of these both sequences reached a median DSC of 0.81-0.89.A T1-CE-only protocol suffices for the segmentation of BMs. The combination of T1-CE and T2-FLAIR is important for edema segmentation. Missing either T1-CE or T2-FLAIR decreases performance. These findings may improve imaging routines by omitting unnecessary sequences, thus allowing for faster procedures in daily clinical practice while enabling optimal neural network-based target definitions.Copyright © 2023. Published by Elsevier B.V.