Every story, newest first.
AIRS Medical, developer of the SwiftMR deep-learning MRI acceleration platform, has received private equity investment. The 2018-founded firm claims SwiftMR reduces scan times while improving image quality; deal terms were not disclosed.
FDA cleared E-Scopics' hepatoscope, a quantitative ultrasound device. It combines transient elastography for fibrosis, attenuation imaging for steatosis, and B-mode for morphology in one exam, intended for point-of-care liver assessment.
FDA issues warning letter to Zoll Medical over safety lapses with its MRI-compatible ventilators, alerting clinicians to potential hazards during scanning. Details of the lapses were not specified in the brief trade report.
RSNA's portfolio of journals achieved significant impact factor increases, with 'Radiology' rising to 19.7 and 'RadioGraphics' to 6.5, solidifying their positions as top-tier resources in medical imaging. Other journals also saw double-digit percentage gains.
Expert commentary from Michael Hofman summarizes key molecular imaging themes from the 2026 SNMMI annual meeting. Specific findings and data not reported in source; full details require access to the original interview.
AJR. American journal of roentgenology
AJR. American journal of roentgenology
AJR. American journal of roentgenology
AJR. American journal of roentgenology
AJR. American journal of roentgenology
AJR. American journal of roentgenology
AJR. American journal of roentgenology
AJR. American journal of roentgenology
Opportunistic screening leverages existing imaging examinations performed for unrelated routine clinical indications to systematically extract quantitative biomarkers. Artificial intelligence tools have made deployment at scale increasingly feasible. However, the pathway from...
AJR. American journal of roentgenology
BACKGROUND. Prior studies using habitat imaging for lung nodule characterization have been limited by intermixing of nodule types, insufficient handling of lesion heterogeneity, and incomplete consideration of high-risk histologic features. OBJECTIVE. To predict high-risk feat...
AJR. American journal of roentgenology
AJR. American journal of roentgenology
AJR. American journal of roentgenology
AJR. American journal of roentgenology
OBJECTIVES: To evaluate short-term pain relief and safety provided by polidocanol foam sclerotherapy for painful venous malformations (VMs) and determine imaging and procedural predictors of clinical efficacy. MATERIALS AND METHODS: From April 2015 to September 2025, this sing...
OBJECTIVES: MRI can reveal the signal characteristics and invasive potential of tumors. Our study aimed to explore the potential of MRI-identified primary tumor aggressiveness-related factors in nasopharyngeal carcinoma (NPC). MATERIALS AND METHODS: This study retrospectively...
OBJECTIVES: Computed tomography (CT) scans for lung cancer screening provide the opportunity of quantifying incidental findings. We evaluated the repeatability of AI-based measurements of incidental findings using short-term repeat CT scan pairs. MATERIALS AND METHODS: AI-Rad...
PURPOSE: To investigate the effects of vendor-neutral image-domain deep learning reconstruction (DLR) applied retrospectively to dynamic contrast-enhanced (DCE) images from prostate multiparametric magnetic resonance imaging (MRI) on image quality and diagnostic performance fo...
Episode 40: The Next Era of Imaging Intelligence | Podcast
Tube voltage significantly affects CT attenuation-based hepatic steatosis measurements: 120-kVp-equivalent vs. 80-kVp images showed r = 0.921–0.975, but regression-adjusted values agreed excellently (ICC 0.966–0.992, mean difference ≤0.7 HU), enabling reliable cross-kVp steatosi…
AI-assisted appendicular fracture detection (AUC 0.847, 95% CI 0.811–0.881) improved accuracy for 2 of 3 radiologists (~76% → 83%, p≤0.001) and cut median read time 33% (12.9→8.6 s) in a retrospective MRMC study; prospective multicenter validation still needed.
AI assistance significantly improved radiologic technologist detection of intraventricular and subdural hemorrhage (5/30 reader-task comparisons, p≤0.007) but did not improve overall any-hemorrhage AUC in this retrospective 100-CT study.
AI (mostly U-Net CNNs) segments craniofacial airways on CBCT with Dice scores 0.90–0.97 and ICC >0.90 vs. manual methods across 14 studies. But external validation is scarce and only 1 study tested OSA prediction against polysomnography — not yet ready for routine use.
MRI radiomics predicts pathological complete response (pCR) in rectal cancer after neoadjuvant chemoradiotherapy: pooled sensitivity 0.82, specificity 0.86, AUC 0.85 (38-study meta-analysis). Deep learning models outperformed. Prospective validation still lacking.
In 221 patients undergoing cardiac CT/CTA, epicardial adipose tissue volume (EAV) independently associated with CAD after adjusting for traditional risk factors and calcium score; extensive plaque burden rose from 15.6% to 46.7% across EAV quartiles. EAV did not predict high-ris…
AI-assisted biparametric MRI (uAI, United Imaging) raised novice-reader AUC from 0.684 to 0.744 and sensitivity from 0.71 to 0.79 at PI-RADS ≥3 in 646 men; experienced-reader sensitivity gains were smaller and nonsignificant (p=0.344/0.291). Retrospective.
90% of students preferred a combined 3D-model plus 2D-image approach over either alone in station-based dermatology learning. 2D images scored marginally higher for diagnostic skill (7.3/10) and clinical application (7.2/10) vs. 3D models (6.8 and 6.7). Findings are perception-b…
Neurosurgical technique paper describes a standardised retractorless bifrontal craniotomy approach—pericranial flap harvest, frontal sinus obliteration, bilateral olfactory nerve dissection, intradural repair—for traumatic anterior fossa CSF fistulas. Outcomes quantified only qu…
Cross-sectional survey of 368 Jordanian medical students found AI-tool users had significantly more positive attitudes toward AI-integrated anatomy teaching (p<0.001); chatbots were the most-used AI tool (73.9%), but traditional slides remained the dominant study resource (91.9%…
3D T1 VIBE detects intracavernous cranial nerves far better than MPRAGE in neuro-ophthalmic MRI. In 54 exams, VIBE visualized CN V1 in 65–70% vs 6–9% and CN VI in 70–78% vs 19–22% for MPRAGE (all p<0.001), suggesting VIBE should be the preferred sequence.
Fish-mouthing (focal end convergence) occurred in 20% of Surpass Evolve flow diverter cases at 1 month but resolved in most, falling to 7% at 1 year. Fusiform shape, multiple aneurysms, and MCA location were risk factors. Retrospective; n=94.
A DL-generated high-contrast thin-slice CT (HCCT) from plain NCCT pushed inter-rater ASPECTS correlation from 0.72 to 0.94 (p<0.001) in 303 LVO stroke patients across 4 centers — outperforming standard NCCT for early ischemic change detection and favorable-outcome prediction.
Acute-phase T2-FLAIR radiomics improved risk stratification for delayed encephalopathy after CO poisoning: AUC 0.876, sensitivity 0.80, specificity 0.84 in held-out testing. Deep white matter was the dominant signal source. Retrospective; not externally validated.
Deep learning-accelerated DIR MRI reduced optic nerve scan time by 44% (23 min → 13 min) in 75 patients with suspected optic neuropathy, detected significantly longer lesions than STIR (β=7.4–7.6%, p<0.001), and was interchangeable with conventional DIR. Prospective single-cente…
