Department of Radiology, Stanford University School of Medicine, Stanford, California, USA.
Department of Neurosurgery, Stanford University School of Medicine, Stanford, California, USA.
World Neurosurg. 2024 Aug;188:35-44. doi: 10.1016/j.wneu.2024.04.145. Epub 2024 Apr 27.
Vestibular schwannomas (VSs) are benign tumors often monitored over time, with measurement techniques for assessing growth rates subject to significant interobserver variability. Automatic segmentation of these tumors could provide a more reliable and efficient for tracking their progression, especially given the irregular shape and growth patterns of VS.
Various studies and segmentation techniques employing different Convolutional Neural Network architectures and models, such as U-Net and convolutional-attention transformer segmentation, were analyzed. Models were evaluated based on their performance across diverse datasets, and challenges, including domain shift and data sharing, were scrutinized.
Automatic segmentation methods offer a promising alternative to conventional measurement techniques, offering potential benefits in precision and efficiency. However, these methods are not without challenges, notably the "domain shift" that occurs when models trained on specific datasets underperform when applied to different datasets. Techniques such as domain adaptation, domain generalization, and data diversity were discussed as potential solutions.
Accurate measurement of VS growth is a complex process, with volumetric analysis currently appearing more reliable than linear measurements. Automatic segmentation, despite its challenges, offers a promising avenue for future investigation. Robust well-generalized models could potentially improve the efficiency of tracking tumor growth, thereby augmenting clinical decision-making. Further work needs to be done to develop more robust models, address the domain shift, and enable secure data sharing for wider applicability.
前庭神经鞘瘤（VSs）是良性肿瘤，通常需要经过长时间的监测，而评估生长速度的测量技术存在显著的观察者间变异性。这些肿瘤的自动分割可以提供更可靠和高效的方法来跟踪其进展，特别是考虑到 VS 的不规则形状和生长模式。
分析了各种使用不同卷积神经网络架构和模型（如 U-Net 和卷积注意转换器分割）的研究和分割技术。根据它们在不同数据集上的性能评估模型，并仔细研究了包括领域转移和数据共享在内的挑战。
自动分割方法为传统的测量技术提供了一种很有前途的替代方法，在精度和效率方面具有潜在的优势。然而，这些方法并非没有挑战，特别是当在特定数据集上训练的模型在应用于不同数据集时表现不佳时，就会出现“领域转移”问题。讨论了诸如域自适应、域泛化和数据多样性等技术作为潜在的解决方案。
准确测量 VS 的生长是一个复杂的过程，目前体积分析似乎比线性测量更可靠。自动分割尽管存在挑战，但为未来的研究提供了一个很有前途的途径。稳健的泛化良好的模型可能会提高跟踪肿瘤生长的效率，从而增强临床决策。需要进一步的工作来开发更强大的模型，解决领域转移问题，并实现安全的数据共享，以实现更广泛的应用。
