Hitziger Sebastian, Ling Wen Xin, Fritz Thomas, D'Albis Tiziano, Lemke Andreas, Grilo Joana
Mediaire GmbH, Berlin, Germany.
Front Neurosci. 2022 Aug 12;16:964250. doi: 10.3389/fnins.2022.964250. eCollection 2022.
We present a deep learning method for the segmentation of new lesions in longitudinal FLAIR MRI sequences acquired at two different time points. In our approach, the 3D volumes are processed slice-wise across the coronal, axial, and sagittal planes and the predictions from the three orientations are merged using an optimized voting strategy. Our method achieved best F1 score (0.541) among all participating methods in the MICCAI 2021 challenge (MSSEG-2). Moreover, we show that our method is on par with the challenge's expert neuroradiologists: on an unbiased ground truth, our method achieves results comparable to those of the four experts in terms of detection (F1 score) and segmentation accuracy (Dice score).
我们提出了一种深度学习方法，用于对在两个不同时间点采集的纵向液体衰减反转恢复（FLAIR）磁共振成像（MRI）序列中的新病变进行分割。在我们的方法中，对三维体积数据按冠状面、轴位面和矢状面逐片进行处理，并使用优化的投票策略合并来自三个方向的预测结果。在2021年医学图像计算与计算机辅助干预国际会议（MICCAI）挑战赛（MSSEG - 2）的所有参赛方法中，我们的方法获得了最佳的F1分数（0.541）。此外，我们表明我们的方法与挑战赛中的神经放射学专家水平相当：在无偏差的真实数据上，我们的方法在检测（F1分数）和分割准确性（Dice分数）方面取得了与四位专家相当的结果。
