Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in Segmentation
This work addresses data distribution misalignment in medical image segmentation, offering a general framework that is incremental over prior separate optimization approaches.
The paper tackles the problem of aligning training and test data distributions in medical image segmentation by jointly optimizing class-specific training-time and test-time data augmentation, resulting in significant and consistent performance improvements across four tasks with state-of-the-art models.
This paper presents an effective and general data augmentation framework for medical image segmentation. We adopt a computationally efficient and data-efficient gradient-based meta-learning scheme to explicitly align the distribution of training and validation data which is used as a proxy for unseen test data. We improve the current data augmentation strategies with two core designs. First, we learn class-specific training-time data augmentation (TRA) effectively increasing the heterogeneity within the training subsets and tackling the class imbalance common in segmentation. Second, we jointly optimize TRA and test-time data augmentation (TEA), which are closely connected as both aim to align the training and test data distribution but were so far considered separately in previous works. We demonstrate the effectiveness of our method on four medical image segmentation tasks across different scenarios with two state-of-the-art segmentation models, DeepMedic and nnU-Net. Extensive experimentation shows that the proposed data augmentation framework can significantly and consistently improve the segmentation performance when compared to existing solutions. Code is publicly available.