In multiple mammography datasets with the original radiologist-detected abnormality removed, deep learning detection of breast cancer had an average area under the curve (AUC) of 87 percent and an accuracy rate of 83 percent, according to research presented at the recent Society for Imaging Informatics in Medicine (SIIM) conference.

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

In a recent video interview from the Society for Imaging Informatics in Medicine (SIIM) conference, Ali Tejani, M.D., discussed pertinent insights on leveraging the value of adjunctive artificial intelligence (AI)-enabled triage software for computed tomography (CT) scans with radiology workflow improvements to achieve “clinically meaningful change” for patients with incidental pulmonary emboli findings.

In a recent video interview, Stephen Rose, M.D., reviewed a variety of factors that can impact interpretation of breast imaging for women with breast implants and discussed recent research showing a 22 percent reduction in cancer detection rate for this population in comparison to women without breast implants.

For patients initially diagnosed with non-metastatic, castration-resistant prostate cancer, pelvic lymph node involvement and five or more polymetastases detected with prostate-specific membrane antigen (PSMA)/ positron emission tomography (PET) are significantly associated with lower overall survival rates, according to recently presented research at the American Society of Clinical Oncology (ASCO) conference.

FIRMM-pix, a brain magnetic resonance imaging (MRI) software module recently launched at the International Society for Magnetic Resonance in Medicine (ISMRM) conference, reportedly employs visual biofeedback and gamification that coaches patients to stay still during brain MRI exams.

For patients with residual or recurrent grade 2 isocitrate dehydrogenase (IDH)-mutant gliomas, magnetic resonance imaging (MRI) revealed that daily dosing of vorasidenib, an inhibitor of mutant IDH1 and IDH2 enzymes, led to a median progression-free survival of 27.7 months in comparison to 11.1 months in a placebo group, according to new research presented at the 2023 American Society of Clinical Oncology (ASCO) Annual Meeting in Chicago.

The combination of Philips’ MR 7700 multi-nuclei scanner with the FDA-approved Xenoview hyperpolarized Xenon magnetic resonance imaging (MRI) contrast agent may facilitate earlier diagnosis and intervention for patients with obstructive lung diseases.

Adjunctive use of an artificial intelligence (AI) software demonstrated nearly equivalent sensitivity and over 28 percent higher accuracy in comparison to radiologist assessment of breast ultrasound images for breast lesions, according to new research presented at the recent Society of Breast Imaging (SBI) conference.

In a recent lecture at the American Roentgen Ray Society (ARRS) 2023 Annual Meeting, Andrew Callen, M.D., discussed a variety of imaging features associated with cerebrospinal fluid (CSF) leaks, the diagnostic utility of the Bern score as well as the merits of 3D T2FS MRI and dynamic computed tomography myelography.

Earlier initiation of imaging after contrast administration with contrast-enhanced mammography may provide better visibility of lesions and conspicuity against background parenchymal enhancement, according to new research presented at the American Roentgen Ray Society (ARRS) 2023 Annual Meeting in Honolulu, Hawaii.

Given the increasing prevalence of breast reconstruction, researchers discussed key signs of common complications on magnetic resonance imaging (MRI), ultrasound and other imaging during a recent presentation at the American Roentgen Ray Society (ARRS) 2023 Annual Meeting in Honolulu, Hawaii.

Three-dimensional (3D) slice-to-volume (SVR) fetal magnetic resonance imaging (MRI) has over six times the fetal optic pathway visualization rate of standard two-dimensional MRI, according to new research presented at the American Roentgen Ray Society (ARRS) 2023 Annual Meeting in Honolulu, Hawaii.

In a recent video interview, Kathy Schilling, M.D., discussed findings from a study of ProFound AI, an adjunctive artificial intelligence (AI) software for digital breast tomosynthesis (DBT), that demonstrated a 23 percent increase in breast cancer detection in comparison to DBT alone.

Comparing year-long findings with and without adjunctive artificial intelligence (AI) at a breast cancer screening program in Spain, researchers found the combination of digital breast tomosynthesis and AI had a 92.5 percent accuracy for diagnosing cancer in patients with elevated risk.

In a cum laude awarded presentation at the European Congress of Radiology (ECR), researchers discussed misconceptions and pertinent principles for magnetic resonance imaging (MRI) of patients with rectal cancer, ranging from the diagnosis of mucinous tumors to the impact of mesorectal fascia status for rectal cancer recurrence.

The new launches include the 80/160-slice computed tomography (CT) scanner Aquilion Serve, which allows simultaneous previews of axial, lateral and AP views, and Celex, a multipurpose X-ray system that offers automated and customizable features to help maximize workflow efficiencies.

In a video interview from the recent American Society of Clinical Oncology Genitourinary Cancers (ASCO GU) Symposium, Brian Chapin, MD, discussed emerging research that demonstrated the ability of the positron emission tomography (PET) agent 18F-rhPSMA-7.3 to diagnose distant M1 lesions prior to surgery for patients with intermediate to high-risk prostate cancer.

In a video interview at the recent Radiological Society of North America (RSNA) conference, Wayne Dell, M.D., discussed retrospective research that examined the use of hyperlinked multimedia radiology reports across modality and subspecialty five years after initial implementation of the technology at the University of Virginia.

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