A Review of Predictive and Contrastive Self-supervised Learning for Medical Images
arXiv:2302.05043 · doi:10.1007/s11633-022-1406-4
Abstract
Over the last decade, supervised deep learning on manually annotated big data has been progressing significantly on computer vision tasks. But the application of deep learning in medical image analysis was limited by the scarcity of high-quality annotated medical imaging data. An emerging solution is self-supervised learning (SSL), among which contrastive SSL is the most successful approach to rivalling or outperforming supervised learning. This review investigates several state-of-the-art contrastive SSL algorithms originally on natural images as well as their adaptations for medical images, and concludes by discussing recent advances, current limitations, and future directions in applying contrastive SSL in the medical domain.
Article links: https://link.springer.com/article/10.1007/s11633-022-1406-4
References in corpus (29)
- Bootstrap your own latent: A new approach to self-supervised Learning
- Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
- CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
- Learning Representations by Maximizing Mutual Information Across Views
- Self-Supervised Representation Learning: Introduction, Advances and Challenges
- Self-supervised learning methods and applications in medical imaging analysis: A survey
- Self-supervised driven consistency training for annotation efficient histopathology image analysis
- Self-supervised deep convolutional neural network for chest X-ray classification
- AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation
- Federated Contrastive Learning for Volumetric Medical Image Segmentation
- Self-Supervised Nuclei Segmentation in Histopathological Images Using Attention
- PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation
- COVID-19 Prognosis via Self-Supervised Representation Learning and Multi-Image Prediction
- A Study of the Generalizability of Self-Supervised Representations
- Cervical Optical Coherence Tomography Image Classification Based on Contrastive Self-Supervised Texture Learning
- Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels
- CAiD: Context-Aware Instance Discrimination for Self-supervised Learning in Medical Imaging
- Self-supervised Cross-silo Federated Neural Architecture Search
- Evaluating the Robustness of Self-Supervised Learning in Medical Imaging
- Pose from Action: Unsupervised Learning of Pose Features based on Motion
- Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
- Self-Supervised Learning for 3D Medical Image Analysis using 3D SimCLR and Monte Carlo Dropout
- Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers
- Dive into Self-Supervised Learning for Medical Image Analysis: Data, Models and Tasks
- DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning
- Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning
- Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning
- Aggregative Self-Supervised Feature Learning from a Limited Sample
- Resource and data efficient self supervised learning