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.
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.
A multiphase CT angiography spot sign identified high-risk intracerebral hemorrhage: hematoma expansion occurred in 25/51 (49%) phase-1, 13/28 (46%) phase-2, and 4/9 (44%) phase-3 spots versus 12/71 (17%) with no spot sign.
A hippocampal laterality radiomics model using 18F-FDG PET texture asymmetry achieved an AUC of 0.898 for differentiating anti-LGI1 from anti-GABABR encephalitis in a retrospective study of 82 patients.
Quantitative MRI metrics such as apparent diffusion coefficient, relaxation times, and perfusion reflect tumor cellularity and hypoxia, enabling biology-guided radiotherapy target delineation; standardization and multicenter validation remain key challenges.
International expert consensus guidelines provide 17 recommendations for lung ultrasound (LUS)-guided non-fiberobronchoscopic bronchoalveolar lavage (NFB-BAL) in neonates with atelectatic pulmonary disease, aiming to standardize care and improve outcomes.
SimonMed Optellum partner on AI lung nodule risk assessment
Lawrence Tanenbaum Named Executive Medical Director at Subtle Medicalrr
Subtle Medical names Tanenbaum executive medical director
Prenuvo integrates Myocardial Solutions' MRI software.
<![CDATA[Advances in AI — August 2026]]>
Surgeon-Performed Point-of-Care Ultrasound in Complex Breast Lesions: Implications for Oncologic Diagnosis and Surgical Planning
<![CDATA[Misfortune, Mistake, or Malfeasance? A Tool to Hone Outside of Radiology]]>
Radiotherapy access could address gynecological cancer disparities
MRI detects ARIA in 21% of real-world donanemab patients
Radiology groups told CMS chief of staff that some insurers propose in-network rates 21% below market, driving costly arbitration. CMS acknowledges enforcement gaps, vows priority action, as appeals court nixes ‘ghost rates’ for qualifying payment amounts.
Mammography for isolated breast pain with normal clinical exam found cancer in 0.6% (6 per 1,000) of 6,670 women—lower than the UK screening rate of 0.7%. Avoiding this low-yield imaging could reduce unnecessary costs and clinic congestion.
In 880 men, mpMRI readings with 99% certainty of prostate cancer had 100% clinically significant tumors on biopsy. At 90% certainty, 98% had significant disease. Overall, 14% of patients could potentially skip biopsy and proceed directly to treatment.
Multimodal artificial intelligence in prostate cancer: integrating multiparametric MRI with clinicopathological, molecular, and functional imaging data
AI can enhance HRCT interpretation in interstitial lung disease by detecting subtle abnormalities, classifying patterns, and generating quantitative biomarkers. Multimodal models may refine risk stratification. Prospective validation is needed for clinical translation.
A trastuzumab-targeted ultrasmall iron-oxide MRI nanoprobe plus 3D nnU-Net post-processing yielded a 2.59-fold higher tumor-to-normal ratio and Dice 0.93 for HER2-positive breast tumor boundary delineation.
PRECISE v2 provides a standardized lexicon for prostate MRI during active surveillance, covering lesion-level and technical descriptors, stable disease, and the non-assessable PRECISE X category. Organizing terms by context of use may improve consistency and reduce ambiguity in…
Combining multiparametric MRI with clinical variables incrementally improves prostate cancer AI model discrimination over MRI alone. Integration with PSMA PET and pathology further aids staging and prognosis. Domain shift and missing-modality robustness remain key barriers to cl…
Expanding Role of Radiology in the Era of Artificial Intelligence and Multi-Omics: From Image Interpreter to Integrated Diagnostician
Cloud-based AI segmented anterior teeth on CBCT from five scanners with 90.1% adequacy, Dice coefficients 0.96-0.97, and <0.07mm median distance. Endodontic treatment, brackets, and high-density artifacts increased refinement odds.
An integrated CT-MRI deep learning model plus clinical features achieved AUCs of 0.89-0.90 for preoperative hepatocellular carcinoma (HCC) grading, significantly outperforming multimodality alone (0.72-0.82) and clinical model (0.59-0.73) in 250 patients across three institution…
In 99 renal cell carcinoma (RCC) patients receiving immune checkpoint blockade before nephrectomy, ≥30% radiologic tumor shrinkage (p=0.0036) and greater pathologic regression (HR 0.97, CI 0.95-0.99) predicted longer time to next therapy.
New analysis of AI learning objectives in radiography curricula reveals three themes — Knowledge, Skills, Competencies — spanning 15 subthemes, from patient safety to coding AI, highlighting need for role-based education.
Vacuum-Assisted Retrieval of a Migrated Bullet.
Stacked deep learning ensembles achieved 0.96 accuracy and 1.00 macro-AUC for periapical lesion detection, with 0.94 sensitivity for lesions <2 mm. Small internal study; external validation needed.
A multiparametric MRI habitat imaging model predicted Ki-67 proliferation index ≥5% in meningiomas with AUCs of 0.929 in training and 0.903–0.914 in two external validation sets, outperforming whole-tumor radiomics.
Author Correction: Classification of fallers in Parkinson's disease through machine learning based feature analysis.
An MRI-based network vulnerability index improved prediction of MCI-to-dementia conversion (HR 1.47, p=0.004) when added to plasma p-tau217/Aβ42 model—supporting a plasma+MRI triage pathway for Alzheimer's.
