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 R2 = 0.14. The performance was improved for both outcomes when adding hippocampal volume (AUC = 0.86, R2 = 0.16). Adding FreeSurfer brain regions improved prediction of four-year cognitive decline but not progression to AD (AUC = 0.83, R2 = 0.17), while the DL model worsened the performance for both outcomes (AUC = 0.84, R2 = 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.

中文翻译：

---

比较用于提取脑萎缩模式的预定义方法与深度学习方法，以预测具有轻度认知症状的患者因阿尔茨海默氏病导致的认知能力下降

预测主观认知能力下降 (SCD) 或轻度认知障碍 (MCI) 患者未来与阿尔茨海默病 (AD) 相关的认知能力下降是医疗保健领域的一项重要任务。通过磁共振成像（MRI）测量的大脑结构成像可能有助于做出此类预测。目前尚不清楚，与使用预定义的大脑区域相比，在深度学习 (DL) 模型中使用整个大脑图像是否可以提高 MRI 的预测性能。瑞典 BioFINDER-1 研究纳入了 332 名 SCD/MCI 患者的队列。目标是预测四年内 SCD/MCI 至 AD 痴呆的纵向进展和简易精神状态检查 (MMSE) 的变化。使用不同的预测因子评估四个模型：(1) 仅临床数据，包括人口统计、认知测试和 APOE ε4 状态，(2) 临床数据加上海马体积，(3) 临床数据加上所有区域 MRI 灰质体积 (N = 68 ）使用 FreeSurfer 软件提取，（4）使用 MRI 图像、雅可比行列式图像和基线认知作为输入的多任务学习训练的 DL 模型。使用了双重交叉验证方案，其中有五个测试折叠，并且对于这十个验证折叠中的每个折叠。对部分 ADNI 数据集（包括 108 名患者）进行了外部评估。Mann-Whitney U 检验用于确定统计上显着的绩效差异，p 值小于 0.05 被认为是显着的。在 BioFINDER 队列中，109 名患者 (33%) 进展为 AD 痴呆。预测 AD 痴呆进展的临床数据模型的性能为曲线下面积 (AUC) = 0.85，四年认知能力下降为 R2 = 0.14。当增加海马体积时，这两种结果的表现均得到改善（AUC = 0.86，R2 = 0.16）。添加 FreeSurfer 大脑区域改善了对四年认知能力下降的预测，但没有进展为 AD（AUC = 0.83，R2 = 0.17），而 DL 模型使这两种结果的表现恶化（AUC = 0.84，R2 = 0.08）。敏感性分析表明，雅可比行列式图像比 MRI 图像提供更多信息，但当两者都包含时，性能最大化。在 ADNI 的外部评估队列中，23 名患者 (21%) 进展为 AD 痴呆。预测 AD 痴呆进展的结果与 BioFINDER 测试数据的结果相似，而认知能力下降的表现则恶化。与具有单个预定义大脑区域的回归模型相比，深度学习模型并没有显着改善 AD 临床疾病进展的预测。