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.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us
GLOBETECH PUBLISHING LLC

Download Mobile App




AI Model Achieves Clinical Expert Level Accuracy in Analyzing Complex MRIs and 3D Medical Scans

By MedImaging International staff writers
Posted on 07 Oct 2024
Print article
Image: The new AI model efficiently reaches clinical-expert-level accuracy in complex medical scans (Photo courtesy of Leticia Ortiz/UCLA)
Image: The new AI model efficiently reaches clinical-expert-level accuracy in complex medical scans (Photo courtesy of Leticia Ortiz/UCLA)

Artificial neural networks train by performing repeated calculations on large datasets that have been carefully examined and labeled by clinical experts. While standard 2D images display length and width, 3D imaging technologies introduce depth, creating "volumetric" images that require more time, skill, and attention for expert interpretation. For instance, a 3D retinal imaging scan may consist of nearly 100 2D images, necessitating several minutes of close examination by a highly trained specialist to identify subtle disease biomarkers, such as measuring the volume of an anatomical swelling. Now, researchers have developed a deep-learning framework that rapidly trains itself to automatically analyze and diagnose MRIs and other 3D medical images, achieving accuracy comparable to medical experts but in a fraction of the time.

Unlike other models being developed for 3D image analysis, the new framework created by researchers at UCLA (Los Angeles, CA, USA) is highly adaptable across various imaging modalities. It has been studied with 3D retinal scans (optical coherence tomography) for disease risk biomarkers, ultrasound videos for heart function assessment, 3D MRI scans to evaluate liver disease severity and 3D CT scans for chest nodule malignancy screening. In a paper published in Nature Biomedical Engineering, the researchers highlight the broad capabilities of the system, suggesting that it could be valuable in many other clinical settings. Additional studies are planned to further explore its applications.

The UCLA model, named SLIViT (SLice Integration by Vision Transformer), features a unique combination of two artificial intelligence components and a specialized learning approach. According to the researchers, this combination enables it to accurately predict disease risk factors from medical scans across multiple volumetric modalities, even with moderately sized labeled datasets. SLIViT’s automated annotation could benefit both patients and clinicians by enhancing diagnostic efficiency and timeliness, while also advancing medical research by reducing data acquisition costs and shortening the time required for data collection. Additionally, it establishes a foundational model that can expedite the development of future predictive models.

“SLIViT overcomes the training dataset size bottleneck by leveraging prior ‘medical knowledge’ from the more accessible 2D domain,” said Berkin Durmus, a UCLA PhD student and co-first author of the article. “We show that SLIViT, despite being a generic model, consistently achieves significantly better performance compared to domain-specific state-of-the-art models. It has clinical applicability potential, matching the accuracy of manual expertise of clinical specialists while reducing time by a factor of 5,000. And unlike other methods, SLIViT is flexible and robust enough to work with clinical datasets that are not always in perfect order.”

New
Gold Member
X-Ray QA Meter
T3 AD Pro
New
Doppler String Phantom
CIRS Model 043A
Ultrasound Color LCD
U156W
New
Ultrasound Imaging System
P12 Elite

Print article
Radcal

Channels

Radiography

view channel
Image: The CT scanner prototype eliminates the need for physical compression of the breast (Photo courtesy of Quion Lowe and Lisa Dahm/U of A Cancer Center)

Novel Breast Cancer Screening Technology Could Offer Superior Alternative to Mammogram

Breast cancer represents 15.5% of new cancer cases and 7% of cancer-related deaths in the United States. Approximately 13.1% of women will be diagnosed with breast cancer during their lifetime.... Read more

Ultrasound

view channel
Image: Wearable ultrasound device offers continuous, long-term monitoring of muscle activity (Photo courtesy of Muyang Lin/UC San Diego)

Wearable Ultrasound Device Provides Long-Term, Wireless Muscle Monitoring

Electromyography (EMG) is the current clinical standard for monitoring muscle activity, utilizing metal electrodes placed on the skin to capture electrical signals from muscles. Despite its long-standing... Read more

Nuclear Medicine

view channel
Image: PET scans of a glioblastoma patient\'s brain, 72 hours after injection with the radiotracer (Photo courtesy of Dr Gabriela Kramer-Marek, The Institute of Cancer Research, London)

New Immuno-PET Imaging Technique Identifies Glioblastoma Patients Who Would Benefit from Immunotherapy

Glioblastoma is a type of brain tumor associated with a very poor prognosis, with average survival rates of 12 to 18 months and only 5% of patients surviving beyond five years. Research has shown that... Read more

General/Advanced Imaging

view channel
Image: Heavy smokers can ben Image (2):	efit from lung cancer screening using low-dose CT (Photo courtesy of 123RF)

Low-Dose CT Screening for Lung Cancer Can Benefit Heavy Smokers

Lung cancer is often diagnosed at a late stage, with only about one-fifth to one-sixth of patients surviving five years after diagnosis. A new report now suggests that low-dose computed tomography (CT)... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

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

Industry News

view channel
Image: The advocacy partnership aims to help accelerate access to life-saving treatments (Photo courtesy of Philips)

Philips and Medtronic Partner on Stroke Care

A stroke is typically an acute incident primarily caused by a blockage in a brain blood vessel, which disrupts the adequate blood supply to brain tissue and results in the permanent loss of brain cells.... Read more
Copyright © 2000-2024 Globetech Media. All rights reserved.