AI

Assessing the simulated use of AI-generated suspicion scores for determining whether one should continue with full MRI or shift to an abbreviated MRI, the authors of a new study noted comparable sensitivity, specificity, and positive predictive value for biopsies between the MRI approaches.

The use of adjunctive AI software with pre-treatment PET imaging demonstrated over a fourfold higher likelihood of predicting progression-free survival (PFS) in patients being treated for lymphoma, according to a new meta-analysis.

Through AI recognition of subtle patterns in breast tissue on screening mammograms, the Clairity Breast software reportedly provides validated risk scoring for predicting one’s five-year risk of breast cancer.

The Optive AI software, the tenth software release for the Swoop portable MRI system, reportedly offers enhanced clarity and anatomical detail for ultra-low-field MRI of the brain.

Catch up on the most-well viewed radiology content in May 2025.

The Lunit Insight CXR4 update reportedly offers new features such as current-prior comparison of chest X-rays (CXRs), acute bone fracture detection and a 99.5 percent negative predictive value (NPV) for identifying normal CXRs.

Catch up on the top AI-related news and research in radiology over the past month.

Catch up on the top radiology content of the past week.

The MSKai software provides AI-powered segmentation, labeling, and measurement tools for assessment of T2-weighted MRIs of the lumbar spine.

In a study involving over 12,000 Asian women, researchers found that an artificial intelligence (AI) model converted over 83 percent of false positives in patients with initial BI-RADS 3 and 4 assessments into benign BI-RADS categories.

The Rapid CTP AI software offered 23 percent greater detection of medium vessel occlusions in comparison to the Viz CTP AI software, according to research presented at the European Stroke (Organization) Conference (ESOC).

The cloud-based platform reportedly facilitates AI-enhanced teleradiology workflow efficiencies across multiple systems and facilities.

In never-smokers, deep learning assessment of single baseline low-dose computed tomography (CT) scans demonstrated a 79 percent AUC for predicting lung cancer up to six years later, according to new research presented today at the American Thoracic Society (ATS) 2025 International Conference.

Catch up on the top radiology content of the past week.

The CleaRecon DL software reportedly removes streak artifacts that can occur with the use of cone-beam computed tomography (CBCT) during interventional radiology procedures.

In a recent interview, C. Alberto Morales, M.D., discussed the impact of advances with CTA imaging and AI, and a shifting emphasis in cardiac risk stratification from stenosis to plaque burden.

In a study involving over 1,000 patients who had coronary computed tomography angiography (CCTA) exams, AI software demonstrated a 90 percent AUC for assessments of cases > CAD-RADS 3 and 4A and had a 98 percent NPV for obstructive coronary artery disease.

The latest FDA 510(k) clearance is for B-Right Views, an AI-enabled device, which provides automated detection of required views necessary for second- and third-trimester fetal heart ultrasound exams.

Employing intelligent robotics and enhanced low-dose image quality, the uAngio AVIVA X-ray system also offers hands-free image review and movement.

The use of AI software for digital breast tomosynthesis (DBT) facilitated a higher cancer detection rate and over double the PPV for exams with abnormal interpretation, according to a newly published study.

The combination of high-performance gradient technology and AI tools with the Signa Sprint MRI reportedly facilitate enhanced MRI workflow efficiencies in cardiac and oncology imaging.

Catch up on the top radiology content of the past week.

While AI-enabled hippocampal segmentation on MRI offered a 95 percent AUC for differentiating between Alzheimer’s disease and normal controls in a 27-study meta-analysis, it offered significantly lower sensitivity and specificity in differentiating mild cognitive impairment.

For DBT breast cancer screening, 47 percent of radiologist-only flagged false positives involved mass presentations whereas 40 percent of AI-only flagged false positive cases involved benign calcifications, according to research presented at the recent American Roentgen Ray Society (ARRS) conference.

The combination of the Aurora SPECT/CT system with AI-enabled Clarify DL image reconstruction reportedly offers the potential of enhanced image quality and streamlined workflows in nuclear medicine.