A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises

Abstract

Since its renaissance, deep learning has been widely used in various medical imaging tasks and has achieved remarkable success in many medical imaging applications, thereby propelling us into the so-called artificial intelligence (AI) era. It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing. However, medical imaging presents unique challenges that confront deep learning approaches. In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues. We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc. Then, we present several case studies that are commonly found in clinical practice, including digital pathology and chest, brain, cardiovascular, and abdominal imaging. Rather than presenting an exhaustive literature survey, we instead describe some prominent research highlights related to these case study applications. We conclude with a discussion and presentation of promising future directions.

20 pages, 7 figures

References in corpus (6)

• Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
• DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy
• Relational Modeling for Robust and Efficient Pulmonary Lobe Segmentation in CT Scans
• Fully Automated Myocardial Strain Estimation from CMR Tagged Images using a Deep Learning Framework in the UK Biobank
• Deep Small Bowel Segmentation with Cylindrical Topological Constraints

Cited by in corpus (39)

• Self-supervised learning methods and applications in medical imaging analysis: A survey
• Knowledge Matters: Radiology Report Generation with General and Specific Knowledge
• Is attention all you need in medical image analysis? A review
• LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation
• Automated Radiology Report Generation: A Review of Recent Advances
• You Only Learn Once: Universal Anatomical Landmark Detection
• Quantifying the unknown impact of segmentation uncertainty on image-based simulations
• Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study
• Cross-Modal Causal Intervention for Medical Report Generation
• Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
• Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs
• Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI
• Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and Demonstration with Hyper Suprime-Cam Data
• Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence
• RPLHR-CT Dataset and Transformer Baseline for Volumetric Super-Resolution from CT Scans
• Medical Image Segmentation using LeViT-UNet++: A Case Study on GI Tract Data
• Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets
• Meta-learning in healthcare: A survey
• GLIMS: Attention-Guided Lightweight Multi-Scale Hybrid Network for Volumetric Semantic Segmentation
• A Self Supervised StyleGAN for Image Annotation and Classification with Extremely Limited Labels
• CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detection
• Coronary Artery Disease Classification with Different Lesion Degree Ranges based on Deep Learning
• Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learning
• Precision-medicine-toolbox: An open-source python package for facilitation of quantitative medical imaging and radiomics analysis
• How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
• Meta-hallucinator: Towards Few-Shot Cross-Modality Cardiac Image Segmentation
• Combining Federated Learning and Control: A Survey
• Robust and Explainable Framework to Address Data Scarcity in Diagnostic Imaging
• Muographic Image Upsampling with Machine Learning for Built Infrastructure Applications
• Microwave lymphedema assessment using deep learning with contour assisted backprojection
• Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classification
• From Nano to Macro: Overview of the IEEE Bio Image and Signal Processing Technical Committee
• Fast Marching Energy CNN
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• CoRPA: Adversarial Image Generation for Chest X-rays Using Concept Vector Perturbations and Generative Models
• KEVS: Enhancing Segmentation of Visceral Adipose Tissue in Pre-Cystectomy CT with Gaussian Kernel Density Estimation
• Multi-cancer detection using a computationally efficient CNN with transfer learning
• A robust multi-domain network for short-scanning amyloid PET reconstruction
• Chromatic and spatial analysis of one-pixel attacks against an image classifier