Senior Editor, Diagnostic Imaging
In a retrospective study involving mammography screening in over 114,000 women, researchers found that an artificial intelligence model had comparable specificity and sensitivity to radiologist screenings, reduced false positive results by 25 percent and reduced radiologist workload by more than 62 percent.
Emerging literature suggests a seemingly insurmountable wave of physician burnout in radiology. While the recently enacted Dr. Lorna Breen Health Care Provider Protection Act offers the promise of increased awareness, education, and funding to help prevent burnout, an increased commitment and flexibility from institutional leadership may also be key to erasing stigmas and driving meaningful change.
A new study suggests that deep learning algorithms with multimodal ultrasound have comparable specificity and sensitivity to subjective expert assessment and use of the O-RADS classification to distinguish between benign and malignant ovarian tumors.
Emphasizing the proper diagnostic characterization of sidewall aneurysms, the authors of a new study found no significant differences in occlusion status or complications when they compared the approved use of intrasaccular flow disruption for bifurcation aneurysms to off-label treatment of sidewall aneurysms.
Validating a prognostic scoring system for locoregional recurrence risk in post-mastectomy patients with varying levels of axillary lymph node involvement, emerging research suggests patients with intermediate risk for breast cancer recurrence could benefit from post-mastectomy radiotherapy.
The advisory emphasizes that the computer-aided triage and notification (CADt) devices, many of which incorporate artificial intelligence (AI) or machine learning technology, are intended to aid radiologists in prioritizing the assessment of brain imaging that may reveal signs of large vessel occlusion (LVO).
In a recent video interview, Arun Krishnaraj, MD, MPH and David Larson, MD, MBA, discussed the continued use of physical media to transport medical images between different health-care facilities, resulting inefficiencies and delays with patient care, and the initiative to create a linked multi-hub model to end this dated practice once and for all.
In addition to segmentation of the prostate, the artificial intelligence (AI)-enabled advance reportedly facilitates PI-RADS scoring by assessing the size and intensity of possible lesions.
The new artificial intelligence (AI) algorithm reportedly flags suspected cases of brain aneurysm and facilitates multidisciplinary care.
In a formal request to the Centers for Medicare and Medicaid Services (CMS), the American College of Radiology (ACR) emphasized that Medicare and Medicaid coverage of computed tomography colonography (CTC) could significantly improve colorectal cancer screening rates for at-risk populations.
Employing a deep learning system for pancreatic segmentation, researchers found that intrapancreatic fat percentage and pancreatic fractal dimension were among the key predictors for type 2 diabetes mellitus in a multivariable analysis.
Multivariable analysis from a recently published study found that males and people older than 60 years of age were more prone to persistent abnormalities on chest computed tomography (CT) one year after COVID-19 pneumonia.
Preliminary ultrasound findings from a study of over 3,000 women in early pregnancy found no association between fetal anomalies and initial COVID-19 vaccination.
The authors of a new meta-analysis found no significant differences between clinicians and artificial intelligence in diagnosing fractures but conceded that slightly over half of the studies assessed had a high risk of potential bias.
Powered by artificial intelligence, the new Ultrasound Workspace platform reportedly offers advanced echocardiography capabilities and facilitates enhanced diagnostic workflows.
In a recent video interview, Syam Reddy, MD discussed the merits of computed tomography (CT) colonography, a non-invasive alternative to conventional colonoscopy, which may help reduce gaps in screening for colorectal cancer.
A closer look at the Canadian National Breast Screening Studies (CNBSS) has revealed key methodological flaws that may prohibit use of the findings in the development of future guidelines on mammography screening for breast cancer.
The combination of the imaging agent Locametz and the targeted radioligand therapy Pluvicto may allow targeted treatment and mortality risk reduction in patients with prostate cancer.
In a recent video interview, Kevin J. Abrams, MD, discussed highlights from the recent 25th Annual Symposium of the American Society of Spine Radiology (ASSR), including lectures on imaging for spontaneous intracranial hypotension, the emergence of dynamic susceptibility contrast for MR perfusion and insights on the use of dual-energy computed tomography (CT) for diagnosing vertebral fractures.
Distinguishing between classic and non-classic presentations of isolated adnexal lesions on pelvic ultrasound reportedly had a high specificity and sensitivity in diagnosing ovarian cancer in women at average risk.
The artificial intelligence (AI) model reportedly had an 89.3 accuracy rate in differentiating between non-dense and dense breasts on mammography scans, and a 90.4 percent rate of agreement with human radiologist reviewers.
While breast arterial calcification is a common incidental finding on mammograms that is not routinely recommended for follow-up, statistically significant associations with cardiovascular risks may change that approach for postmenopausal women.
Emerging research suggests that an experimental alpha-synuclein (a-syn) positron emission tomography (PET) tracer may help diagnose multiple system atrophy (MSA) and potentially other neurodegenerative diseases such as Parkinson’s disease and Lewy body dementia.
New additions to the Philips Capsule Surveillance software include improved integration with health information technology (HIT) systems and enhanced visibility of patient data across remote devices.
The retrospective study, which involved nearly 1,000 patients with COVID-19, found that a high initial chest radiograph severity score was an independent risk factor for intrathoracic complications.
Offering a potential antidote to health-care silos that can hamper and delay care, the Enterprise Imaging and Informatics Suite may revamp image sharing and communication between providers.
The expanded FDA clearance for Collaboration Live (Philips) gives clinicians the option to consult on or diagnose ultrasound images from their mobile devices.
In addition to facilitating strong interreader agreement among radiologists of various experience levels, use of the proposed Neuropathy Score Reporting and Data System (NS-RADS) classification for peripheral neuropathy reportedly improved accuracy in differentiating between milder and more severe categories for muscle abnormalities and nerve lesions.
In a large study reviewing biennial mammography screening for women between the ages of 50 to 74, researchers estimated a 6.1 percent overdiagnosis rate for indolent pre-clinical cancer and a 9.3 percent overdiagnosis rate for progressive pre-clinical cancer in women who would have died from other causes prior to clinical diagnosis.
A recent multicenter study of BoneView AI noted a significant increase in sensitivity for fracture detection on X-rays and decreases in reading time for radiographs.
