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.
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.
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.
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…
<![CDATA[Could Quantification of Extracellular Volume Fraction with PCCT Be a Viable Alternative for Staging Liver Fibrosis?]]>
Siemens Healthineers and Cleveland Clinic Forge 10-Year Alliance to Boost Imaging and Clinical Innovation
Can LLMs fill the communication gap with referring clinicians?
AI Succeeds at Opportunistic Screening for Osteoporosis
Aycan launches AI anonymizer tool for medical imaging data
Incidence Proportion and Clinicopathological Characteristics of Phyllodes Tumors of the Breast Among Patients With Breast Lumps in Dubai, 2017-2022: A Retrospective Observational Study
Medicare outpatient imaging interpretation turnaround times increased 27% from 2023 to 2024, reaching 6 h 1 min on average. The share of studies read ≥1 day later quadrupled in a decade (1.97% to 7.39%), per JACR analysis of ~3M claims.
<![CDATA[Emerging Insights, Research and Trends in Computed Tomography]]>
Fees and Payments (5-6-2026)
Medara nets $400,000 NCI grant for AI breast cancer risk platform
The Accreditation Process (Revised 8-4-2026)
Phantom Testing: PET (Revised 8-4-2026)
Phantom Testing: Nuclear Medicine (Revised 8-4-2026)
Quality Control: PET (Revised 8-4-2026)
Quality Control: Nuclear Medicine (Revised 8-4-2026)
ASTRO Names 39 Radiation Oncology Leaders as 2026 Fellows
Virginia Physicians for Women Employer Profile
60-year-old man with lesion on carcinoma follow-up revisited
GE HealthCare Launches Invenia ABUS Prime and ABUS StreamVue
A nonlinear subspace model using a denoising autoencoder jointly reconstructs k-q-space data, showing improved noise suppression and detail preservation versus MUSE and LLR in high b-value diffusion-weighted imaging, with minimal bias and higher precision.
After acute MI, multivessel disease (MVD) shows higher native T1, extracellular volume, and T2 in remote myocardium vs. single-vessel disease, differences persisting after adjusting for infarct size. Incomplete revascularization links to elevated remote ECV and T2.
Preliminary study: In bovine cartilage, Gaussian process regression predicted proteoglycan content from MR fingerprinting (median r=0.81, NRMSE 11.7%), but collagen fiber anisotropy prediction was weak (r=0.40). Raw MRF data outperformed qMRI maps.
In prostate MRI, moderate-to-severe hip prosthesis artifacts degraded all three deep-learning models (AUC 0.62–0.71) compared with exams without prostheses (AUC 0.74–0.81), while radiologist PI-RADS performance held up better (AUC 0.77–0.79 across artifact categories).
DLIR-H/50-keV dual-energy CT protocol showed non-inferiority to MRI for detecting arterial phase hyperenhancement (APHE) and washout in HCC, offering an alternative when MRI access is limited.
Manus AI using cone beam CT (CBCT) data achieved 95% detection and correct diagnosis of jaw lesions in 97 patients. Gemini 2.5 Pro detected 80% but correctly diagnosed 56%. Copilot and Claude were least accurate. Significant differences between chatbots.
National Turnaround Time Trends for Medicare Fee-for-Service Beneficiaries: Updated Through 2024.
A semi-automated CFD pipeline using deep-learning MRI assessed carotid wall shear stress in 100 Rotterdam Study participants. Lumen segmentation Dice 0.89±0.02 and inter-rater ICC 0.89–0.98, demonstrating feasibility for large-scale studies.
Nuclear medicine trainees can use AI to draft study guides, generate questions, and simulate patients, but must critically verify AI outputs to avoid inaccurate, biased information that undermines learning. Effective use requires goal setting, self-effort, and faculty review.
Nuclear medicine educators can practically apply AI through prompt engineering, chain-of-thought prompting, retrieval-augmented generation, custom tool development, and multimedia creation to build scalable, equitable, and personalized learning.
AI tools in nuclear medicine education must be grounded in learning theories and ethical guardrails: structured prompting, retrieval-augmented generation, and expert review safeguard human judgment, privacy, and critical thought.
