Jung Diagnostics GmbH, Hamburg, Germany.
University Hospital Carl Gustav Carus, Department of Neurology, Technische Universität Dresden, Dresden, Germany.
Comput Biol Med. 2024 Dec;183:109289. doi: 10.1016/j.compbiomed.2024.109289. Epub 2024 Oct 18.
Clinical validation of "BrainLossNet", a deep learning-based method for fast and robust estimation of brain volume loss (BVL) from longitudinal T1-weighted MRI, for the detection of accelerated BVL in multiple sclerosis (MS) and for the discrimination between MS patients with versus without disability progression.
A longitudinal normative database of healthy controls (n = 563), two mono-scanner MS cohorts (n = 414, 156) and a mixed-scanner cohort acquired for various indications (n = 216) were included retrospectively. Mean observation period from the baseline (BL) to the last follow-up (FU) MRI scan was 2-3 years. Expanded Disability Status Scale (EDSS) at BL and FU was available in 149 MS patients. Annual BVL was computed using BrainLossNet and Siena and then adjusted for age. Repeated-measures ANOVA and Cohen's effect size were used to compare BrainLossNet and Siena regarding the detection of accelerated BVL and the differentiation between MS patients with versus without EDSS progression.
Cohen's effect size for the differentiation of patients from healthy controls based on the age-adjusted annual BVL was larger with BrainLossNet than with Siena (MS cohort 1: 0.927 versus 0.495, MS cohort 2: 0.671 versus 0.456, mixed-scanner cohort: 0.918 versus 0.730, all p < 0.001). Cohen's effect size for the discrimination between MS patients with (n = 51) versus without (n = 98) EDSS progression was larger with BrainLossNet (0.503 versus 0.400, p = 0.048).
BrainLossNet can provide added value in clinical routine and MS therapy trials regarding the detection of accelerated BVL in MS and the differentiation between MS patients with versus without disability progression.
验证基于深度学习的脑容量损失（BVL）快速、稳健估算方法“BrainLossNet”的临床有效性，该方法用于检测多发性硬化症（MS）中的BVL 加速，并用于区分有和无残疾进展的 MS 患者。
本研究回顾性纳入了一个纵向正常对照数据库（n=563）、两个单扫描仪 MS 队列（n=414，156）和一个因各种适应证采集的混合扫描仪队列（n=216）。从基线（BL）到最后一次随访（FU）MRI 扫描的平均观察期为 2-3 年。149 名 MS 患者的 BL 和 FU 时扩展残疾状态量表（EDSS）可用。使用 BrainLossNet 和 Siena 计算每年的 BVL，然后根据年龄进行调整。使用重复测量方差分析和 Cohen's 效应量比较 BrainLossNet 和 Siena 在检测 BVL 加速和区分有和无 EDSS 进展的 MS 患者方面的差异。
基于年龄调整后的年度 BVL，BrainLossNet 区分患者与健康对照的 Cohen's 效应量大于 Siena（队列 1：0.927 对 0.495，队列 2：0.671 对 0.456，混合扫描仪队列：0.918 对 0.730，均 p<0.001）。基于 BrainLossNet，MS 患者（n=51）与无 EDSS 进展的患者（n=98）之间的区分 Cohen's 效应量更大（0.503 对 0.400，p=0.048）。
BrainLossNet 在 MS 中检测 BVL 加速和区分有和无残疾进展的 MS 患者方面可为临床常规和 MS 治疗试验提供附加价值。
