Danish Research Center for Magnetic Resonance, Center for Functional and Diagnostic Imaging and Research, Copenhagen University Hospital-Amager and Hvidovre, Kattegaard Alle 30, Hvidovre, Denmark.
Danish Research Center for Magnetic Resonance, Center for Functional and Diagnostic Imaging and Research, Copenhagen University Hospital-Amager and Hvidovre, Kattegaard Alle 30, Hvidovre, Denmark.
Comput Methods Programs Biomed. 2024 Mar;245:108008. doi: 10.1016/j.cmpb.2024.108008. Epub 2024 Jan 10.
Reliable detection of white matter hyperintensities (WMH) is crucial for studying the impact of diffuse white-matter pathology on brain health and monitoring changes in WMH load over time. However, manual annotation of 3D high-dimensional neuroimages is laborious and can be prone to biases and errors in the annotation procedure. In this study, we evaluate the performance of deep learning (DL) segmentation tools and propose a novel volumetric segmentation model incorporating self-attention via a transformer-based architecture. Ultimately, we aim to evaluate diverse factors that influence WMH segmentation, aiming for a comprehensive analysis of the state-of-the-art algorithms in a broader context.
We trained state-of-the-art DL algorithms, and incorporated advanced attention mechanisms, using structural fluid-attenuated inversion recovery (FLAIR) image acquisitions. The anatomical MRI data utilized for model training was obtained from healthy individuals aged 62-70 years in the Live active Successful Aging (LISA) project. Given the potential sparsity of lesion volume among healthy aging individuals, we explored the impact of incorporating a weighted loss function and ensemble models. To assess the generalizability of the studied DL models, we applied the trained algorithm to an independent subset of data sourced from the MICCAI WMH challenge (MWSC). Notably, this subset had vastly different acquisition parameters compared to the LISA dataset used for training.
Consistently, DL approaches exhibited commendable segmentation performance, achieving the level of inter-rater agreement comparable to expert performance, ensuring superior quality segmentation outcomes. On the out of sample dataset, the ensemble models exhibited the most outstanding performance.
DL methods generally surpassed conventional approaches in our study. While all DL methods performed comparably, incorporating attention mechanisms could prove advantageous in future applications with a wider availability of training data. As expected, our experiments indicate that the use of ensemble-based models enables the superior generalization in out-of-distribution settings. We believe that introducing DL methods in the WHM annotation workflow in heathy aging cohorts is promising, not only for reducing the annotation time required, but also for eventually improving accuracy and robustness via incorporating the automatic segmentations in the evaluation procedure.
可靠地检测脑白质高信号（WMH）对于研究弥漫性脑白质病变对大脑健康的影响以及监测 WM 负荷随时间的变化至关重要。然而，3D 高维神经图像的手动标注既繁琐，又容易在标注过程中产生偏差和错误。在这项研究中，我们评估了深度学习（DL）分割工具的性能，并提出了一种新的基于变压器架构的包含自注意力的容积分割模型。最终，我们旨在评估影响 WMH 分割的多种因素，旨在更全面地分析更广泛背景下的最新算法。
我们使用结构液体衰减反转恢复（FLAIR）图像采集来训练最先进的 DL 算法，并结合先进的注意力机制。模型训练使用的解剖 MRI 数据来自“长寿积极老龄化（LISA）”项目中 62-70 岁的健康个体。鉴于健康衰老个体中病变体积可能稀疏，我们探讨了纳入加权损失函数和集成模型的影响。为了评估所研究的 DL 模型的泛化能力，我们将经过训练的算法应用于源自 MICCAI WMH 挑战赛（MWSC）的独立数据集。值得注意的是，与用于训练的 LISA 数据集相比，该数据集的采集参数差异很大。
一致地，DL 方法表现出出色的分割性能，达到了与专家表现相当的组内一致性水平，确保了高质量的分割结果。在样本外数据集上，集成模型表现出最出色的性能。
在我们的研究中，DL 方法通常优于传统方法。虽然所有的 DL 方法表现相当，但在未来的应用中，引入注意力机制可能会在有更多训练数据的情况下具有优势。正如预期的那样，我们的实验表明，在离群数据设置下，使用基于集成的模型可以实现更好的泛化。我们相信，在健康老龄化队列的 WMH 注释工作流程中引入 DL 方法不仅可以减少注释所需的时间，而且还可以通过将自动分割纳入评估过程来最终提高准确性和稳健性。
