Brain-Aware Replacements for Supervised Contrastive Learning in Detection of Alzheimer's Disease.
Brain-Aware Replacements for Supervised Contrastive Learning in Detection of Alzheimer's Disease.
复制标题
大脑感知替代监督对比学习在阿尔茨海默病检测中的应用。
DOI：
10.1007/978-3-031-16431-6_44
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Shapiro,Linda
中科院分区：
文献类型：
--
作者：
Seyfioğlu,MehmetSaygın;Liu,Zixuan;Kamath,Pranav;Gangolli,Sadjyot;Wang,Sheng;Grabowski,Thomas;Shapiro,Linda
我们提出了一个新的框架阿尔茨海默氏病（AD）检测使用脑MRI。该框架从一种名为大脑感知替换（BAR）的数据增强方法开始，该方法利用标准的大脑分割来替换随机挑选的MRI中的锚MRI中的医学相关3D大脑区域，以创建合成样本。地面实况“硬”标签也根据替换比率线性混合，以便创建“软”标签。BAR产生了各种各样的逼真的合成MRI，与其他基于混合的方法（如CutMix）相比，具有更高的局部变异性。在BAR之上，我们建议使用具有软标签能力的监督对比损失，旨在学习表示的相对相似性，以反映使用我们的软标签的合成MRI的混合程度。这样，我们不会完全耗尽硬标签的熵容量，因为我们只使用它们通过BAR创建软标签和合成MRI。我们表明，使用我们的框架预训练的模型可以使用用于创建合成样本的硬标签通过交叉熵损失进行进一步微调。我们验证了我们的框架在二进制AD检测任务中对从头开始的监督训练和最先进的自监督训练加微调方法的性能。然后，我们评估了BAR的个人性能相比，另一个混合的方法CutMix集成在我们的框架。我们表明，我们的框架产生上级的结果，在精度和召回的AD检测任务。
We propose a novel framework for Alzheimer’s disease (AD) detection using brain MRIs. The framework starts with a data augmentation method called Brain-Aware Replacements (BAR), which leverages a standard brain parcellation to replace medically-relevant 3D brain regions in an anchor MRI from a randomly picked MRI to create synthetic samples. Ground truth “hard” labels are also linearly mixed depending on the replacement ratio in order to create “soft” labels. BAR produces a great variety of realistic-looking synthetic MRIs with higher local variability compared to other mix-based methods, such as CutMix. On top of BAR, we propose using a soft-label-capable supervised contrastive loss, aiming to learn the relative similarity of representations that reflect how mixed are the synthetic MRIs using our soft labels. This way, we do not fully exhaust the entropic capacity of our hard labels, since we only use them to create soft labels and synthetic MRIs through BAR. We show that a model pre-trained using our framework can be further fine-tuned with a cross-entropy loss using the hard labels that were used to create the synthetic samples. We validated the performance of our framework in a binary AD detection task against both from-scratch supervised training and state-of-the-art self-supervised training plus fine-tuning approaches. Then we evaluated BAR’s individual performance compared to another mix-based method CutMix by integrating it within our framework. We show that our framework yields superior results in both precision and recall for the AD detection task.