Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse. Equivariant contrastive learning, on the other hand, provides representations sensitive to specific image transformations while remaining invariant to others. By introducing equivariance to time-induced transformations, such as disease-related anatomical changes in longitudinal imaging, the model can effectively capture such changes in the representation space. In this work, we propose a Time-equivariant Contrastive Learning (TC) method. First, an encoder embeds two unlabeled scans from different time points of the same patient into the representation space. Next, a temporal equivariance module is trained to predict the representation of a later visit based on the representation from one of the previous visits and the corresponding time interval with a novel regularization loss term while preserving the invariance property to irrelevant image transformations. On a large longitudinal dataset, our model clearly outperforms existing equivariant contrastive methods in predicting progression from intermediate age-related macular degeneration (AMD) to advanced wet-AMD within a specified time-window.

翻译：对比预训练通过确保表征对不同图像变换的不变性，同时防止表征坍缩，从而提供稳健的表征。另一方面，等变对比学习则提供对特定图像变换敏感、同时对其他变换保持不变的表示。通过引入对时间诱导变换（如纵向成像中疾病相关的解剖学变化）的等变性，模型可以在表征空间中有效捕捉此类变化。在本研究中，我们提出了一种时间等变对比学习（TC）方法。首先，编码器将来自同一患者不同时间点的两次未标注扫描嵌入到表征空间中。接着，时间等变性模块通过一种新颖的正则化损失项，基于先前某次访问的表征及对应时间间隔，预测后续访问的表征，同时保持对无关图像变换的不变性。在大型纵向数据集上，我们的模型在预测特定时间窗口内从中度年龄相关性黄斑变性（AMD）向晚期湿性AMD进展的任务中，明显优于现有的等变对比方法。