Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis

&NA; Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi‐supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not‐so‐supervised_a_survey_of_semi‐supervised_multi‐instance_and_transfer_learning_in_medical_image_analysis_/7479416.

• Publication year

  2018

• Venue

  Medical Image Anal.

• Publication date

  2018-04-17

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1016/j.media.2019.03.009arXiv 1804.06353PMID 30959445
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• DALSA: Domain Adaptation for Supervised Learning From Sparsely Annotated MR Images

  2024cited by this paper
• Domain Adaptation

  2020cited by this paper
• Semi-Supervised Learning

  2019cited by this paper
• An Overview of Multi-task Learning

  2018cited by this paper
• MS-Net: Mixed-Supervision Fully-Convolutional Networks for Full-Resolution Segmentation

  2018cited by this paper
• Places: A 10 Million Image Database for Scene Recognition

  2018cited by this paper
• Cats or CAT scans: transfer learning from natural or medical image source datasets?

  2018cited by this paper
• GENERATIVE ADVERSARIAL NETS

  2018cited by this paper
• Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications

  2018influential reference
• Knowledge transfer for melanoma screening with deep learning

  2017cited by this paper
• Deep features for breast cancer histopathological image classification

  2017cited by this paper
• Feature selection and thyroid nodule classification using transfer learning

  2017cited by this paper
• Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

  2017cited by this paper
• Comparison of breast DCE-MRI contrast time points for predicting response to neoadjuvant chemotherapy using deep convolutional neural network features with transfer learning

  2017cited by this paper
• Transfer Learning for Melanoma Detection: Participation in ISIC 2017 Skin Lesion Classification Challenge

  2017cited by this paper
• Towards Alzheimer's disease classification through transfer learning

  2017cited by this paper
• Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation

  2017cited by this paper
• Low quality dermal image classification using transfer learning

  2017cited by this paper
• Exploiting the potential of unlabeled endoscopic video data with self-supervised learning

  2017cited by this paper
• Automatic Scoring of Multiple Semantic Attributes With Multi-Task Feature Leverage: A Study on Pulmonary Nodules in CT Images

  2017influential reference
• A survey on deep learning in medical image analysis

  2017cited by this paper
• Transfer Learning for Multicenter Classification of Chronic Obstructive Pulmonary Disease

  2017cited by this paper
• Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II

  2017cited by this paper
• Exploring transfer learning for gastrointestinal bleeding detection on small-size imbalanced endoscopy images

  2017cited by this paper
• A transfer learning approach for classification of clinical significant prostate cancers from mpMRI scans

  2017influential reference
• Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation

  2017cited by this paper
• Negative results in computer vision: A perspective

  2017cited by this paper
• Constrained Deep Weak Supervision for Histopathology Image Segmentation

  2017cited by this paper
• Bladder cancer treatment response assessment using deep learning in CT with transfer learning

  2017cited by this paper
• Transfer learning from RF to B-mode temporal enhanced ultrasound features for prostate cancer detection

  2017cited by this paper
• Deep Learning with Permutation-invariant Operator for Multi-instance Histopathology Classification

  2017cited by this paper
• Semi-supervised Deep Learning for Fully Convolutional Networks

  2017cited by this paper
• Thoracic Disease Identification and Localization with Limited Supervision

  2017cited by this paper
• Who Said What: Modeling Individual Labelers Improves Classification

  2017cited by this paper
• MR Acquisition-Invariant Representation Learning

  2017cited by this paper
• Semi-supervised Learning for Biomedical Image Segmentation via Forest Oriented Super Pixels(Voxels)

  2017cited by this paper
• Epithelium-Stroma Classification via Convolutional Neural Networks and Unsupervised Domain Adaptation in Histopathological Images

  2017cited by this paper
• Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-task Learning

  2017cited by this paper
• A deep learning approach for the analysis of masses in mammograms with minimal user intervention

  2017cited by this paper
• Multisource Transfer Learning With Convolutional Neural Networks for Lung Pattern Analysis

  2017cited by this paper
• Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training

  2017cited by this paper
• Multiple instance learning for age-related macular degeneration diagnosis in optical coherence tomography images

  2017cited by this paper
• Automatic Detection and Classification of Colorectal Polyps by Transferring Low-Level CNN Features From Nonmedical Domain

  2017cited by this paper
• Multiple-Instance Learning for Medical Image and Video Analysis

  2017influential reference
• Joint Weakly and Semi-Supervised Deep Learning for Localization and Classification of Masses in Breast Ultrasound Images

  2017cited by this paper
• Exploring texture Transfer Learning for Colonic Polyp Classification via Convolutional Neural Networks

  2017cited by this paper
• GP-Unet: Lesion Detection from Weak Labels with a 3D Regression Network

  2017cited by this paper
• Simple domain adaptation for cross-dataset analyses of brain MRI data

  2017cited by this paper
• Direct aneurysm volume estimation by multi-view semi-supervised manifold learning

  2017cited by this paper
• Liver Fibrosis Classification Based on Transfer Learning and FCNet for Ultrasound Images

  2017cited by this paper
• An Overview of Multi-Task Learning in Deep Neural Networks

  2017cited by this paper
• Medical Image Description Using Multi-task-loss CNN

  2016cited by this paper
• Self-Transfer Learning for Weakly Supervised Lesion Localization

  2016cited by this paper
• Learning under Distributed Weak Supervision

  2016cited by this paper
• Neuron Segmentation Based on CNN with Semi-Supervised Regularization

  2016cited by this paper
• Asymmetric similarity-weighted ensembles for image segmentation

  2016cited by this paper
• Understanding the Mechanisms of Deep Transfer Learning for Medical Images

  2016cited by this paper
• Domain Adaptive Classification for Compensating Variability in Histopathological Whole Slide Images

  2016cited by this paper
• Scale-Invariant Feature Learning using Deconvolutional Neural Networks for Weakly-Supervised Semantic Segmentation

  2016cited by this paper
• Digital mammographic tumor classification using transfer learning from deep convolutional neural networks

  2016cited by this paper
• Active learning based segmentation of Crohns disease from abdominal MRI

  2016cited by this paper
• Early Experiences with Crowdsourcing Airway Annotations in Chest CT

  2016cited by this paper
• Multi-Instance Deep Learning: Discover Discriminative Local Anatomies for Bodypart Recognition

  2016cited by this paper
• Learning from Experts: Developing Transferable Deep Features for Patient-Level Lung Cancer Prediction

  2016cited by this paper
• Computerized breast cancer analysis system using three stage semi-supervised learning method

  2016cited by this paper
• Multi-source Transfer Learning with Convolutional Neural Networks for Lung Pattern Analysis

  2016cited by this paper
• Subcategory Classifiers for Multiple-Instance Learning and Its Application to Retinal Nerve Fiber Layer Visibility Classification

  2016cited by this paper
• Self-Transfer Learning for Fully Weakly Supervised Object Localization

  2016influential reference
• Domain adaptation for Alzheimer's disease diagnostics

  2016cited by this paper
• AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images

  2016cited by this paper
• Center-Focusing Multi-task CNN with Injected Features for Classification of Glioma Nuclear Images

  2016cited by this paper
• Unsupervised domain adaptation in brain lesion segmentation with adversarial networks

  2016cited by this paper
• Deep Learning for Multi-Task Medical Image Segmentation in Multiple Modalities

  2016cited by this paper
• Transfer Learning for Endoscopic Image Classification

  2016cited by this paper
• Interactive Cell Segmentation Based on Active and Semi-Supervised Learning

  2016cited by this paper
• Semi-supervised learning of anatomical manifolds for atlas-based segmentation of medical images

  2016cited by this paper
• Semisupervised learning using denoising autoencoders for brain lesion detection and segmentation

  2016influential reference
• Mass detection in digital breast tomosynthesis: Deep convolutional neural network with transfer learning from mammography.

  2016cited by this paper
• Multi-instance multi-label learning for whole slide breast histopathology

  2016cited by this paper
• Supervised domain adaptation of decision forests: Transfer of models trained in vitro for in vivo intravascular ultrasound tissue characterization

  2016cited by this paper
• On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis

  2016cited by this paper
• Transfer learning of a convolutional neural network for HEp-2 cell image classification

  2016cited by this paper
• Deep transfer learning of virtual endoluminal views for the detection of polyps in CT colonography

  2016cited by this paper
• Semi-supervised Hierarchical Multimodal Feature and Sample Selection for Alzheimer's Disease Diagnosis

  2016cited by this paper
• Multiple instance learning: A survey of problem characteristics and applications

  2016cited by this paper
• Scalable Unsupervised Domain Adaptation for Electron Microscopy

  2016cited by this paper
• Towards Automated Melanoma Screening: Exploring Transfer Learning Schemes

  2016cited by this paper
• Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

  2016cited by this paper
• Combining multiple expert annotations using semi-supervised learning and graph cuts for medical image segmentation

  2016cited by this paper
• Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks

  2016influential reference
• Multiple Instance Learning

  2016cited by this paper
• Four challenges in medical image analysis from an industrial perspective

  2016cited by this paper
• Machine learning approaches in medical image analysis: From detection to diagnosis

  2016cited by this paper
• Optimizing area under the ROC curve using semi-supervised learning

  2015cited by this paper
• Domain Adaptation for Microscopy Imaging

  2015cited by this paper
• Label Stability in Multiple Instance Learning

  2015cited by this paper
• Patch-Based Convolutional Neural Network for Whole Slide Tissue Image Classification

  2015cited by this paper
• Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects

  2015cited by this paper
• Simpler Non-Parametric Methods Provide as Good or Better Results to Multiple-Instance Learning

  2015cited by this paper
• Semi-Supervised Nearest Mean Classification Through a Constrained Log-Likelihood

  2015cited by this paper

• Semi-supervised dual-teacher comparative learning with bidirectional balanced copy-paste for medical image segmentation

  2026cites this paper
• Improving generalization of polyp detection via conditional StyleGAN augmented training

  2026cites this paper
• VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation

  2026cites this paper
• Towards Segmenting the Invisible: An End-to-End Registration and Segmentation Framework for Weakly Supervised Tumour Analysis

  2026cites this paper
• Application of deep learning on MRI for prognostic prediction in rectal cancer.

  2026cites this paper
• Wavelet-Based Frequency Replacement and Edge Enhancement for Semi-Supervised Fetal Ultrasound Image Segmentation.

  2026cites this paper
• Closed loop text guided framework for lung cancer lesion segmentation and quantification.

  2026cites this paper
• Advances in Deep Learning Applications for Choroidal Images Analysis: A Narrative Review

  2026cites this paper
• Enhancing Deep Boosting Algorithm Performance for Panic Disorder Detection Through Biometric and Spatio-Temporal Data Integration

  2026cites this paper
• Comparison of conventional 512-matrix CT images with Swin2SR-based 2048-matrix images in the visualization and diagnosis of lung nodules

  2026cites this paper
• Machine Learning-Based Multiscale Geomechanical Modeling

  2026cites this paper
• A hybrid Transformer-CNN framework for uncertainty-guided semi-supervised multiclass eye disease classification with enhanced interpretability

  2026cites this paper
• Transcriptomic-guided whole-slide image classification for molecular subtype identification

  2026cites this paper
• Weakly Supervised Deep Learning for Ocular Image Segmentation: A Systematic Review of Fundus and OCT Methods

  2026cites this paper
• AutoPromptSeg: Automated Decoupling of Uncertainty Prompts with SAM for semi-supervised medical image segmentation

  2026cites this paper
• MICCAI STS 2024 challenge: Semi-supervised instance-level tooth segmentation in panoramic X-ray and CBCT images.

  2026cites this paper
• Learning with less: A survey of deep learning in medical imaging under varying supervision levels

  2026cites this paper
• Pathomics Signature for Prognosis and CA19-9 Interception in Pancreatic Ductal Adenocarcinoma: A Real-Life, Multi-Center Study.

  2026cites this paper
• Structured Prompt-Guided Segmentation of Enhanced CT Images for Predicting Lateral Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma

  2026cites this paper
• Significance of unifying semi and self-supervision for the radical improvement of medical imaging: a collaborative research effort

  2026cites this paper
• Attention Mechanisms in U-Net Variants for Brain MRI Segmentation: A Narrative Review of Spatial, Channel, and Transformer-Based Approaches

  2025cites this paper
• Spine endoscopic atlas: an open-source dataset for surgical instrument segmentation

  2025cites this paper
• DTSC-Net: Dual-Teacher Semi-Supervised Segmentation with Structural Consistency and Prompted SAM*

  2025cites this paper
• Research on the identification of Ziziphi Spinosae semen and its adulterants based on the fusion of hyperspectral technology and transfer learning.

  2025cites this paper
• Improving skull-stripping for infant MRI via weakly supervised domain adaptation using adversarial learning

  2025cites this paper
• Diffusion-based vision-language model for zero-shot anomaly detection in medical images

  2025cites this paper
• Photonic Biosensors based on Nanoparticle Superstructures: from Data Analysis to Artificial Intelligence (AI) Detection

  2025cites this paper
• Unlabeled Insight, Labeled Boost: Contrastive Learning and Class-Adaptive Pseudo-Labeling for Semi-Supervised Medical Image Classification

  2025cites this paper
• Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation

  2025cites this paper
• Click, Predict, Trust: Clinician-in-the-Loop AI Segmentation for Lung Cancer CT-Based Prognosis within the Knowledge-to-Action Framework

  2025cites this paper
• A hybrid model for brain tumor classification via deep feature extraction and optimized classifier weighting

  2025cites this paper
• Large Language Models in Medical Image Analysis: A Systematic Survey and Future Directions

  2025cites this paper
• SingleStrip: learning skull-stripping from a single labeled example

  2025cites this paper
• Unveiling hidden risks: A Holistically-Driven Weak Supervision framework for ultra-short-term ACS prediction using CCTA

  2025cites this paper
• Artificial Intelligence for Response Assessment in Pediatric Neuro-Oncology (AI-RAPNO), part 2: challenges, opportunities, and recommendations for clinical translation.

  2025cites this paper
• Machine Learning in Nursing: A Cross-Disciplinary Review

  2025cites this paper
• Machine Learning for Chronic Kidney Disease Detection from Planar and SPECT Scintigraphy: A Scoping Review

  2025cites this paper
• Enhancing Radiomic Feature Robustness Through Voxel Spacing-Aware Extraction in Anisotropic CT Data

  2025cites this paper
• All-in-One Multi-Organ Segmentation in 3D CT Images via Self-Supervised and Cross-Dataset Learning

  2025cites this paper
• RAIL: Region-Aware Instructive Learning for Semi-Supervised Tooth Segmentation in CBCT

  2025cites this paper
• Using Foundation Models as Pseudo-Label Generators for Pre-Clinical 4D Cardiac CT Segmentation

  2025cites this paper
• Uncertainty-guided weakly supervised segmentation of cardiac substructures with adapter fine-tuning and Fourier feature extraction

  2025cites this paper
• THPFF: A tensor-based high-precision feature fusion model for multi-source data in smart healthcare systems

  2025cites this paper
• An EEG Screening Method for Severe Obstructive Sleep Apnea Based on Limited Penetrable Difference Visibility Graph and Graph Convolutional Network

  2025cites this paper
• Lessons learned from RadiologyNET foundation models for transfer learning in medical radiology

  2025cites this paper
• PedSemiSeg: Pedagogy-inspired semi-supervised polyp segmentation

  2025cites this paper
• Semi-supervised learning for linear extremile regression

  2025cites this paper
• Beyond Manual Annotation: A Human-AI Collaborative Framework for Medical Image Segmentation Using Only "Better or Worse" Expert Feedback

  2025cites this paper
• Explainable artificial intelligence for medical imaging systems using deep learning: a comprehensive review

  2025cites this paper
• Non-parametric prediction of brain MRI microstructure using transfer learning

  2025cites this paper
• Methodology for a fully automated pipeline of AI-based body composition tools for abdominal CT

  2025cites this paper
• Hybrid VGG16 and Vision Transformer Approach for Breast Cancer Classification in Ultrasound Imaging with Explainable AI

  2025cites this paper
• ERSR: An Ellipse-constrained pseudo-label refinement and symmetric regularization framework for semi-supervised fetal head segmentation in ultrasound images

  2025cites this paper
• Integration of Artificial Intelligence in Laryngeal Cancer Diagnosis and Prognosis: A Comparative Analysis Bridging Traditional Medical Practices with Modern Computational Techniques

  2025cites this paper
• DeepNeuroScan: Advanced CNN Architecture for Precise Brain Tumor Identification in Medical Imaging

  2025cites this paper
• ModelX : A Novel Transfer Learning Approach Across Heterogeneous Datasets

  2025cites this paper
• A review and systematic guide to counteracting medical data scarcity for AI applications

  2025cites this paper
• AttriGen: Automated Multi-Attribute Annotation for Blood Cell Datasets

  2025cites this paper
• How Accurate Is AI in Detecting Marginal Jaw Bone Loss? A Systematic Review and Meta-Analysis.

  2025cites this paper
• SAM2-3dMed: Empowering SAM2 for 3D Medical Image Segmentation

  2025cites this paper
• Private Data Incrementalization: Data-Centric Model Development for Clinical Liver Segmentation

  2025cites this paper
• Applying machine learning for perioperative adverse event prediction: a narrative review toward better clinical efficacy and usability

  2025cites this paper
• A CT-Based Deep Learning Radiomics Nomogram for Early Recurrence Prediction in Pancreatic Cancer: A Multicenter Study

  2025cites this paper
• Artificial intelligence in early screening for esophageal squamous cell carcinoma.

  2025cites this paper
• Limitations of nomogram models in predicting survival outcomes for glioma patients

  2025cites this paper
• Neighbor-Guided Unbiased Framework for Generalized Category Discovery in Medical Image Classification

  2025cites this paper
• Retrieval Augmented Medical Diagnosis System

  2025cites this paper
• A comprehensive review of artificial intelligence - based algorithm towards fetal facial anomalies detection (2013–2024)

  2025cites this paper
• Automatic maxillary sinus segmentation and age estimation model for the northwestern Chinese Han population

  2025cites this paper
• Development of a deep learning radiomics model combining lumbar CT, multi-sequence MRI, and clinical data to predict high-risk cage subsidence after lumbar fusion: a retrospective multicenter study

  2025cites this paper
• A self-supervised representation learning paradigm with global content perception and peritumoral context restoration for MRI breast tumor segmentation

  2025cites this paper
• Semantic segmentation dataset authoring with simplified labels

  2025cites this paper
• A unified approach to medical image segmentation by leveraging mixed supervision and self and transfer learning (MIST)

  2025cites this paper
• Deep learning-based image analysis in muscle histopathology using photo-realistic synthetic data

  2025cites this paper
• A semi-supervised domain adaptive medical image segmentation method based on dual-level multi-scale alignment

  2025cites this paper
• See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias

  2025cites this paper
• Comprehensive Survey on Computational Techniques for Brain Tumor Detection: Past, Present and Future

  2025cites this paper
• Enhanced Brain Tumor Detection via ResNet50 Classification and Residual U-Net Segmentation

  2025cites this paper
• Retinal OCT image segmentation with deep learning: A review of advances, datasets, and evaluation metrics

  2025cites this paper
• Single-Slice Semi-Supervised 3D Medical Image Segmentation via Correlation Information Enhancement and Hybrid Pseudo Mask Generation

  2025cites this paper
• Deep Learning Approaches for Medical Imaging Under Varying Degrees of Label Availability: A Comprehensive Survey

  2025cites this paper
• Weakly Semi-supervised Whole Slide Image Classification by Two-level Cross Consistency Supervision

  2025cites this paper
• Distribution-Aware Multi-Attention Tri-branch Networks with Feedforward Differential Features for semi-supervised medical image segmentation

  2025cites this paper
• Self-supervision enhances instance-based multiple instance learning methods in digital pathology: a benchmark study

  2025cites this paper
• SegQC: a segmentation network-based framework for multi-metric segmentation quality control and segmentation error detection in volumetric medical images

  2025cites this paper
• Evaluating Data Augmentation Strategies for Robust Cross-Dataset Generalization in Wound Classification

  2025cites this paper
• DeepSystem: The Effect of the Optimized Deep Learning and Blurring Filters on the Automated Detection of Pneumonia Using X-ray Images

  2025cites this paper
• Exploring interpretable echo analysis using self-supervised parcels

  2025cites this paper
• Developing a Deep Learning Radiomics Model Combining Lumbar CT, Multi-Sequence MRI, and Clinical Data to Predict High-Risk Adjacent Segment Degeneration Following Lumbar Fusion: A Retrospective Multicenter Study

  2025cites this paper
• A Quad-Step Approach to Uncertainty-Aware Deep Learning for Skin Cancer Classification

  2025cites this paper
• Augmented Multiple Perturbation Dual Mean Teacher Model for Semi‐Supervised Intracranial Haemorrhage Segmentation

  2025cites this paper
• Update of machine learning for ultrasound diagnosis of metabolic dysfunction-associated steatotic liver disease: a bright future for deep learning

  2025cites this paper
• Advancements in deep learning and explainable artificial intelligence for enhanced medical image analysis: A comprehensive survey and future directions

  2025cites this paper
• A Review on the Applications of Machine Learning in Biomaterials, Biomechanics, and Biomanufacturing for Tissue Engineering

  2025cites this paper
• Annotation Ambiguity Aware Semi-Supervised Medical Image Segmentation

  2025cites this paper
• Computational and Imaging Approaches for Precision Characterization of Bone, Cartilage, and Synovial Biomolecules

  2025cites this paper
• SoK: Private Knowledge Sharing in Distributed Learning

  2025cites this paper
• Mitigating Multi-Sequence 3D Prostate MRI Data Scarcity through Domain Adaptation using Locally-Trained Latent Diffusion Models for Prostate Cancer Detection

  2025cites this paper
• Diffusion model for medical image denoising, reconstruction and translation

  2025cites this paper
• Identification of benign and malignant breast nodules on ultrasound: comparison of multiple deep learning models and model interpretation

  2025cites this paper