Thomas Marie Franziska, Kofler Florian, Grundl Lioba, Finck Tom, Li Hongwei, Zimmer Claus, Menze Björn, Wiestler Benedikt
From the Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, Technical University of Munich, Munich.
Image-Based Biomedical Modeling, Chair for Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, Garching.
Invest Radiol. 2022 Mar 1;57(3):187-193. doi: 10.1097/RLI.0000000000000828.
Although automated glioma segmentation holds promise for objective assessment of tumor biology and response, its routine clinical use is impaired by missing sequences, for example, due to motion artifacts. The aim of our study was to develop and validate a generative adversarial network for synthesizing missing sequences to allow for a robust automated segmentation.
Our model was trained on data from The Cancer Imaging Archive (n = 238 WHO II-IV gliomas) to synthesize either missing FLAIR, T2-weighted, T1-weighted (T1w), or contrast-enhanced T1w images from available sequences, using a novel tumor-targeting loss to improve synthesis of tumor areas. We validated performance in a test set from both the REMBRANDT repository and our local institution (n = 68 WHO II-IV gliomas), using qualitative image appearance metrics, but also segmentation performance with state-of-the-art segmentation models. Segmentation of synthetic images was compared with 2 commonly used strategies for handling missing input data, entering a blank mask or copying an existing sequence.
Across tumor areas and missing sequences, synthetic images generally outperformed both conventional approaches, in particular when FLAIR was missing. Here, for edema and whole tumor segmentation, we improved the Dice score, a common metric for evaluation of segmentation performance, by 12% and 11%, respectively, over the best conventional method. No method was able to reliably replace missing contrast-enhanced T1w images.
Replacing missing nonenhanced magnetic resonance sequences via synthetic images significantly improves segmentation quality over most conventional approaches. This model is freely available and facilitates more widespread use of automated segmentation in routine clinical use, where missing sequences are common.
尽管自动胶质瘤分割有望实现对肿瘤生物学特性和反应的客观评估，但其在常规临床应用中会因序列缺失（例如由于运动伪影）而受到影响。我们研究的目的是开发并验证一种生成对抗网络，用于合成缺失序列，以实现可靠的自动分割。
我们的模型使用来自癌症影像存档（n = 238例世界卫生组织II-IV级胶质瘤）的数据进行训练，通过一种新颖的肿瘤靶向损失来改善肿瘤区域的合成，从而从可用序列中合成缺失的液体衰减反转恢复（FLAIR）、T2加权、T1加权（T1w）或对比增强T1w图像。我们使用定性图像外观指标以及与最先进的分割模型进行分割性能验证，在来自伦勃朗数据库和我们本地机构的测试集（n = 68例世界卫生组织II-IV级胶质瘤）中进行验证。将合成图像的分割与处理缺失输入数据的两种常用策略进行比较，即输入空白掩码或复制现有序列。
在肿瘤区域和缺失序列方面，合成图像总体上优于两种传统方法，尤其是在FLAIR序列缺失时。在此情况下，对于水肿和全肿瘤分割，我们分别比最佳传统方法将常用的分割性能评估指标Dice分数提高了12%和11%。没有方法能够可靠地替代缺失的对比增强T1w图像。
通过合成图像替代缺失的非增强磁共振序列，与大多数传统方法相比，显著提高了分割质量。该模型可免费获取，有助于在常规临床应用中更广泛地使用自动分割，因为在常规临床应用中序列缺失很常见。
