Wodzinski Marek, Hemmerling Daria, Daniol Mateusz
Annu Int Conf IEEE Eng Med Biol Soc. 2024 Jul;2024:1-4. doi: 10.1109/EMBC53108.2024.10781853.
Thousands of people suffer from cranial injuries every year. They require personalized implants that need to be designed and manufactured before the reconstruction surgery. The manual design is expensive and time-consuming leading to searching for algorithms whose goal is to automatize the process. The problem can be formulated as volumetric shape completion and solved by deep neural networks dedicated to supervised image segmentation. However, such an approach requires annotating the ground-truth defects which is costly and time-consuming. Usually, the process is replaced with synthetic defect generation. However, even the synthetic ground-truth generation is time-consuming and limits the data heterogeneity, thus the deep models' generalizability. In our work, we propose an alternative and simple approach to use a self-supervised masked autoencoder to solve the problem. This approach by design increases the heterogeneity of the training set and can be seen as a form of data augmentation. We compare the proposed method with several state-of-the-art deep neural networks and show both the quantitative and qualitative improvement on the SkullBreak and SkullFix datasets. The proposed method can be used to efficiently reconstruct the cranial defects in real time.
每年都有成千上万的人遭受颅脑损伤。他们需要个性化的植入物，这些植入物需要在重建手术前进行设计和制造。人工设计昂贵且耗时，因此需要寻找能够使这一过程自动化的算法。该问题可被表述为体积形状完成问题，并通过专门用于监督图像分割的深度神经网络来解决。然而，这种方法需要对真实缺陷进行标注，这既昂贵又耗时。通常，这个过程会被合成缺陷生成所取代。然而，即使是合成真实数据的生成也很耗时，并且限制了数据的异质性，从而限制了深度模型的泛化能力。在我们的工作中，我们提出了一种替代的简单方法，即使用自监督掩码自动编码器来解决这个问题。这种方法在设计上增加了训练集的异质性，并且可以被视为一种数据增强形式。我们将所提出的方法与几个最先进的深度神经网络进行了比较，并在SkullBreak和SkullFix数据集上展示了定量和定性的改进。所提出的方法可用于实时高效地重建颅骨缺损。
