Artificial intelligence and machine learning for medical imaging: A technology review
Искусственный интеллект и машинное обучение для медицинской визуализации: обзор технологий
2021-03-01
SCID: 54.1/bj4m5yn7
Discuss with AI
artificial intelligenceimage classificationimage segmentationmachine learningmedical imaging
Figures from the paper
Abstract (AI)
Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.
Key Findings
1
AI methods are becoming ubiquitous in medical image analysis workflows and are paving the way for clinical implementation of AI-based solutions.
2
AI, driven by advances in image analysis, has become widely applied in medical imaging specialties such as radiology, pathology, and oncology.
3
Machine learning methods are now mainstream tools for medical imaging tasks including diagnosis, segmentation, and classification.
4
Safe and efficient clinical use of AI depends partly on practitioners being informed about the underlying technologies and methods.
5
The review presents fundamental AI technologies, state-of-the-art methods, applications to medical imaging, and discusses new trends and future research directions.
Research Object
Medical imaging (clinical image data and analysis workflows)
Research Subject
Application and state-of-the-art of artificial intelligence and machine learning methods for image analysis tasks (diagnosis, segmentation, classification), including technological foundations, trends, and implications for clinical implementation
Publication Details
Publication Date
2021-03-01
Journal
Publisher
ISSN
Cited by
458
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai13
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
Image-to-Image Translation with Conditional Adversarial Networks2017
Reducing the Dimensionality of Data with Neural Networks2006
Generative adversarial networks2020
The FAIR Guiding Principles for scientific data management and stewardship2016
A survey on Image Data Augmentation for Deep Learning2019
Dissecting racial bias in an algorithm used to manage the health of populations2019
The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)2014
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning2016
UNETR: Transformers for 3D Medical Image Segmentation2022
Text Data Augmentation for Deep Learning2021
Deep Learning for Accurate Diagnosis of Liver Tumor Based on Magnetic Resonance Imaging and Clinical Data2020
Qualitative Spatial Reasoning over Questions (Short Paper)2022