AI

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

In a recently published article, researchers from Yale University discuss the pros and cons of current FDA regulations as they apply to the clearance and use of adjunctive artificial intelligence (AI) software with conventional breast cancer screening modalities such as mammography.

Emerging research revealed that a deep learning model had a nearly twofold increase in successful segmentation and reconstruction of coronary total occlusions (CTOs) on coronary computed tomography angiogram (CCTA) and a 73 percent reduction in post-processing and measurement time in comparison to a conventional manual approach.

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

In separate test sets of Israeli women and United States women who had either ductal carcinoma in situ or invasive breast cancer, emerging artificial intelligence (AI) algorithms achieved an area under the curve (AOC) of 88 percent and 80 percent, respectively, for malignancy detection.

Catch up on the top AI-related radiology content of the past month.

Rads will always have to deal with forces outside of their control, but it’s how we address those forces that makes us the type of radiologist we can be proud of.

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

The retrospective study of patients 21 years of age or younger found that a deep learning algorithm and use of the American College of Radiology’s Thyroid Imaging Reporting and Data System (TI-RADS) both had more than a 26 percent greater sensitivity for differentiating thyroid nodules on ultrasound in comparison to radiologist assessment.

For physicians performing radiotherapy treatment of soft tissue tumors in the head and neck, the MRCAT Head and Neck offers an artificial intelligence (AI) application that allows the use of magnetic resonance imaging (MRI) as the primary or sole imaging for procedure planning.

Plaque Analysis and RoadMap Analysis, two artificial intelligence (AI)-enabled assessment products, may enhance clinical evaluation of coronary artery disease (CAD) on cardiac computed tomography angiography (CCTA).

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

While artificial intelligence (AI) models have been acknowledged for aiding imaging analysis or facilitating workflow enhancements, this author envisions AI as a potential workstation conceierge capable of turning common venting and gripes into actionable items for significant improvements.

Incorporating artificial intelligence (AI)-based technology, Neosoma HGG reportedly demonstrated a 95.5 percent accuracy rate in measuring brain tumor volume on brain magnetic resonance imaging (MRI) scans at various points during the treatment of patients with high-grade gliomas.

TeraRecon Neuro reportedly offers six automated and customizable computed tomography (CT) perfusion maps that facilitate assessment of brain function in hemorrhagic and ischemic neurological cases.

Addressing upgrades of traditional infrastructure used in everyday radiology practice may be a more practical use of resources than investment in artificial intelligence (AI) technology that is still evolving.

AIR Recon DL, a deep learning-based image reconstruction software, will now be available with 3D sequences as well as PROPELLER motion-insensitive sequences on magnetic resonance imaging (MRI) scanners from GE Healthcare.

Catch up on the top AI-related radiology content of the past month.

Given the influx of artificial intelligence (AI)-powered tools in health care, this author examines the potential intersection of this technology and ultrasound examination in obstetrics and gynecologic (OB/GYN) care

New research reveals that an emerging deep learning tool had comparable sensitivity and specificity to radiologist assessment of contrast-enhanced computed tomography (CT) scans for pancreatic cancer, and a 74.7 percent sensitivity rate for tumors smaller than 2 cm.

Assessing high-resolution computed tomography (CT) scans of the wrist, CurveBeam AI’s OssView software reportedly enables clinicians to ascertain bone fragility and fracture risk for women over the age of 70.

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

Offering uniform high-resolution images through a combination of beamforming and enhanced image processing, the new ultrasound platform reportedly has an array of diagnostic features ranging from cardiovascular applications to breast lesion assessment.

Examining imaging data of patients from multiple countries, researchers found that a deep learning system demonstrated higher sensitivity and non-inferior specificity for detecting active tuberculosis on chest radiographs in comparison to nine radiologist reviewers.

A little positivity and praise towards others can go a long way for how you assess and treat yourself, too.

Researchers suggest that an artificial intelligence (AI)-powered risk stratification tool for lung nodules identified on computed tomography (CT) scans may identify likely malignancies more than one year prior to definitive diagnosis.

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

Researchers found that stand-alone use of an artificial intelligence (AI) model led to a 24.9 percent increase in sensitivity for diagnosing pulmonary nodules and a 21.4 percent increase in sensitivity for diagnosing pneumonia.

The automated measurement of heart ventricle diameters and detection of potential dilation in the right ventricle may facilitate quicker intervention in cases of pulmonary embolism.

In comparison to initial sonographer assessment of echocardiograms, cardiologists are over 10 percent less likely to change initial artificial intelligence (AI) assessment of left ventricular ejection fraction (LVEF), according to new research recently presented at the European Society of Cardiology Congress in Barcelona, Spain.