Wang Nicholas C, Noll Douglas C, Srinivasan Ashok, Gagnon-Bartsch Johann, Kim Michelle M, Rao Arvind
Department of Computational Medicine and Bioinformatics, University of Michigan, USA.
Department of Biomedical Engineering, University of Michigan, USA.
BME Front. 2022 Nov 1;2022:9807590. doi: 10.34133/2022/9807590. eCollection 2022.
. Seven types of MRI artifacts, including acquisition and preprocessing errors, were simulated to test a machine learning brain tumor segmentation model for potential failure modes. . Real-world medical deployments of machine learning algorithms are less common than the number of medical research papers using machine learning. Part of the gap between the performance of models in research and deployment comes from a lack of hard test cases in the data used to train a model. . These failure modes were simulated for a pretrained brain tumor segmentation model that utilizes standard MRI and used to evaluate the performance of the model under duress. These simulated MRI artifacts consisted of motion, susceptibility induced signal loss, aliasing, field inhomogeneity, sequence mislabeling, sequence misalignment, and skull stripping failures. . The artifact with the largest effect was the simplest, sequence mislabeling, though motion, field inhomogeneity, and sequence misalignment also caused significant performance decreases. The model was most susceptible to artifacts affecting the FLAIR (fluid attenuation inversion recovery) sequence. . Overall, these simulated artifacts could be used to test other brain MRI models, but this approach could be used across medical imaging applications.
模拟了七种类型的MRI伪影，包括采集和预处理错误，以测试机器学习脑肿瘤分割模型的潜在故障模式。机器学习算法在实际医疗中的应用不如使用机器学习的医学研究论文数量那么普遍。研究模型和实际应用模型之间性能差距的部分原因在于，用于训练模型的数据缺乏严格的测试案例。针对一个利用标准MRI的预训练脑肿瘤分割模型模拟了这些故障模式，并用于评估该模型在压力下的性能。这些模拟的MRI伪影包括运动、磁化率诱导信号丢失、混叠、磁场不均匀性、序列错误标记、序列失准和去颅骨失败。影响最大的伪影是最简单的序列错误标记，不过运动、磁场不均匀性和序列失准也会导致性能显著下降。该模型对影响FLAIR（液体衰减反转恢复）序列的伪影最为敏感。总体而言，这些模拟伪影可用于测试其他脑MRI模型，但这种方法可应用于整个医学成像应用。
