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




Ultra-Low Dose CT Aids Pneumonia Diagnosis in Immunocompromised Patients

By MedImaging International staff writers
Posted on 17 Mar 2025
Print article
Image: Axial noncontrast chest CT lung window images of three different sample patches shown in each row (Photo courtesy of Radiology: Cardiothoracic Imaging)
Image: Axial noncontrast chest CT lung window images of three different sample patches shown in each row (Photo courtesy of Radiology: Cardiothoracic Imaging)

Lung infections can be life-threatening for patients with weakened immune systems, making timely diagnosis crucial. While CT scans are considered the gold standard for detecting pneumonia, repeated scans can expose patients to harmful levels of radiation. Early diagnosis is particularly important for immunocompromised patients, but the cumulative risk of radiation exposure from frequent CT scans raises concerns. Ultra-low dose CT scans, which reduce radiation exposure, often suffer from poor image quality due to added “noise,” leading to grainy textures that can hinder accurate diagnosis. A new study, published in Radiology: Cardiothoracic Imaging, reveals that denoised ultra-low dose CT scans can diagnose pneumonia in immunocompromised patients effectively, using only 2% of the radiation dose of standard CT scans.

The research, conducted by scientists at Sheba Medical Center (Ramat Gan, Israel), aimed to evaluate the denoising capabilities of a deep learning algorithm on ultra-low dose CT scans. Between September 2020 and December 2022, 54 immunocompromised patients with fevers underwent two chest CT scans: one with a standard dose and another with an ultra-low dose. The ultra-low dose CT scans were processed using a deep learning algorithm designed to reduce noise. Radiologists then assessed the scans independently, noting their findings from the standard, ultra-low dose, and denoised ultra-low dose CT images, without being aware of the patients’ clinical details.

The deep learning algorithm significantly enhanced the image quality of the ultra-low dose CT scans, improving clarity and reducing false positives. Nodules were also more easily detectable on the denoised scans. Importantly, the effective radiation dose from the ultra-low dose scans was only 2% of the standard CT scan’s radiation dose. The researchers suggest that this deep learning-based denoising method could benefit other patient groups, including pediatric patients. They plan to conduct future studies with larger sample sizes to further validate the promising results of this approach.

“This study paves the way for safer, AI-driven imaging that reduces radiation exposure while preserving diagnostic accuracy,” said lead study author Maximiliano Klug, M.D. “This pilot study identified infection with a fraction of the radiation dose. “This approach could drive larger studies and ultimately reshape clinical guidelines, making denoised ultra-low dose CT the new standard for young immunocompromised patients.”

Related Links:
Sheba Medical Center

LED-Based X-Ray Viewer
Dixion X-View
Mini C-arm Imaging System
Fluoroscan InSight FD
New
X-Ray Illuminator
X-Ray Viewbox Illuminators
3T MRI Scanner
MAGNETOM Cima.X

Print article

Channels

MRI

view channel
Image: Combining AI with bpMRI improves detection of clinically significant prostate cancer (Photo courtesy of 123RF)

Biparametric MRI Combined with AI Enhances Detection of Clinically Significant Prostate Cancer

Artificial intelligence (AI) technologies are transforming the way medical images are analyzed, offering unprecedented capabilities in quantitatively extracting features that go beyond traditional visual... Read more

Ultrasound

view channel
Image: The model trained on echocardiography, can identify liver disease in people without symptoms (Photo courtesy of 123RF)

Artificial Intelligence Detects Undiagnosed Liver Disease from Echocardiograms

Echocardiography is a diagnostic procedure that uses ultrasound to visualize the heart and its associated structures. This imaging test is commonly used as an early screening method when doctors suspect... 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
Copyright © 2000-2025 Globetech Media. All rights reserved.