GE HealthCare is now a standalone public company after the 2021–2024 breakup of the 130-year-old conglomerate into three firms. The medical imaging division, along with GE Aerospace and GE Vernova, together are worth several times GE's pre-split valuation.
GE HealthCare to acquire Sofie Biosciences for $945M
Breast imaging experts call adjunctive artificial intelligence (AI) a second set of eyes, not a replacement for radiologist judgment; they split on saving its outputs and cautioned against charging patients for access.
Allegheny Health Network (AHN) Neuroradiologist Remote/Pittsburgh Job Opening in Remote
Torsion of the #spleen on #CTscan. #radiology #foamrad #radres
A knee MRI anatomy tutorial breaks down the medial and lateral menisci, covering the anterior horn, body, posterior horn, and key attachments, with emphasis on practical identification of normal structures and differences between menisci.
Breast Ultrasound AI Scores High, Faces Trial Gap
Video tutorial from CTisus on CT of small bowel infectious etiologies and conditions that mimic them. Learn to distinguish infectious enteritis from inflammatory or neoplastic look-alikes on CT.
A point-counterpoint in AJR debates wide AI use in mammography screening. Pro: RCTs show diagnostic gains, AI can reduce second-reader needs and speed workflow. Con: Most evidence from 2D not DBT, no mortality reduction, legal concerns. The tech imperative likely prevails.
AI Prostate MRI Tool Shows High Sensitivity but Hard Trade-Offs in Real-World Test
A convolutional neural network (CNN) detected hyperintense and hypointense artifacts on high b-value (b=1500) breast diffusion-weighted imaging (DWI) slices with AUROCs of 0.91 and 0.95, respectively, in a retrospective study of 11,806 slices. Further validation is needed.
Letter to the Editor: Multicentre validation of the PRECISE scoring system for prostate MRI during active surveillance.
Methodological considerations regarding the association between emphysema and pulmonary vascular volume heterogeneity.
Reply to the Letter to the Editor: Methodological considerations regarding the association between emphysema and pulmonary vascular volume heterogeneity.
A multi-task model (MoEMIL) integrating MRI and pathology images achieved an AUC of 0.801 for predicting induction chemotherapy response in locally advanced nasopharyngeal carcinoma, significantly outperforming radiomics and TNM staging. It also stratified overall survival (P<0.…
In multicenter chest CT data from the LIBRA study, a mixed-effects radiomics model for lung nodule cancer prediction achieved AUC 0.91 (95% CI 0.90–0.93), significantly outperforming ComBat and providing net benefit over volume and Brock score alone.
ML models integrating clinical data and chest CT features predicted lung cancer subtype (small cell, EGFR-mutant, EGFR-wild-type) with AUC up to 0.907, to guide early brain metastasis management.
Diagnostic breast imaging completion within 3 weeks rose from 57.4% to 65.3% (p<0.001) and median wait fell from 18 to 14 days after implementing a high-priority scheduling guideline; high-priority symptomatic exam completion improved from 49.5% to 61.1%.
In a matched case-control study, fetal brain DWI showed higher ADC in MBH, basal ganglia, thalamus, pons and lower ADC in centrum semiovale, periventricular and occipital white matter among GDM-exposed fetuses (all p<0.05).
Interventional oncology research leverages animal models (mouse, rat, woodchuck, rabbit, pig, dog, non-human primate) alongside new approach methodologies like organoids, organ-on-a-chip, and AI in silico models to complement human biology-based testing.
In 12 patients with high-risk hepatocellular adenomas, Y-90 radioembolization achieved a 100% objective response rate (20/20 target lesions), with 85% complete response and no grade ≥2 adverse events.
A generative AI model jointly synthesizing brain MRI magnitude and phase images produced synthetic data that trained a classifier to detect abnormal tissue with AUROC 0.880, beating real-data training (0.842) on fastMRI, and persisted on an external biopsy-confirmed set.
Adding multisequence MRI to CT improved deep learning dose prediction for glioblastoma radiotherapy: mean absolute error was 5.99 Gy vs 6.92 Gy (p=0.006), with better spatial agreement (SSIM 0.599 vs 0.564) and high-dose region estimation.
In a scoping review of imaging for adolescent endometriosis, ovarian endometrioma and posterior deep endometriosis were most consistently detected. Superficial disease was poorly captured, and normal imaging was common in symptomatic patients. Most primary studies used ultrasoun…
Corrigendum to "Reliability and Educational Quality of Online Video-based CBCT Interpretation Training: Implications for Radiology Education" (Academic Radiology, Volume 33, Issue 7 [2026] 2790-2795).
Soft Tissue-RADS accuracy for distinguishing benign from suspicious soft-tissue tumors on MRI was 82% vs 61% for qualitative reads (p<0.001), with good inter-reader agreement (κ=0.79) in a 150-patient validation by expert MSK radiologists.
An unsupervised domain adaptation framework combining entropy-based adversarial alignment, pixel-wise contrastive learning, and channel-wise similarity regularization achieved 85.88% Dice on one private dataset and 86.62% on BraTS-2023 SSA for cross-center brain tumor segmentati…
For postmenopausal women with acute pelvic pain, ultrasound is the first-line imaging study; MRI or CT are reserved for inconclusive sonographic findings, according to the ACR Appropriateness Criteria 2026 update.
On an external test set, a hybrid CNN-Transformer deep learning model predicted human epidermal growth factor receptor 2 (HER2) status from breast diffusion-weighted MRI with AUC 0.91 (accuracy 0.84), outperforming clinical experts (AUC 0.65 and 0.63). Internal test AUC 0.93. Re…
For one-step coronary and carotid-cerebral CTA, an AI CAD platform cut interpretation time by up to 88.33% and mouse clicks by up to 57.77% compared with radiologists, while demonstrating high diagnostic accuracy.
