Zhang Lintao, Wu Jinjian, Wang Lihong, Wang Li, Steffens David C, Qiu Shijun, Potter Guy G, Liu Mingxia
Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.
The First School of Clinical Medicine, Guangzhou University of Chinese Medicine, Guangzhou, Guangdong 510031, China.
Pattern Recognit. 2025 Sep;165. doi: 10.1016/j.patcog.2025.111603. Epub 2025 Mar 21.
Brain structural MRI has been widely used to assess the future progression of cognitive impairment (CI). Previous learning-based studies usually suffer from the issue of small-sized labeled training data, while a huge amount of structural MRIs exist in large-scale public databases. Intuitively, brain anatomical structures derived from these public MRIs (even without task-specific label information) can boost CI progression trajectory prediction. However, previous studies seldom use such brain anatomy structure information as priors. To this end, this paper proposes a brain anatomy prior modeling (BAPM) framework to forecast the clinical progression of cognitive impairment with small-sized target MRIs by exploring anatomical brain structures. Specifically, the BAPM consists of a and a , with a shared brain anatomy-guided encoder to model brain anatomy prior using auxiliary tasks explicitly. Besides the encoder, the pretext model also contains two decoders for two auxiliary tasks (, MRI reconstruction and brain tissue segmentation), while the downstream model relies on a predictor for classification. The brain anatomy-guided encoder is pre-trained with the pretext model on 9,344 auxiliary MRIs without diagnostic labels for anatomy prior modeling. With this encoder frozen, the downstream model is then fine-tuned on limited target MRIs for prediction. We validate BAPM on two CI-related studies with T1-weighted MRIs from 448 subjects. Experimental results suggest the effectiveness of BAPM in (1) four CI progression prediction tasks, (2) MR image reconstruction, and (3) brain tissue segmentation, compared with several state-of-the-art methods.
脑结构磁共振成像（MRI）已被广泛用于评估认知障碍（CI）的未来进展。以往基于学习的研究通常存在标记训练数据量小的问题，而大规模公共数据库中存在大量的结构MRI。直观地说，从这些公共MRI中提取的脑解剖结构（即使没有特定任务的标签信息）也可以促进CI进展轨迹预测。然而，以往的研究很少将这种脑解剖结构信息用作先验信息。为此，本文提出了一种脑解剖先验建模（BAPM）框架，通过探索脑解剖结构，利用小尺寸目标MRI预测认知障碍的临床进展。具体而言，BAPM由一个[此处原文缺失具体内容]和一个[此处原文缺失具体内容]组成，具有一个共享的脑解剖引导编码器，通过辅助任务明确地对脑解剖先验进行建模。除了编码器， pretext模型还包含用于两个辅助任务（MRI重建和脑组织分割）的两个解码器，而下游模型依赖于一个用于分类的预测器。脑解剖引导编码器在9344个无诊断标签的辅助MRI上使用pretext模型进行预训练，以进行解剖先验建模。在冻结此编码器后，下游模型然后在有限的目标MRI上进行微调以进行预测。我们使用来自448名受试者的T1加权MRI在两项与CI相关的研究中验证了BAPM。实验结果表明，与几种最新方法相比，BAPM在（1）四项CI进展预测任务、（2）MR图像重建和（3）脑组织分割方面是有效的。
