Self-supervised learning methods and applications in medical imaging analysis: A survey

Abstract

The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its advancement. Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered an effective solution for the scarcity of annotated medical data. This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with a concentration on their applications in the field of medical imaging analysis. The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative, and contrastive approaches. Moreover, the article covers 40 of the most recent research papers in the field of self-supervised learning in medical imaging analysis aiming at shedding the light on the recent innovation in the field. Finally, the article concludes with possible future research directions in the field.

References in corpus (15)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Bootstrap your own latent: A new approach to self-supervised Learning
• Recent advances and clinical applications of deep learning in medical image analysis
• Contrastive Representation Learning: A Framework and Review
• Graph Self-Supervised Learning: A Survey
• Recent Advances in Autoencoder-Based Representation Learning
• High-Fidelity Image Generation With Fewer Labels
• PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation
• COVID-19 Prognosis via Self-Supervised Representation Learning and Multi-Image Prediction
• MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation
• A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
• Self-Supervised Learning for Spinal MRIs
• Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning
• Multimodal Transfer Learning-based Approaches for Retinal Vascular Segmentation

Cited by in corpus (11)

• Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis
• A Review of Predictive and Contrastive Self-supervised Learning for Medical Images
• Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic Problem
• Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation
• HSMix: Hard and Soft Mixing Data Augmentation for Medical Image Segmentation
• Mpox-AISM: AI-Mediated Super Monitoring for Mpox and Like-Mpox
• Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learning
• Edema Estimation From Facial Images Taken Before and After Dialysis via Contrastive Multi-Patient Pre-Training
• CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion
• Leveraging Modified Ex Situ Tomography Data for Segmentation of In Situ Synchrotron X-Ray Computed Tomography
• MultiMAE for Brain MRIs: Robustness to Missing Inputs Using Multi-Modal Masked Autoencoder