Dereskewicz Emma, La Rosa Francesco, Dos Santos Silva Jonadab, Sizer Edward, Kohli Amit, Wynen Maxence, Mullins William A, Maggi Pietro, Levy Sarah, Onyemeh Kamso, Ayci Batuhan, Solomon Andrew J, Assländer Jakob, Al-Louzi Omar, Reich Daniel S, Sumowski James, Beck Erin S
Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
Windreich Department of Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
J Neuroimaging. 2025 Sep-Oct;35(5):e70085. doi: 10.1111/jon.70085.
Assessment of brain lesions on magnetic resonance imaging (MRI) is crucial for research in multiple sclerosis (MS). Manual segmentation is time-consuming and inconsistent. We aimed to develop an automated MS lesion segmentation algorithm for T2-weighted fluid-attenuated inversion recovery (FLAIR) MRI.
We developed FLAIR Lesion Analysis in Multiple Sclerosis (FLAMeS), a deep learning-based MS lesion segmentation algorithm based on the nnU-Net 3D full-resolution U-Net and trained on 668 FLAIR 1.5 and 3 tesla scans from persons with MS. FLAMeS was evaluated on three external datasets: MSSEG-2 (n = 14), MSLesSeg (n = 51), and a clinical cohort (n = 10), and compared to SAMSEG, LST-LPA, and LST-AI. Performance was assessed qualitatively by two blinded experts and quantitatively by comparing automated and ground truth lesion masks using standard segmentation metrics.
In a blinded qualitative review of 20 scans, both raters selected FLAMeS as the most accurate segmentation in 15 cases, with one rater favoring FLAMeS in two additional cases. Across all testing datasets, FLAMeS achieved a mean Dice score of 0.74, a true positive rate of 0.84, and an F1 score of 0.78, consistently outperforming the benchmark methods. For other metrics, including positive predictive value, relative volume difference, and false positive rate, FLAMeS performed similarly to or better than benchmark methods. Most lesions missed by FLAMeS were smaller than 10 mm, whereas the benchmark methods missed larger lesions in addition to smaller ones.
FLAMeS is an accurate, robust method for MS lesion segmentation that outperforms other publicly available methods.
在多发性硬化症（MS）研究中，通过磁共振成像（MRI）评估脑损伤至关重要。手动分割既耗时又不一致。我们旨在开发一种用于T2加权液体衰减反转恢复（FLAIR）MRI的自动MS病变分割算法。
我们开发了多发性硬化症中的FLAIR病变分析（FLAMeS），这是一种基于深度学习的MS病变分割算法，基于nnU-Net 3D全分辨率U-Net，并在668例来自MS患者的FLAIR 1.5和3特斯拉扫描图像上进行训练。FLAMeS在三个外部数据集上进行评估：MSSEG-2（n = 14）、MSLesSeg（n = 51）和一个临床队列（n = 10），并与SAMSEG、LST-LPA和LST-AI进行比较。由两名盲法专家进行定性评估，并通过使用标准分割指标比较自动分割和真实病变掩码进行定量评估。
在对20次扫描的盲法定性评估中，两位评估者在15例中都选择FLAMeS为最准确的分割方法，其中一位评估者在另外两例中更倾向于FLAMeS。在所有测试数据集中，FLAMeS的平均骰子系数为0.74，真阳性率为0.84，F1分数为0.78，始终优于基准方法。对于其他指标，包括阳性预测值、相对体积差异和假阳性率，FLAMeS的表现与基准方法相似或更好。FLAMeS遗漏的大多数病变小于10毫米，而基准方法除了较小的病变外还遗漏了较大的病变。
FLAMeS是一种准确、稳健的MS病变分割方法，优于其他公开可用的方法。
