Jung Diagnostics GmbH, Hamburg, Germany.
Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Martinistr. 52, 20246, Hamburg, Germany.
Int J Comput Assist Radiol Surg. 2024 Sep;19(9):1763-1771. doi: 10.1007/s11548-024-03201-3. Epub 2024 Jun 16.
MRI-derived brain volume loss (BVL) is widely used as neurodegeneration marker. SIENA is state-of-the-art for BVL measurement, but limited by long computation time. Here we propose "BrainLossNet", a convolutional neural network (CNN)-based method for BVL-estimation.
BrainLossNet uses CNN-based non-linear registration of baseline(BL)/follow-up(FU) 3D-T1w-MRI pairs. BVL is computed by non-linear registration of brain parenchyma masks segmented in the BL/FU scans. The BVL estimate is corrected for image distortions using the apparent volume change of the total intracranial volume. BrainLossNet was trained on 1525 BL/FU pairs from 83 scanners. Agreement between BrainLossNet and SIENA was assessed in 225 BL/FU pairs from 94 MS patients acquired with a single scanner and 268 BL/FU pairs from 52 scanners acquired for various indications. Robustness to short-term variability of 3D-T1w-MRI was compared in 354 BL/FU pairs from a single healthy men acquired in the same session without repositioning with 116 scanners (Frequently-Traveling-Human-Phantom dataset, FTHP).
Processing time of BrainLossNet was 2-3 min. The median [interquartile range] of the SIENA-BrainLossNet BVL difference was 0.10% [- 0.18%, 0.35%] in the MS dataset, 0.08% [- 0.14%, 0.28%] in the various indications dataset. The distribution of apparent BVL in the FTHP dataset was narrower with BrainLossNet (p = 0.036; 95th percentile: 0.20% vs 0.32%).
BrainLossNet on average provides the same BVL estimates as SIENA, but it is significantly more robust, probably due to its built-in distortion correction. Processing time of 2-3 min makes BrainLossNet suitable for clinical routine. This can pave the way for widespread clinical use of BVL estimation from intra-scanner BL/FU pairs.
MRI 衍生的脑容量损失（BVL）被广泛用作神经退行性变的标志物。SIENA 是 BVL 测量的最新技术，但受到计算时间长的限制。这里我们提出了“BrainLossNet”，一种基于卷积神经网络（CNN）的 BVL 估计方法。
BrainLossNet 使用基于 CNN 的非线性配准基线（BL）/随访（FU）3D-T1w-MRI 对。通过对 BL/FU 扫描中分割的脑实质掩模进行非线性配准来计算 BVL。使用总颅内体积的表观体积变化校正 BVL 估计值的图像失真。BrainLossNet 在来自 83 台扫描仪的 1525 对 BL/FU 上进行了训练。在来自 94 名 MS 患者的单个扫描仪采集的 225 对 BL/FU 上和来自用于各种适应症的 52 台扫描仪采集的 268 对 BL/FU 上评估了 BrainLossNet 和 SIENA 的一致性。在同一会话中未重新定位的情况下，在来自单个健康男性的 354 对 BL/FU 上比较了 3D-T1w-MRI 的短期变异性的稳健性，共 116 台扫描仪（经常旅行人体模型数据集，FTHP）。
BrainLossNet 的处理时间为 2-3 分钟。在 MS 数据集和各种适应症数据集，SIENA-BrainLossNet BVL 差值的中位数[四分位数范围]分别为 0.10%[-0.18%，0.35%]和 0.08%[-0.14%，0.28%]。FTHP 数据集的表观 BVL 分布更窄，BrainLossNet （p=0.036；95% 位数：0.20% vs 0.32%）。
BrainLossNet 平均提供与 SIENA 相同的 BVL 估计值，但它具有更高的稳健性，可能是由于其内置的失真校正。2-3 分钟的处理时间使 BrainLossNet 适用于临床常规。这为广泛使用 BL/FU 对的 intra-scanner 进行 BVL 估计铺平了道路。
