Biomedical Engineering, University of Virginia, 22903, Charlottesville, VA, USA.
Carina Medical LLC, Lexington, KY, 40513, USA.
J Digit Imaging. 2023 Oct;36(5):2075-2087. doi: 10.1007/s10278-023-00860-7. Epub 2023 Jun 20.
Deep convolutional neural networks (DCNNs) have shown promise in brain tumor segmentation from multi-modal MRI sequences, accommodating heterogeneity in tumor shape and appearance. The fusion of multiple MRI sequences allows networks to explore complementary tumor information for segmentation. However, developing a network that maintains clinical relevance in situations where certain MRI sequence(s) might be unavailable or unusual poses a significant challenge. While one solution is to train multiple models with different MRI sequence combinations, it is impractical to train every model from all possible sequence combinations. In this paper, we propose a DCNN-based brain tumor segmentation framework incorporating a novel sequence dropout technique in which networks are trained to be robust to missing MRI sequences while employing all other available sequences. Experiments were performed on the RSNA-ASNR-MICCAI BraTS 2021 Challenge dataset. When all MRI sequences were available, there were no significant differences in performance of the model with and without dropout for enhanced tumor (ET), tumor (TC), and whole tumor (WT) (p-values 1.000, 1.000, 0.799, respectively), demonstrating that the addition of dropout improves robustness without hindering overall performance. When key sequences were unavailable, the network with sequence dropout performed significantly better. For example, when tested on only T1, T2, and FLAIR sequences together, DSC for ET, TC, and WT increased from 0.143 to 0.486, 0.431 to 0.680, and 0.854 to 0.901, respectively. Sequence dropout represents a relatively simple yet effective approach for brain tumor segmentation with missing MRI sequences.
深度卷积神经网络（DCNN）在从多模态 MRI 序列中分割脑肿瘤方面表现出了很大的潜力，能够适应肿瘤形状和外观的异质性。融合多个 MRI 序列可以让网络探索互补的肿瘤信息以进行分割。然而，开发一个在某些 MRI 序列不可用或不常见的情况下仍保持临床相关性的网络是一个重大挑战。虽然一种解决方案是使用不同 MRI 序列组合训练多个模型，但训练所有可能序列组合的每个模型是不切实际的。在本文中，我们提出了一种基于 DCNN 的脑肿瘤分割框架，其中包含一种新的序列丢弃技术，该技术可以在使用所有其他可用序列的同时训练网络以对缺失的 MRI 序列具有鲁棒性。实验是在 RSNA-ASNR-MICCAI BraTS 2021 挑战赛数据集上进行的。当所有 MRI 序列都可用时，具有和不具有 dropout 的模型在增强肿瘤（ET）、肿瘤（TC）和整个肿瘤（WT）的性能上没有显著差异（p 值分别为 1.000、1.000 和 0.799），这表明添加 dropout 可以提高鲁棒性而不会影响整体性能。当关键序列不可用时，具有序列丢弃的网络性能显著提高。例如，当仅在 T1、T2 和 FLAIR 序列一起测试时，ET、TC 和 WT 的 DSC 分别从 0.143 增加到 0.486、0.431 增加到 0.680 和 0.854 增加到 0.901。序列丢弃是一种相对简单但有效的方法，可以用于具有缺失 MRI 序列的脑肿瘤分割。
