Skattebøl Lars, Nygaard Gro O, Leonardsen Esten H, Kaufmann Tobias, Moridi Thomas, Stawiarz Leszek, Ouellette Russel, Ineichen Benjamin V, Ferreira Daniel, Muehlboeck J Sebastian, Beyer Mona K, Sowa Piotr, Manouchehrinia Ali, Westman Eric, Olsson Tomas, Celius Elisabeth G, Hillert Jan, Kockum Ingrid, Harbo Hanne F, Piehl Fredrik, Granberg Tobias, Westlye Lars T, Høgestøl Einar A
Department of Neurology, Oslo University Hospital, Oslo 0450, Norway.
Institute of Clinical Medicine, University of Oslo, Oslo 0318, Norway.
Brain Commun. 2025 Apr 18;7(3):fcaf152. doi: 10.1093/braincomms/fcaf152. eCollection 2025.
'Brain age' is a numerical estimate of the biological age of the brain and an overall effort to measure neurodegeneration, regardless of disease type. In multiple sclerosis, accelerated brain ageing has been linked to disability accrual. Artificial intelligence has emerged as a promising tool for the assessment and quantification of the impact of neurodegenerative diseases. Despite the existence of numerous AI models, there is a noticeable lack of comparative imaging data for traditional machine learning versus deep learning in conditions such as multiple sclerosis. A retrospective observational study was initiated to analyse clinical and MRI data (4584 MRIs) from various scanners in a large longitudinal cohort ( = 1516) of people with multiple sclerosis collected from two institutions (Karolinska Institute and Oslo University Hospital) using a uniform data post-processing pipeline. We conducted a comparative assessment of brain age using a deep learning simple fully convolutional network and a well-established traditional machine learning model. This study was primarily aimed to validate the deep learning brain age model in multiple sclerosis. The correlation between estimated brain age and chronological age was stronger for the deep learning estimates ( = 0.90, < 0.001) than the traditional machine learning estimates ( = 0.75, < 0.001). An increase in brain age was significantly associated with higher expanded disability status scale scores (traditional machine learning: = 5.3, < 0.001; deep learning: = 3.7, < 0.001) and longer disease duration (traditional machine learning: = 6.5, < 0.001; deep learning: = 5.8, < 0.001). No significant inter-model difference in clinical correlation or effect measure was found, but significant differences for traditional machine learning-derived brain age estimates were found between several scanners. Our study suggests that the deep learning-derived brain age is significantly associated with clinical disability, performed equally well to the traditional machine learning-derived brain age measures, and may counteract scanner variability.
“脑龄”是对大脑生物学年龄的数值估计，也是衡量神经退行性变的一项综合指标，与疾病类型无关。在多发性硬化症中，脑加速老化与残疾累积有关。人工智能已成为评估和量化神经退行性疾病影响的一种有前景的工具。尽管存在众多人工智能模型，但在多发性硬化症等疾病中，传统机器学习与深度学习的对比成像数据明显不足。启动了一项回顾性观察研究，以分析来自两个机构（卡罗林斯卡学院和奥斯陆大学医院）收集的一个大型纵向队列（n = 1516）的多发性硬化症患者的各种扫描仪的临床和MRI数据（4584次MRI），使用统一的数据后处理流程。我们使用深度学习简单全卷积网络和成熟的传统机器学习模型对脑龄进行了对比评估。本研究的主要目的是在多发性硬化症中验证深度学习脑龄模型。深度学习估计的估计脑龄与实际年龄之间的相关性（r = 0.90，p < 0.001）比传统机器学习估计的相关性（r = 0.75，p < 0.001）更强。脑龄增加与更高的扩展残疾状态量表评分（传统机器学习：r = 5.3，p < 0.001；深度学习：r = 3.7，p < 0.001）和更长的病程（传统机器学习：r = 6.5，p < 0.001；深度学习：r = 5.8，p < 0.001）显著相关。在临床相关性或效应量方面未发现模型间的显著差异，但在几台扫描仪之间发现传统机器学习得出的脑龄估计存在显著差异。我们的研究表明，深度学习得出的脑龄与临床残疾显著相关，与传统机器学习得出的脑龄测量表现相当，并且可能抵消扫描仪变异性的影响。
