Technology

Initial breast cancer risk scoring with adjunctive AI assessment of screening mammograms increased by approximately 80 percent in a subsequent screening round for women with breast cancer, according to research findings presented at the European Congress of Radiology.

Catch up on a variety of new FDA clearances and approvals in radiology from the past week.

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

The Harrison.ai software is reportedly the first AI software to gain clearance for acute infarct triage on non-contrast CT scans.

Reportedly the first generative AI model in radiology to receive the FDA breakthrough device designation, Cognita Chest X-Ray (CXR) facilitated an 18 percent improvement in CXR interpretation efficiency based on preliminary data.

In addition to significantly reduced interpretation time, researchers found that adjunctive AI with ultrasound resulted in accuracy improvements of greater than 7 percent for nodule echogenicity and 16 percent for nodule margin assessments.

Offering reportedly seamless integration into workflows for prenatal evaluations and real-time decision-making, the cloud-based Delivery Date AI software was trained on millions of ultrasound images from diverse pregnancies.

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

Catch up on the most-well viewed radiology content in February 2026.

The FDA clearance for the AI-enabled chest X-ray software qXR-Detect reportedly includes detection of findings in the lung, pleura, hila and heart, bone and mediastinum.

Catch up on the most well-viewed video interviews from Diagnostic Imaging in February 2026.

Offering AI-powered automation features and advanced imaging capabilities, the new LOGIQ E10 series, the LOGIC Fortis™ and the LOGIQ Totus™ ultrasound platforms will be introduced at the European Congress of Radiology in March.

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

In a recent interview, Nina Kottler, M.D., discussed the agility of agentic AI to achieve system-level goals in radiology, the need for transparency and how agentic AI may affect the future of radiology.

The use of adjunctive AI led to higher detection of breast cancer in women with dense breasts as well as increased detection of invasive cancer and lobular cancer, according to new research involving over 100,000 screening DBT exams.

Catch up on a variety of new FDA clearances and approvals in radiology from the past week.

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

New MRI research suggests that adjunctive AI may lead to a significant reduction of unnecessary prostate biopsies.

The FDA clearances include the 1.5T SIGNA Sprint with Freelium MRI platform, the 3T SIGNA Bolt MRI system and the AI-powered SIGNA One, which reportedly enhances MRI workflow efficiencies.

A machine learning model incorporating cardiac MRI and clinical data provided a 91 percent AUC for predicting major adverse cardiovascular events (MACE) in patients with STEMI, according to a new study involving over 1,000 patients and a median follow-up of 40 months.

Sharing his perspective as well as insights from recently published research, Benjamin Kann, M.D., discussed the utility of AI foundation models for accessing an array of diagnostic and prognostic data from brain MRI scans.

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

In the debut of her new “Breast Imaging in Focus” series, Manisha Bahl, M.D., discusses the recently published Lancet study on AI, mammography and interval breast cancer, and shares her perspective on the potential impact of these findings for breast radiologists.

Artificial intelligence scores > 73.5 percent for mammography were associated with over a threefold higher cumulative incidence rate for ipsilateral recurrence of DCIS in women treated with breast-conserving surgery, according to new research.

Emphasizing that specialized standalone AI tools are on the verge of being obsolete, this author maintains that successful AI platforms will facilitate access to clinical context data, adaptability and seamless integration into radiology workflows.