PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation

Abstract

It has been widely recognized that the success of deep learning in image segmentation relies overwhelmingly on a myriad amount of densely annotated training data, which, however, are difficult to obtain due to the tremendous labor and expertise required, particularly for annotating 3D medical images. Although self-supervised learning (SSL) has shown great potential to address this issue, most SSL approaches focus only on image-level global consistency, but ignore the local consistency which plays a pivotal role in capturing structural information for dense prediction tasks such as segmentation. In this paper, we propose a PriorGuided Local (PGL) self-supervised model that learns the region-wise local consistency in the latent feature space. Specifically, we use the spatial transformations, which produce different augmented views of the same image, as a prior to deduce the location relation between two views, which is then used to align the feature maps of the same local region but being extracted on two views. Next, we construct a local consistency loss to minimize the voxel-wise discrepancy between the aligned feature maps. Thus, our PGL model learns the distinctive representations of local regions, and hence is able to retain structural information. This ability is conducive to downstream segmentation tasks. We conducted an extensive evaluation on four public computerized tomography (CT) datasets that cover 11 kinds of major human organs and two tumors. The results indicate that using pre-trained PGL model to initialize a downstream network leads to a substantial performance improvement over both random initialization and the initialization with global consistency-based models. Code and pre-trained weights will be made available at: https://git.io/PGL.

arXiv comment13 pages

References in corpus (6)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Learning deep representations by mutual information estimation and maximization
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• Large Batch Training of Convolutional Networks
• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• Self-supervised Label Augmentation via Input Transformations

Cited by in corpus (7)

• Self-supervised learning methods and applications in medical imaging analysis: A survey
• A Review of Predictive and Contrastive Self-supervised Learning for Medical Images
• Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification
• HSMix: Hard and Soft Mixing Data Augmentation for Medical Image Segmentation
• Learning from the few: Fine-grained approach to pediatric wrist pathology recognition on a limited dataset
• Self-supervised Tumor Segmentation through Layer Decomposition
• Contrastive Learning with Temporal Correlated Medical Images: A Case Study using Lung Segmentation in Chest X-Rays