4.6 Review

Artificial Intelligence to Reduce or Eliminate the Need for Gadolinium-Based Contrast Agents in Brain and Cardiac MRI A Literature Review

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Radiology, Nuclear Medicine & Medical Imaging

Simultaneous T1, T2, and T1ρ cardiac magnetic resonance fingerprinting for contrast agent-free myocardial tissue characterization

Carlos Velasco et al.

Summary: The study introduced a novel cardiac MRF approach for simultaneous quantification of myocardial T-1, T-2, and T-1 rho in a single breath-hold MR scan, showing good agreement with reference spin echo measurements and conventional clinical maps in healthy subjects and phantom studies.

MAGNETIC RESONANCE IN MEDICINE (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Can Deep Learning Replace Gadolinium in Neuro-Oncology? A Reader Study

Samy Ammari et al.

Summary: The study successfully predicted surrogate images for contrast-enhanced T1 from multiparametric MRI using a deep learning method, indicating the potential to reduce gadolinium exposure while maintaining good lesion detection performance.

INVESTIGATIVE RADIOLOGY (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

From Dose Reduction to Contrast Maximization Can Deep Learning Amplify the Impact of Contrast Media on Brain Magnetic Resonance Image Quality? A Reader Study

Alexandre Bone et al.

Summary: The aim of this study was to evaluate a deep learning method that enhances the contrast-to-noise ratio in contrast-enhanced gradient echo T1 weighted brain MRI. The processed images showed superior contrast and lesion detection performance compared to the original images, and the proposed processing method improved the sensitivity of gradient echo T1 MRI. Overall, the deep learning method successfully amplified the beneficial effects of contrast agent injection on image quality and lesion detection performance.

INVESTIGATIVE RADIOLOGY (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep learning-based 3D MRI contrast-enhanced synthesis from a 2D noncontrast T2Flair sequence

Yulin Wang et al.

Summary: This study proposed a deep learning framework to synthesize 3D full-contrast MR images from 2D images, addressing the issues caused by GBCAs injection. The improved network showed excellent performance in quantitative and qualitative evaluations, instilling high confidence in diagnosis.

MEDICAL PHYSICS (2022)

Review Pharmacology & Pharmacy

Synthetic Post-Contrast Imaging through Artificial Intelligence: Clinical Applications of Virtual and Augmented Contrast Media

Luca Pasquini et al.

Summary: The development of 'virtual' and 'augmented' contrasts in biomedical imaging using artificial intelligence techniques has enabled the generation of synthetic post-contrast images through computational modeling, reducing the risks and limitations associated with traditional contrast media in clinical practice.

PHARMACEUTICS (2022)

Article Cardiac & Cardiovascular Systems

Artificial Intelligence for Contrast-Free MRI: Scar Assessment in Myocardial Infarction Using Deep Learning-Based Virtual Native Enhancement

Qiang Zhang et al.

Summary: A new technology called VNE has been developed for noninvasive assessment of myocardial scars. VNE uses artificial intelligence to generate virtual images similar to late gadolinium enhancement (LGE) without the need for contrast agents. The study showed that VNE provided high-quality images and had strong agreement with LGE in quantifying scar size and transmurality, as well as good visuospatial agreement with histopathology.

CIRCULATION (2022)

Article Computer Science, Artificial Intelligence

A Deep Learning Segmentation Pipeline for Cardiac T1 Mapping Using MRI Relaxation-based Synthetic Contrast Augmentation

Nitish Bhatt et al.

Summary: This study designed and evaluated an automated deep learning method for segmentation and analysis of cardiac MRI T1 maps using synthetic T1-weighted images. The method showed accurate results in T1 and ECV analysis across different abnormalities, centers, scanners, and T1 sequences.

RADIOLOGY-ARTIFICIAL INTELLIGENCE (2022)

Article Computer Science, Artificial Intelligence

Clinical Assessment of Deep Learning-based Super-Resolution for 3D Volumetric Brain MRI

Jeffrey D. Rudie et al.

Summary: This study evaluated the application of AI-based image enhancement in clinical brain MRI and found that the AI-enhanced scans were noninferior to standard-of-care scans in terms of image quality. Quantitative analysis showed that the AI software restored the high spatial resolution of small structures. The study demonstrates that AI-based software can improve patient experience and scanner efficiency without sacrificing diagnostic quality.

RADIOLOGY-ARTIFICIAL INTELLIGENCE (2022)

Review Physics, Multidisciplinary

Explainable AI: A Review of Machine Learning Interpretability Methods

Pantelis Linardatos et al.

Summary: Recent advances in artificial intelligence have led to widespread industrial adoption, with machine learning systems demonstrating superhuman performance. However, the complexity of these systems has made them difficult to explain, hindering their application in sensitive domains. Therefore, there is a renewed interest in the field of explainable artificial intelligence.

ENTROPY (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Use of Intravenous Gadolinium-based Contrast Media in Patients with Kidney Disease: Consensus Statements from the American College of Radiology and the National Kidney Foundation

Jeffrey C. Weinreb et al.

Summary: This article summarizes the inaugural consensus statements developed and endorsed by the American College of Radiology and the National Kidney Foundation to standardize care for patients with kidney disease receiving intravenous gadolinium-based contrast media. The article highlights the low risk of nephrogenic systemic fibrosis from group II GBCM in advanced kidney disease patients, and emphasizes the need to balance potential harms and benefits when considering MRI with GBCM in patients with acute kidney injury or low eGFR.

RADIOLOGY (2021)

Article Oncology

Deep Learning Algorithm Trained with COVID-19 Pneumonia Also Identifies Immune Checkpoint Inhibitor Therapy-Related Pneumonitis

Carlo Augusto Mallio et al.

Summary: The distinction between ICI therapy-related pneumonitis and COVID-19 pneumonia using deep learning algorithm based on CT images is challenging, with limited specificity in differentiation but high accuracy in identifying ICI therapy-related pneumonitis compared to pneumonia-free controls. Awareness among clinicians about the imaging similarities between the two conditions is crucial.

CANCERS (2021)

Article Multidisciplinary Sciences

Using explainable machine learning to characterise data drift and detect emergent health risks for emergency department admissions during COVID-19

Christopher Duckworth et al.

Summary: The research demonstrates how explainable machine learning can monitor data drift and emerging health risks in healthcare settings. By training and evaluating models, two benefits were discovered that can help improve the accuracy of predicting patient hospital admission risk in emergency departments.

SCIENTIFIC REPORTS (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep learning-based methods may minimize GBCA dosage in brain MRI

Huanyu Luo et al.

Summary: The deep learning-based method showed accurate lesion detection in brain MRI exams with reduced GBCA dose, but may miss enhancement of small lesions in patients with multiple lesions. It is a feasible way to minimize GBCA dosage without sacrificing diagnostic information.

EUROPEAN RADIOLOGY (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

A generic deep learning model for reduced gadolinium dose in contrast-enhanced brain MRI

Srivathsa Pasumarthi et al.

Summary: A DL model was proposed for predicting contrast-enhanced brain MRI images at approximately 10% of the standard dose, with technical solutions to improve model robustness and generalizability. The model showed promising results in terms of peak signal-to-noise ratio, structural similarity, and consistency with radiologists' observations.

MAGNETIC RESONANCE IN MEDICINE (2021)

Article Cardiac & Cardiovascular Systems

Toward Replacing Late Gadolinium Enhancement With Artificial Intelligence Virtual Native Enhancement for Gadolinium-Free Cardiovascular Magnetic Resonance Tissue Characterization in Hypertrophic Cardiomyopathy

Qiang Zhang et al.

Summary: The study introduced a new CMR technology called VNE that can achieve LGE-like imaging without the need for contrast agent. VNE demonstrated high agreement with LGE in lesion distribution and quantification, while also providing significantly better image quality.

CIRCULATION (2021)

Editorial Material Cardiac & Cardiovascular Systems

Automated Noncontrast Myocardial Tissue Characterization for Hypertrophic Cardiomyopathy Holy Grail or False Prophet?

Charlotte H. Manisty et al.

CIRCULATION (2021)

Article Computer Science, Artificial Intelligence

Feasibility of Simulated Postcontrast MRI of Glioblastomas and Lower-Grade Gliomas by Using Three-dimensional Fully Convolutional Neural Networks

Evan Calabrese et al.

Summary: Simulated postcontrast T1-weighted brain MR images generated by a three-dimensional deep convolutional neural network were found to be similar to real acquired images in both quantitative and qualitative analysis, demonstrating high diagnostic accuracy.

RADIOLOGY-ARTIFICIAL INTELLIGENCE (2021)

Article Medical Informatics

Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study

Chandrakanth Jayachandran Preetha et al.

Summary: This study utilized deep convolutional neural networks to synthesize post-contrast T1-weighted MRI sequences from pre-contrast MRI for tumor response assessment in neuro-oncology. The synthetic sequences showed a strong linear relationship in tumor volume assessment compared to true sequences, and similar performance in predicting overall survival in patients.

LANCET DIGITAL HEALTH (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep Learning for Predicting Enhancing Lesions in Mu pie Sclerosis from Noncontrast MRI

Ponnada A. Narayana et al.

RADIOLOGY (2020)

Editorial Material Clinical Neurology

Gadolinium Deposition Safety: Seeking the Patient's Perspective

C. A. Mallio et al.

AMERICAN JOURNAL OF NEURORADIOLOGY (2020)

Review Engineering, Environmental

Anthropogenic gadolinium in freshwater and drinking water systems

Robert Bruenjes et al.

WATER RESEARCH (2020)

Article Environmental Sciences

Impact on gadolinium anomaly in river waters in Tokyo related to the increased number of MRI devices in use

Kazumasa Inoue et al.

MARINE POLLUTION BULLETIN (2020)

Article Cardiac & Cardiovascular Systems

2020 AHA/ACC Guideline for the Diagnosis and Treatment of Patients With Hypertrophic Cardiomyopathy

Steve R. Ommen et al.

JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY (2020)

Article Computer Science, Artificial Intelligence

Automated Myocardial T2 and Extracellular Volume Quantification in Cardiac MRI Using Transfer Learning-based Myocardium Segmentation

Yanjie Zhu et al.

RADIOLOGY-ARTIFICIAL INTELLIGENCE (2020)

Article Radiology, Nuclear Medicine & Medical Imaging

Can Virtual Contrast Enhancement in Brain MRI Replace Gadolinium? A Feasibility Study

Jens Kleesiek et al.

INVESTIGATIVE RADIOLOGY (2019)

Article Medicine, General & Internal

Magnetic Resonance Perfusion or Fractional Flow Reserve in Coronary Disease

Eike Nagel et al.

NEW ENGLAND JOURNAL OF MEDICINE (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep Learning for Diagnosis of Chronic Myocardial Infarction on Nonenhanced Cardiac Cine MRI

Nan Zhang et al.

RADIOLOGY (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

Gadolinium Deposition in the Brain in a Large Animal Model Comparison of Linear and Macrocyclic Gadolinium-Based Contrast Agents

Alexander Radbruch et al.

INVESTIGATIVE RADIOLOGY (2019)

Editorial Material Health Care Sciences & Services

Framing the challenges of artificial intelligence in medicine

Kun-Hsing Yu et al.

BMJ QUALITY & SAFETY (2019)

Review Medicine, General & Internal

Gadolinium Deposition in Neurology Clinical Practice

Tyler E. Smith et al.

OCHSNER JOURNAL (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI

Enhao Gong et al.

JOURNAL OF MAGNETIC RESONANCE IMAGING (2018)

Article Medicine, General & Internal

MRI-Guided Thrombolysis for Stroke with Unknown Time of Onset

G. Thomalla et al.

NEW ENGLAND JOURNAL OF MEDICINE (2018)

Review Radiology, Nuclear Medicine & Medical Imaging

Immediate Allergic Reactions to Gadolinium-based Contrast Agents: A Systematic Review and Meta-Analysis

Ashkan Heshmatzadeh Behzadi et al.

RADIOLOGY (2018)

Article Clinical Neurology

Gadolinium deposition in the brain: summary of evidence and recommendations

Vikas Gulani et al.

LANCET NEUROLOGY (2017)

Article Computer Science, Interdisciplinary Applications

Reconstruction of 7T-Like Images From 3T MRI

Khosro Bahrami et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2016)

Article Computer Science, Interdisciplinary Applications

q-Space Deep Learning: Twelve-Fold Shorter and Model-Free Diffusion MRI Scans

Vladimir Golkov et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2016)

Article Oncology

Brain metastatic volume and white matter lesions in advanced cancer patients

Carlo Cosimo Quattrocchi et al.

JOURNAL OF NEURO-ONCOLOGY (2013)

Article Urology & Nephrology

Nephrogenic systemic fibrosis: Suspected causative role of gadodiamide used for contrast-enhanced magnetic resonance imaging

Peter Marckmann et al.

JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY (2006)