developmentstoday

Ask DT AI Audio Brief Videos Podcast +

Ask DT AI Audio Brief Videos Podcast

HomeTagsmedical imaging

#medical imaging

All articles tagged with "medical imaging"

Company

About Us
Advertise
Contact
Editorial Policy

Legal

Terms of Service
Privacy Policy
Cookie Policy
AI & Ethics Policy
Do Not Sell My Info
FAQ
Archive
Site Map

Discover

Newsletter
Ask DT AI
Audio Brief
Videos
Podcast
DT Premium

Connect

Twitter / X
Facebook
LinkedIn
YouTube
Instagram
TikTok
Flipboard
RSS Feed

© 2026 Developments Today. All rights reserved.

medical imaging Articles | Developments Today

Imaging-based modalities compared for identifying at-risk MASH

FAST Score Shows Strongest Rule-Out Performance for At-Risk MASH

A review of 20 studies covering 9,480 participants compared imaging-based tests for at-risk MASH.
FAST had the highest rule-out sensitivity, at 0.871, with specificity of 0.567.
MRI-based technologies also showed strong evidence but involve different performance and practical tradeoffs.

DE

DT Editorial Team·Oct 16, 2026·via medicalxpress.com

More in Health→

Simple, noninvasive technique can assess collagen in the skin of scleroderma patients

Light-Based Imaging May Improve Scleroderma Skin Assessment

Boston University researchers applied SFDI to scleroderma skin assessment.
The noncontact method measures reflected patterned light.
Readings were compared with biopsy collagen, ultrasound and clinical skin scores.
The approach may detect subtle changes but needs further validation.

DE

DT Editorial Team·Oct 15, 2026·via medicalxpress.com

More in Health→

AI Finds 9 in 10 Esophageal Cancers on Routine Chest CTs | The Dr Kumar Discovery (via drkumardiscovery.com)

AI Model EAGLE Detects Early Esophageal Cancer on Routine Chest CT Scans

EAGLE (Esophageal AI-Guided malignant Lesion Evaluation) detects esophageal cancer and precancerous lesions from noncontrast chest CT, a task the authors say was historically considered impossible.
The model was trained on 6,813 patients from two centers and validated across 12 centers in three countries involving 80,612 patients.
In opportunistic screening external test cohorts (eight centers, n = 11,466), EAGLE achieved 98.5% specificity, 90.0% sensitivity for cancer and 52.5% for precancerous lesions.
Low-dose CT validation (two centers, n = 1,607) showed comparable performance, supporting screening through existing lung cancer screening programs.

DE

DT Editorial Team·Sep 23, 2026·via nature.com

More in Health→

AI assistant learns from radiology reports to spot problems in abdominal scans

AI Assistant RADAR Learns From Radiology Reports to Read Abdominal CT Scans

Researchers presented RADAR (Rapid Abdominal Diagnosis with AI and Radiology), a generalist AI assistant that interprets abdominal CT scans to help doctors reach diagnoses.
The vision-language framework was trained directly on clinical reports covering 424,911 examinations, 1.5 million image-text pairs and more than 15 million anatomy-specific pairs, with no manual tagging required.
RADAR reached an average diagnostic accuracy (AUC) of 0.913 in real-world hospital testing, outperforming existing medical vision-language AI models.
Performance held across eight hospitals, emergency room cases and diverse patient populations.

DE

DT Editorial Team·Sep 22, 2026·via medicalxpress.com

More in Health→

AbdomenAtlas: an AI-based approach for early cancer diagnosis - The Johns Hopkins News-Letter (via www.jhunewsletter.com)

Science Details Expert-Level Generalist AI for Abdominal CT Diagnosis

Science published a study titled as an expert-level generalist AI for abdominal CT diagnosis in Volume 393, Issue 6817, September 2026.
The framing suggests a departure from narrow, single-condition medical imaging models toward systems handling a broad range of diagnostic questions.
Abdominal CT is a demanding test domain due to dense anatomy, incidental findings, and wide variation in scan quality and protocols.
Likely near-term clinical uses include triage, second-reader support, and expanded access where radiology coverage is limited.

DE

DT Editorial Team·Sep 19, 2026·via science.org

More in AI & Robotics→

Learning from routine health system data builds better neuroimaging AI models | Nature Medicine (via www.nature.com)

Health-System Scans Help Build Stronger Neuroimaging AI

Researchers trained a 3D neuroimaging foundation model on 5.24 million routine CT and MRI series.
The study reports state-of-the-art diagnosis compared with models trained on public internet and medical data.
The model also enabled preliminary report generation and triage in real health systems.

DE

DT Editorial Team·Aug 4, 2026·via nature.com

More in Health→

AI-based clinician decision support system for diagnosis of inherited retinal diseases: a multicenter, randomized trial - Nature Medicine

AI trial shows retina imaging system improves inherited disease diagnosis

Retina4IRD predicts 17 genotype categories from retinal images.
The model was trained and validated on data from 1,843 genetically confirmed patients across three countries.
In a randomized trial, AI-assisted specialists achieved 88.5% top-5 genetic accuracy versus 67.3% without the tool.

DE

DT Editorial Team·Jul 29, 2026·via nature.com

More in Health→

Midjourney, the AI image generator, is developing a full-body ultrasonic scanner - Engadget

Midjourney moves into medical hardware with a 60-second body scanner

Midjourney says its first hardware product is a full-body ultrasonic scanner.
The company claims the system could produce MRI-like body maps in under 60 seconds.
Midjourney plans to open a first scanner-equipped Spa in San Francisco next year and pursue FDA approval for diagnostic use.

DE

DT Editorial Team·Jun 18, 2026·via engadget.com

More in News→

Heart Disease Treatment Shifts Toward Inflammation

Inflammation is emerging as a measurable driver of cardiovascular risk beyond cholesterol alone.
AI-enhanced coronary imaging may identify patients facing sharply higher chances of later heart attacks or death.
The shift could support more tailored use of immune-targeting therapies alongside standard lipid treatment.

DE

DT Editorial Team·Jun 6, 2026·via nature.com

More in Health→

Seven-second X-ray scan detects severity of heart valve regurgitation in patients with repaired congenital heart defects

Seven-second chest X-ray offers a faster read on post-surgery valve failure

Kyushu University tested a seven-second Dynamic Chest Radiography scan for pulmonary regurgitation.
The study reported 93% accuracy in identifying severe cases after Tetralogy of Fallot repair.
Researchers say the method could help patients who cannot undergo standard cardiac MRI.

DE

DT Editorial Team·Jun 4, 2026·via medicalxpress.com

More in Health→

A close-up image of a person

Eye-Video Screening Tool Spots Anemia Risk Without a Needle

The method estimates red blood cell levels from short videos of the eye.
In a 224-participant trial, it identified anemia more than 80% of the time.
Researchers and outside experts say it could become a screening tool, not a replacement for blood tests.

DE

DT Editorial Team·May 26, 2026·via livescience.com

More in Science→

AI unlocks cardiac MRI reading without manual labels, beating general models by 35%

Cardiac MRI AI model reads complex heart scans without manual labels

CMR-CLIP learns from cardiac MRI scans paired with radiology reports instead of manual labels.
Researchers said the system outperformed general-purpose AI models by more than 35% in some tests.
The model could support screening, case retrieval, and clinician decision support in cardiac imaging.

DE

DT Editorial Team·May 21, 2026·via medicalxpress.com

More in Health→

Illustration of pancreatic cancer in a human body.

AI Study Suggests Pancreatic Cancer May Be Detectable Years Earlier on Routine CT Scans

Researchers used an AI model to analyze nearly 2,000 CT scans that had previously been cleared as normal.
The system reportedly identified subtle pancreatic irregularities linked to tissue that later became tumor.
The study suggests pancreatic cancer might be detectable up to three years earlier than standard clinical discovery.

DE

DT Editorial Team·May 7, 2026·via livescience.com

More in Science→

AI Imaging Method Spots Keratoconus Before Standard Exams Can

Researchers combined PS-OCT with AI to detect subtle corneal changes tied to early keratoconus.
The method focuses on collagen organization rather than corneal shape alone.
The approach could improve screening for patients being evaluated for refractive surgery.

DE

DT Editorial Team·May 4, 2026·via medicalxpress.com

More in Health→

Stable PSA Readings May Miss Prostate Cancer Progression, Trial Analysis Finds

A large analysis of two clinical trials found scans can detect progression despite stable biomarkers.
The finding applies to patients treated with androgen receptor pathway inhibitors.
The result suggests biomarker stability alone may not be enough to rule out advancing disease.

DE

DT Editorial Team·Apr 27, 2026·via medicalxpress.com

More in Health→

Ultrasound’s Carbon Problem May Be in the Linen Cart, Not the Machine

A new JACR study says linens and disposable supplies drive most ultrasound emissions.
The finding differs from other imaging modalities, where equipment is often assumed to dominate.
Hospitals may need to focus on workflow and supply-chain changes, not just device efficiency.

DE

DT Editorial Team·Apr 13, 2026·via medicalxpress.com

More in Health→

A man with clear glasses wearing a white lab coat and stethoscope looks at a holographic blue and orange image of a leg and leg bone.

Researchers Warn of AI ‘Mirages’ in Medical Imaging Systems

Researchers warn some AI systems can describe medical images they were never shown.
The behavior raises concerns beyond ordinary error because fabricated interpretations can look credible.
The finding may push developers and clinicians to test grounding and oversight more rigorously.

DE

DT Editorial Team·Apr 7, 2026·via livescience.com

More in Science→

Study finds imaging result waits have doubled since 2014

A report based on millions of imaging orders says result waits have doubled since 2014.
The source says the sharpest increase in delays occurred recently.
Longer turnaround times can affect follow-up care and patient uncertainty.

DE

DT Editorial Team·Apr 7, 2026·via medicalxpress.com

More in Health→

AI-Powered Colonoscopy Systems Cut Polyp Miss Rates Significantly

AI-assisted colonoscopy raises adenoma detection rates by ~10 percentage points versus unassisted procedures
Flat and sessile serrated adenomas—the most dangerous and hardest-to-see lesions—benefit most from AI detection
Real-time AI overlays alert endoscopists within milliseconds, serving as a second set of eyes that never fatigues
Multiple AI colonoscopy systems have FDA clearance and are entering routine clinical use at medical centers

DE

DT Editorial Team·Mar 22, 2026·via medicalxpress.com

More in Health→