Self-supervised learning (SSL) has emerged as a powerful technique for improving the efficiency and effectiveness of deep learning models. Contrastive methods are a prominent family of SSL that extract similar representations of two augmented views of an image while pushing away others in the representation space as negatives. However, the state-of-the-art contrastive methods require large batch sizes and augmentations designed for natural images that are impractical for 3D medical images. To address these limitations, we propose a new longitudinal SSL method, 3DTINC, based on non-contrastive learning. It is designed to learn perturbation-invariant features for 3D optical coherence tomography (OCT) volumes, using augmentations specifically designed for OCT. We introduce a new non-contrastive similarity loss term that learns temporal information implicitly from intra-patient scans acquired at different times. Our experiments show that this temporal information is crucial for predicting progression of retinal diseases, such as age-related macular degeneration (AMD). After pretraining with 3DTINC, we evaluated the learned representations and the prognostic models on two large-scale longitudinal datasets of retinal OCTs where we predict the conversion to wet-AMD within a six-month interval. Our results demonstrate that each component of our contributions is crucial for learning meaningful representations useful in predicting disease progression from longitudinal volumetric scans.

中文翻译：

---

3DTINC：用于从纵向 OCT 预测疾病进展的时间等变非对比学习


自监督学习 （SSL） 已成为提高深度学习模型效率和有效性的强大技术。对比方法是一个突出的 SSL 系列，它提取图像的两个增强视图的相似表示，同时将表示空间中的其他视图作为负片推开。然而，最先进的对比方法需要大批量和增强，这些增强是为自然图像设计的，这对于 3D 医学图像来说是不切实际的。为了解决这些限制，我们提出了一种基于非对比学习的新纵向 SSL 方法 3DTINC。它旨在使用专为 OCT 设计的增强来学习 3D 光学相干断层扫描 （OCT） 体积的扰动不变特征。我们引入了一个新的非对比相似性损失项，它从不同时间获取的患者内部扫描中隐式学习时间信息。我们的实验表明，这种时间信息对于预测视网膜疾病的进展至关重要，例如年龄相关性黄斑变性 （AMD）。在使用 3DTINC 进行预训练后，我们在视网膜 OCT 的两个大规模纵向数据集上评估了学习的表示和预后模型，我们预测了在六个月间隔内转化为湿性 AMD。我们的结果表明，我们贡献的每个组成部分对于学习有用的有意义的表示都至关重要，这些表示有助于从纵向体积扫描中预测疾病进展。