Deep Learning Approaches for Medical Imaging Under Varying Degrees of Label Availability: A Comprehensive Survey

2025/04/15 by Siteng Ma, Ma, Siteng, Honghui Du +13 · 1 citation
Computer Science · Medicine · #68T07 #68T45 #92C50 #92C55 #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Deep learning #FOS: Computer and information sciences #Field (mathematics) #I.2.10 #I.4.5 #I.4.6 #I.4.9 #Interpretation (philosophy) #J.3 #Machine Learning and Data Classification #Medical imaging #Medical research

paper · pdf · doi:10.48550/arxiv.2504.11588

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/04/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Deep learning has achieved significant breakthroughs in medical imaging, but these advancements are often dependent on large, well-annotated datasets. However, obtaining such datasets poses a significant challenge, as it requires time-consuming and labor-intensive annotations from medical experts. Consequently, there is growing interest in learning paradigms such as incomplete, inexact, and absent supervision, which are designed to operate under limited, inexact, or missing labels. This survey categorizes and reviews the evolving research in these areas, analyzing around 600 notable contributions since 2018. It covers tasks such as image classification, segmentation, and detection across various medical application areas, including but not limited to brain, chest, and cardiac imaging. We attempt to establish the relationships among existing research studies in related areas. We provide formal definitions of different learning paradigms and offer a comprehensive summary and interpretation of various learning mechanisms and strategies, aiding readers in better understanding the current research landscape and ideas. We also discuss potential future research challenges.

Citations

• Additional Positive Enables Better Representation Learning for Medical Images
• Less is More: Unsupervised Mask-guided Annotated CT Image Synthesis with Minimum Manual Segmentations
• Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection
• Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation
• Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation
• MSCDA: Multi-level Semantic-guided Contrast Improves Unsupervised Domain Adaptation for Breast MRI Segmentation in Small Datasets
• MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery
• S³R: Self-supervised Spectral Regression for Hyperspectral Histopathology Image Classification
• Warm Start Active Learning with Proxy Labels & Selection via Semi-Supervised Fine-Tuning
• Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
• Transformer-based unsupervised contrastive learning for histopathological image classification
• MaNi: Maximizing Mutual Information for Nuclei Cross-Domain Unsupervised Segmentation
• MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels
• BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
• Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer
• Masked Autoencoders Are Scalable Vision Learners
• Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation
• Generative Adversarial Networks
• Duo-SegNet: Adversarial Dual-Views for Semi-Supervised Medical Image Segmentation
• A Spatial Guided Self-supervised Clustering Network for Medical Image Segmentation
• Federated Semi-supervised Medical Image Classification via Inter-client Relation Matching
• Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification
• Positional Contrastive Learning for Volumetric Medical Image Segmentation
• Learning to Segment From Scribbles Using Multi-Scale Adversarial Attention Gates
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• Learning Transferable Visual Models From Natural Language Supervision
• Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning
• Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
• WeGleNet: A Weakly-Supervised Convolutional Neural Network for the Semantic Segmentation of Gleason Grades in Prostate Histology Images
• Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency
• Targeted Self Supervision for Classification on a Small COVID-19 CT Scan Dataset
• SAR: Scale-Aware Restoration Learning for 3D Tumor Segmentation
• Contrastive Cross-Modal Pre-Training: A General Strategy for Small Sample Medical Imaging
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
• Semi-supervised Medical Image Segmentation through Dual-task Consistency
• A Survey of Deep Active Learning
• Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
• Suggestive Annotation of Brain Tumour Images with Gradient-guided Sampling
• Contrastive learning of global and local features for medical image segmentation with limited annotations
• 3D Self-Supervised Methods for Medical Imaging
• Semi-supervised Medical Image Classification with Global Latent Mixing
• Semi-Supervised Medical Image Classification With Relation-Driven Self-Ensembling Model
• Deeply Supervised Active Learning for Finger Bones Segmentation
• Deep-COVID: Predicting COVID-19 From Chest X-Ray Images Using Deep Transfer Learning
• FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
• A Simple Framework for Contrastive Learning of Visual Representations
• Localization of Critical Findings in Chest X-Ray without Local Annotations Using Multi-Instance Learning
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• CHAOS Challenge - combined (CT-MR) healthy abdominal organ segmentation
• Momentum Contrast for Unsupervised Visual Representation Learning
• Momentum Contrast for Unsupervised Visual Representation Learning
• Uncertainty guided semi-supervised segmentation of retinal layers in OCT images
• Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations
• A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis
• Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube
• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation
• Automated Muscle Segmentation from Clinical CT using Bayesian U-Net for Personalized Musculoskeletal Modeling
• Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
• Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction
• Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation
• Weakly Supervised Object Detection with 2D and 3D Regression Neural Networks
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation
• InfoMask: Masked Variational Latent Representation to Localize Chest Disease
• Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
• Generative Image Translation for Data Augmentation of Bone Lesion Pathology
• A Style-Based Generator Architecture for Generative Adversarial Networks
• A Style-Based Generator Architecture for Generative Adversarial Networks
• Deep Learning with Mixed Supervision for Brain Tumor Segmentation
• 3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training
• Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
• Unsupervised Identification of Disease Marker Candidates in Retinal OCT Imaging Data
• MedAL: Deep Active Learning Sampling Method for Medical Image Analysis
• Representation Learning with Contrastive Predictive Coding
• Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?
• Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis
• Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training
• mixup: Beyond Empirical Risk Minimization
• Joint Weakly and Semi-Supervised Deep Learning for Localization and Classification of Masses in Breast Ultrasound Images
• A Closer Look at Memorization in Deep Networks
• ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• A Survey on Deep Learning in Medical Image Analysis
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Temporal Ensembling for Semi-Supervised Learning
• Improved Techniques for Training GANs
• Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest
• Learning Deep Features for Discriminative Localization
• Domain-Adversarial Training of Neural Networks
• SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
• Bayesian Active Learning for Classification and Preference Learning
• A Survey on Transfer Learning
• Domain Adaptation via Transfer Component Analysis
• Solving the multiple instance problem with axis-parallel rectangles

Related

• An overview of deep learning in medical imaging
• Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directions
• Data efficient deep learning for medical image analysis: A survey
• Deep Learning for Medical Image Processing: Overview, Challenges and Future
• Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions