MRI

In a multicenter study involving over 1,000 patients, a deep learning software offered comparable sensitivity and specificity for Gleason grade group > 2 tumors in comparison to radiologist interpretation.

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

The updated software reportedly enables a threefold improvement in MRI scan time and enhanced image sharpness.

Adolescents with post-COVID-19 conditions had 37 percent lower quantified lung perfusion than healthy control participants on phase-resolved functional lung MRI, according to findings from a recent prospective study.

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

In a recent literature review, researchers offered insights on current considerations with prostate MRI and discussed keys to effective use of the modality in screening for prostate cancer.

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

Low tumor sphericity on preoperative MRI is associated with a significantly higher mortality rate in patients with IDH-wildtype glioblastoma, according to a new study.

Researchers found that the use of seven-minute threefold parallel imaging-accelerated deep learning 3T MRI had 89 percent sensitivity for supraspinatus-infraspinatus tendon tears and 93 percent sensitivity for superior labral tears.

The updated AI-enabled software reportedly facilitates enhanced MRI imaging of the brain, abdomen, and pelvis.

The open-source, deep learning MRI segmentation tool reportedly offers over a 10 percent higher Dice score than similar segmentation models for 40 anatomical structures.

Black, Hispanic, and Asian women were over 25 percent less likely than White women to have same-day follow-up diagnostic service after abnormal findings on screening mammography exams, according to a new study involving over one million patients.

Researchers found that patients with high PSA density have more than double the risk of false-negative findings on prostate MRI and those with low PSA density are significantly less likely to have false-positive results.

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

Enabling up to 80 percent faster MRI scan times, the SubtleHD software is included in the newly launched AI software suite Subtle-Elite.

Reviewing current and emerging trends in imaging utilization and the impact of attrition rates and radiology residency positions on the field, researchers explore the future of radiology with two new provocative studies.

Preoperative use of the scoring system for gadoxetic acid-enhanced MRI demonstrated an average AUC of 85 percent and average specificity of 89 percent in external validation cohorts for pathologic features of hepatocellular carcinoma.

Anterior tumor location was over 14 times more likely to be associated with axillary metastasis after neoadjuvant treatment for breast cancer, according to new breast MRI and ultrasound research.

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

Emphasizing the role of radiologists in facilitating timely diagnosis of Marfan syndrome, Alan Braverman, M.D. discussed the use of echocardiography, CT, and MRI in evaluating patients with this genetic aortic condition.

For women with intermediate risk and a personal history of breast cancer, an emerging AI system offered an 81 percent AUC for breast cancer detection, according to new research.

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

In external validation testing, a deep learning model demonstrated an average AUC of 87.6 percent for detecting clinically significant prostate cancer (csPCA) on prostate MRI for patients with PI-RADS 3 assessments.

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

For patients with newly diagnosed obstructive coronary artery disease (CAD), a multimodal machine learning model offered an 86 percent AUC for predicting MACE, which was 10 percent higher than CCTA alone and over 35 percent higher than the Framingham Risk Score.