We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

AI-Powered Artefact Removal Can Identify Poor-Quality MRI Images with Near-Human Accuracy in Milliseconds

By MedImaging International staff writers
Posted on 05 Feb 2021

Image: Siemens Magnetom Espree 1.5T (Photo courtesy of Siemens)

Image: Siemens Magnetom Espree 1.5T (Photo courtesy of Siemens)

A new study has demonstrated the effective use of a retrospective artefact correction (RAC) neural network learned with unpaired data to disentangle and remove unwanted artefacts in magnetic resonance (MR) images.

The findings of the study by researchers at the UNC School of Medicine (Chapel Hill, NC, USA) also revealed the capacity of the RAC network to retain anatomical details in MR images with different contrasts, improve magnetic resonance imaging (MRI) quality post acquisition, and enhance image usability.

MRI is susceptible to artefacts caused by motion that can render the images unusable and cause financial losses in imaging studies. At UNC’s Biomedical Research Imaging Center (BRIC), a team is exploring the use of deep learning to identify poor-quality images with near-human accuracy in milliseconds. Their investigative work is aimed at increasing timely decision-making in MRI re-scan. RAC is an increasingly investigated technique in MRI for the correction of motion-induced artefacts. Their study in applied imaging evidences superior motion correction via artificial intelligence (AI) techniques for RAC. Their investigation demonstrates further study of reliable AI techniques for RAC is warranted to benefit image correction and reconstruction in future MRI studies.

“AI-powered RAC can salvage innumerable images with motion artefacts to significantly boost the quantity of usable images and reduce financial losses for imaging studies,” said Pew-Thian Yap, PhD, Image Analysis Core Director at BRIC, who is leading the team.

Related Links:
UNC School of Medicine

Visit expo >

Diagnostic Ultrasound System

DC-80A

X-Ray Illuminator

X-Ray Viewbox Illuminators

High-Precision QA Tool

DEXA Phantom

Ultrasound Table

Women’s Ultrasound EA Table

Latest Industry News News

Channels

Radiography

view channel

Image credit: Shu-Han Chen / St. Paul’s Hospital / National Taiwan University

AI Tool Flags Osteoporosis Risk from Routine Chest X-Rays

Osteoporosis is a progressive loss of bone density that is often silent until a fracture occurs. Current screening frameworks concentrate on older women and select high-risk groups. Many men, younger adults,... Read more

Simple Chest X-Ray Measure Predicts Survival After Lung Cancer Surgery

Obstructive ventilatory disorder, marked by airflow limitation that reduces breathing efficiency, increases postoperative risk in patients with lung cancer. Although surgery offers the best chance of cure,... Read more

AI Detection Tool Improves Identification of Lobular Breast Cancer

Breast cancer screening seeks early detection, yet some subtypes remain difficult to visualize on mammography, risking delayed diagnosis. On average, 1 in 20 women worldwide will develop breast cancer,... Read more

Image: Ambika Bajpayee and her team at Northeastern developed a patented contrast agent 100 times more efficient than current options (photo courtesy of Ruby Wallau/Northeastern University)

New Contrast Agent Enables Low-Dose X-Ray Joint Imaging

X-ray imaging offers limited visualization of soft tissues like cartilage, complicating evaluation of joint pain and degenerative disease. Clinicians often rely on joint-space narrowing as a proxy for... Read more

MRI

view channel

$Image: By training the AI with simulations, researchers can reconstruct brain images with high precision using only one-tenth of the data typically required in magnetic resonance imaging. The image shows a metric known as “fractional anisotropy”—an index of myelination—obtained using conventional methods and with the new approach (Photo courtesy of Instituto de Neurociencias UMH CSIC)$

AI Approach Could Shorten Advanced Brain MRI Scans by Up to 90%

Long acquisition times for advanced brain magnetic resonance imaging (MRI) can limit access, extend waiting lists, and disrupt clinical workflows. Reducing data requirements without sacrificing image fidelity... Read more

Image: Representative cine-CMR four-chamber image demonstrating severe tricuspid regurgitation (Photo courtesy of Dr. Robert Zhang)

Cardiac MRI Measure Improves Risk Prediction in Tricuspid Regurgitation

Tricuspid regurgitation, in which blood flows back from the right ventricle into the right atrium, can lead to progressive right-sided heart failure. Clinicians need reliable ways to gauge severity and... Read more

AI System Improves Accuracy of Cardiac MRI Interpretation

Cardiac magnetic resonance imaging (MRI) is the reference standard for assessing cardiac structure, function, and tissue health. Yet each exam can contain hundreds to thousands of images across multiple... Read more

Image: A multitask deep learning model uses a single baseline MRI scan and demographic data to predict cognitive scores without baseline cognitive testing (image credit: 123RF)

Deep Learning Model Predicts Alzheimer’s Disease Outcomes from Baseline MRI

Alzheimer’s disease, which accounts for 60% to 70% of dementia cases worldwide, remains difficult to predict early in its course. Accurate prognostication typically relies on neuropsychological testing,... Read more

Ultrasound

view channel

AI Robotic Ultrasound System Automates Echocardiography and Improves Consistency

Echocardiography, an ultrasound examination of the heart, is central to diagnosing and managing cardiovascular disease. Many services struggle with limited availability of skilled sonographers, variable... Read more

Image: Whole cross-sectional UST of a healthy adult female (participant 1) (Garrett, D.C., Xu, J., Oh, D. et al. Nat. Biomed. Eng (2026). https://doi.org/10.1038/s41551-026-01660-4)

Whole Cross-Section Ultrasound System Enables Operator-Independent Imaging

Conventional ultrasound is central to bedside imaging but is limited by a narrow field of view and operator variability. Comprehensive cross-sectional assessment typically requires computed tomography... Read more

New Ultrasound AI Tool Supports Rapid Prenatal Assessment

Accurate gestational age estimation guides prenatal screening, detection of complications, and timely intervention. Access to ultrasound and trained sonographers is uneven, with nearly half of U.... Read more

Image: Researchers developed an expert consensus to standardize UDFF use in clinical practice based on extensive literature review, expert experience and recent advances in MASLD diagnosis (Photo courtesy of Dr. Huixiong Xu and Dr. Hong Ding from Fudan University, China)

New Consensus Standardizes Ultrasound-Based Fatty Liver Assessment

Metabolic dysfunction-associated steatotic liver disease (MASLD) is rising along with obesity and diabetes, making accurate, scalable measurement of hepatic fat a clinical priority. Biopsy is invasive... Read more

Nuclear Medicine

view channel

Portable PET System Enables Real-Time Bedside Guidance for Biopsies and Ablations

Interventional radiology procedures typically rely on ultrasound, X-ray fluoroscopy, or computed tomography for image guidance. These modalities visualize anatomy but offer limited molecular information,... Read more

AI Model Predicts Radiation Dose Before Prostate Cancer Therapy

Metastatic castration-resistant prostate cancer (mCRPC) is an advanced form of disease that progresses despite androgen-deprivation therapy and frequently spreads to bone and visceral organs.... Read more

Vault-Free Radiosurgery Platform Expands Access to Cranial Tumor Care

Brain tumors and certain skull base lesions often require precise, non-invasive treatment that protects nearby critical structures. Although stereotactic radiosurgery (SRS) enables outpatient therapy without... Read more

$Image: Imricor\'s NorthStar Mapping System (photo courtesy of Imricor)$

MR-Guided Cardiac Mapping System Enables Radiation-Free Procedures

Cardiac electrophysiology procedures are typically guided by X-ray fluoroscopy, which limits soft-tissue visualization and exposes patients and clinical staff to ionizing radiation. Real-time mapping that... Read more

General/Advanced Imaging

view channel

Image: Representative whole-body PET/CT based organ and tissue segmentation before and 12 months after bariatric surgery in a 20-year-old woman. Coronal PET/CT images and automated segmentation maps show multi-organ structural remodeling, including reductions in subcutaneous adipose tissue, visceral adipose tissue, liver, pancreas, spleen, and skeletal muscle, with apparent enlargement of the colon at 12-month follow-up (Photo courtesy of SNMMI)

Whole-Body PET/CT Tracks Metabolic Changes After Bariatric Surgery

Obesity surgery improves weight and comorbidity profiles, yet clinicians lack tools to monitor organ-level metabolic recovery after the procedure. A clear view of systemic changes could refine follow-up... Read more

Image: Static PET-CT image of patient with hypercortisolism taken at 60 minutes post-injection (Image Credit: SNMMI)

PET Tracer Localizes Overactive Adrenal Glands in Primary Aldosteronism

Primary aldosteronism (Conn’s syndrome) is the leading cause of curable secondary hypertension and results from excess aldosterone produced by the adrenal cortex. Determining whether hormone overproduction... Read more

Multimodal AI Tool Combines CT and Health Records to Predict Heart Risk

Cardiovascular disease is a leading cause of death and an underrecognized risk for people treated for breast cancer. Cardiac complications can affect survival and quality of life. Clinicians need tools... Read more

AI Tool Automates Radiotherapy Planning for Cervical and Prostate Cancer

Cervical cancer causes most of its global mortality in low- and middle-income countries, where radiotherapy capacity and specialist staff are limited. Treatment planning is labor-intensive and can delay... Read more

Imaging IT

view channel

Image: Researchers develop a vision-language model trained on large-scale data to generate clinically relevant findings from chest computed tomography images through visual question answering (Ms. Maiko Nagao from Meijo University, Japan)

Interactive AI Tool Supports Explainable Lung Nodule Assessment

Lung cancer is a leading cause of cancer mortality, and timely characterization of pulmonary nodules on chest computed tomography (CT) is essential for directing care. Interpreting nodule morphology demands... Read more

Breast Imaging Software Enhances Visualization and Tissue Characterization in Challenging Cases

Breast imaging can be particularly challenging in cases involving small breasts or implants, where image reconstruction and tissue characterization may be limited. Clinicians also need reproducible analysis... Read more

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more

Global AI in Medical Diagnostics Market to Be Driven by Demand for Image Recognition in Radiology

The global artificial intelligence (AI) in medical diagnostics market is expanding with early disease detection being one of its key applications and image recognition becoming a compelling consumer proposition... Read more