The 2026 Chinese lung cancer guideline adds AI and opportunistic screening in low-dose CT, expands molecular testing, and updates treatment regimens for NSCLC, including perioperative, consolidation immunotherapy, and targeted therapy for EGFR, ALK, KRAS, HER2, and MET alteratio…
On 76 test cases, the AI framework achieved Cobb angle MAE 2.4°, Lenke curve type accuracy 0.895, and reduced review time from 8.2 to 1.5 min/case.
An AI model (EAGLE) analyzing noncontrast chest CT achieved 90.0% sensitivity for esophageal cancer and 98.5% specificity in external multicenter testing (11,466 patients), and 99.94% specificity in low-dose screening. Could enable opportunistic esophageal cancer screening.
PSAD remained below 0.11 ng/mL² across all ages in 1037 healthy German men, contrasting with continuously rising PSA. 95th percentile reference: PV 51.39 mL, PSA 2.79 ng/mL, PSAD 0.071 ng/mL².
Super-selective embolization for plantar fasciitis with resorbable embolics reduced pain (visual analog scale, VAS) by 2.4 points (p=0.001) and improved function (foot and ankle disability index, FADI) by 22 points at 1 month, with no major adverse events.
In a survey of 435 physicians, 83.7% had positive attitudes toward AI in clinical screening/diagnosis, but only 50.3% demonstrated good knowledge. Radiology (75.9%) was seen as the highest-impact area. Top barriers: insufficient training (58.9%), lack of trust (53.8%).
A 3D-printing workflow using CT data produced high-fidelity skulls that preserved sex-specific traits, individual variation, and pathology.30 dentistry students rated the custom models highly for anatomical realism and valued diverse representation for learning.
PABCNet super-resolves non-contrast coronary MRA, achieving a vessel ROI-PSNR of 32.68 dB (2.18 dB better than the second-best method) and providing pixel-wise confidence maps. Radiologists rated it superior in coronary clarity, cardiac structure depiction, and artifact suppress…
<![CDATA[Study Reveals Mixed Results with Deep Learning Model for Breast MRI]]>
ITM touts research studies at ASTRO 2026
ASRT files comments on CMS proposed 2027 payment rules
USC researchers develop “plug-and-play" platform for PET tracers
What are the effects of COVID-19 pneumonia after 5 years?
What determines ultrasound reflection at a tissue boundary?
Thomas Lowe Fleischner and Anne Haven McDonnell in conversation at Boulder Book Store and other Boulder events for Thursday
How the COVID-19 Pandemic Led to Updated BI-RADS Guidance on Addressing Axillary Lymphadenopathy
Facebook Live: Radiology and Physical AI: The Robots are Coming
Among 90 ED clinicians, mean radiation knowledge score was 5.70/11 and only 27.8% had formal education. More importantly, knowledge did not correlate with imaging referral practices, indicating education alone may not alter referral decisions.
Study cohort construction and multimodal model validation workflow. (IMAGE)
AI Model Combining Ultrasound and Digital Breast Tomosynthesis Improves Specificity in Breast Cancer Triage | Newswise
Chief, Section of Radiology Job Opening in Miami, Florida
<![CDATA[Could Photon-Counting CT Expose the Paradox of Health-Care Economics?]]>
<![CDATA[IR Update: FDA Clears New Device for Liver Embolization Procedures]]>
ACR Seeks New CPT Codes at September Editorial Panel Meeting
100% Remote Cardiothoracic or Thoracic Radiologist Job Opening in Remote
Resources > Conference > ASTRO > ASTRO 2026
Recent Jobs - neuroradiologist - American College of Radiology Career Center
Most interval cancers detected between screening rounds—including lung, breast, and colorectal—exhibit high aggressiveness and poor prognosis, highlighting limitations in current screening strategies.
Noncontrast CT-based unimodal imaging AI detected anterior circulation large vessel occlusion with sensitivity 0.78 (95% credible interval 0.68-0.86) and specificity 0.88, versus expert readers' sensitivity 0.62 and similar specificity; low-certainty retrospective evidence.
YOLOv11s achieved 95.2% mAP@50, 93.6% precision, 91% recall, outperforming transformer-based RF-DETR (94.3% mAP@50, 90.6% precision, 85% recall) in brain tumor MRI.
A four-category framework (Virtual Biopsy, Flowmeter, Signpost, Tiebreaker) turns abdominal imaging artifacts into diagnostic clues, not pitfalls, helping radiologists interpret CT, MRI, ultrasound, and other modalities.
A Pilot Study of Cadaver CT Scan Interpretation by First Year Medical Students as an Introduction to Clinical Radiology During the Gross Anatomy Curriculum.
SIR Foundation research consensus panel calls for standardized acute DVT intervention endpoints: biologically informed patient selection, anatomic/physiologic metrics, validated severity tools, longitudinal biomarkers, and economic/QoL measures to advance precision and reduce po…
AI enhances breast cancer care from risk assessment to treatment response via advanced mammography, MRI, ultrasound, and pathology tools, but its clinical ubiquity is limited by unresolved adoption challenges.
