Centre for Mathematical Sciences, Lund University, Lund, Sweden.
Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden.
Alzheimers Res Ther. 2024 Mar 19;16(1):61. doi: 10.1186/s13195-024-01428-5.
Predicting future Alzheimer's disease (AD)-related cognitive decline among individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) is an important task for healthcare. Structural brain imaging as measured by magnetic resonance imaging (MRI) could potentially contribute when making such predictions. It is unclear if the predictive performance of MRI can be improved using entire brain images in deep learning (DL) models compared to using pre-defined brain regions.
A cohort of 332 individuals with SCD/MCI were included from the Swedish BioFINDER-1 study. The goal was to predict longitudinal SCD/MCI-to-AD dementia progression and change in Mini-Mental State Examination (MMSE) over four years. Four models were evaluated using different predictors: (1) clinical data only, including demographics, cognitive tests and APOE ε4 status, (2) clinical data plus hippocampal volume, (3) clinical data plus all regional MRI gray matter volumes (N = 68) extracted using FreeSurfer software, (4) a DL model trained using multi-task learning with MRI images, Jacobian determinant images and baseline cognition as input. A double cross-validation scheme, with five test folds and for each of those ten validation folds, was used. External evaluation was performed on part of the ADNI dataset, including 108 patients. Mann-Whitney U-test was used to determine statistically significant differences in performance, with p-values less than 0.05 considered significant.
In the BioFINDER cohort, 109 patients (33%) progressed to AD dementia. The performance of the clinical data model for prediction of progression to AD dementia was area under the curve (AUC) = 0.85 and four-year cognitive decline was R = 0.14. The performance was improved for both outcomes when adding hippocampal volume (AUC = 0.86, R = 0.16). Adding FreeSurfer brain regions improved prediction of four-year cognitive decline but not progression to AD (AUC = 0.83, R = 0.17), while the DL model worsened the performance for both outcomes (AUC = 0.84, R = 0.08). A sensitivity analysis showed that the Jacobian determinant image was more informative than the MRI image, but that performance was maximized when both were included. In the external evaluation cohort from ADNI, 23 patients (21%) progressed to AD dementia. The results for predicted progression to AD dementia were similar to the results for the BioFINDER test data, while the performance for the cognitive decline was deteriorated.
The DL model did not significantly improve the prediction of clinical disease progression in AD, compared to regression models with a single pre-defined brain region.
预测有主观认知下降（SCD）或轻度认知障碍（MCI）的个体未来的阿尔茨海默病（AD）相关认知下降是医疗保健的一项重要任务。磁共振成像（MRI）等结构性脑成像技术可能对此类预测有所帮助。目前尚不清楚与使用预定义脑区相比，使用深度学习（DL）模型中的整个脑图像是否可以提高 MRI 的预测性能。
本研究纳入了来自瑞典 BioFINDER-1 研究的 332 名 SCD/MCI 个体。研究目的是预测 SCD/MCI 向 AD 痴呆的纵向进展以及四年内 Mini-Mental State Examination（MMSE）的变化。使用不同的预测因子评估了四种模型：（1）仅临床数据，包括人口统计学、认知测试和 APOE ε4 状态，（2）临床数据加海马体积，（3）临床数据加使用 FreeSurfer 软件提取的所有区域 MRI 灰质体积（N=68），（4）使用多任务学习训练的 DL 模型，输入包括 MRI 图像、雅可比行列式图像和基线认知。使用具有五个测试折叠的双交叉验证方案，对于每个测试折叠，进行了十个验证折叠。使用 ADNI 数据集的一部分进行外部评估，包括 108 名患者。采用曼-惠特尼 U 检验确定性能的统计学显著差异，p 值小于 0.05 被认为具有统计学意义。
在 BioFINDER 队列中，有 109 名患者（33%）进展为 AD 痴呆。用于预测向 AD 痴呆进展的临床数据模型的表现为曲线下面积（AUC）=0.85，四年认知下降为 R=0.14。当添加海马体积时，两种结果的表现均得到改善（AUC=0.86，R=0.16）。添加 FreeSurfer 脑区可改善四年认知下降的预测，但不能改善向 AD 的进展（AUC=0.83，R=0.17），而 DL 模型对两种结果的表现均恶化（AUC=0.84，R=0.08）。敏感性分析表明，雅可比行列式图像比 MRI 图像更具信息量，但当两者都包含时，性能达到最大值。在来自 ADNI 的外部评估队列中，有 23 名患者（21%）进展为 AD 痴呆。AD 痴呆进展预测的结果与 BioFINDER 测试数据的结果相似，而认知下降的表现则恶化。
与具有单个预定义脑区的回归模型相比，DL 模型并未显著改善 AD 临床疾病进展的预测。
