Senior Editor, Diagnostic Imaging
In the second part of a two-part interview on the recently published appropriate use criteria for brain positron emission tomography (PET) for patients with mild cognitive impairment (MCI), Phillip Kuo, M.D. discusses clinical cases involving the use of amyloid and tau PET imaging.
In sequential breast cancer screening with digital breast tomosynthesis (DBT), true positive examinations had more than double the AI case score of true negative examinations and the highest positive AI score changes from previous exams, according to new research.
The CDM Insights software, which can be utilized with scans from 1.5T and 3T MRI, reportedly provides new measurements of cortical thickness and brain microstructure.
In the first part of a two-part interview, Nina Kottler, M.D. offers insights and perspective on the recently issued guidance from the FDA on AI-enabled devices and how it may impact developers in the radiology field.
In computed tomography (CT) scans for patients with solid non-small cell lung cancer (NSCLC) < 30 mm, emerging research suggests the lollipop sign is associated with a greater than fourfold likelihood of angiolymphatic invasion.
Deep learning synthesis of contrast-enhanced MRI from non-contrast prostate MRI sequences provided an average multiscale structural similarity index of 70 percent with actual contrast-enhanced prostate MRI in external validation testing from newly published research.
In a recent interview, Phillip Kuo, M.D., discussed the impact of newer anti-amyloid antibody therapies for Alzheimer’s disease upon recently issued appropriate use criteria (AUC) for amyloid positron emission tomography (PET) imaging as well as the incorporation of tau PET into the AUC for patients with mild cognitive impairment.
Employing baseline MRI and clinical data, an emerging deep learning model was 32 percent more likely to predict the progression of low-risk prostate cancer (PCa) to clinically significant prostate cancer (csPCa), according to new research.
The IQ-UIP AI software may bolster computed tomography diagnosis of usual interstitial pneumonia (UIP), which is reportedly misdiagnosed in over 50 percent of cases.
In a literature review that includes insights from recently issued guidelines from multiple European medical societies, researchers discuss the role of magnetic resonance imaging (MRI) in facilitating appropriate patient selection for fertility-sparing treatments to address early-stage endometrial and cervical cancer.
InkSpace Imaging’s 24-channel MRI coil, which will be included in Magnetom 1.5T scanners from Siemens Healthineers, reportedly facilitates quicker set-ups for technologists and enhanced spatial resolution.
In a study of over 463,000 women who had screening mammography exams, adjunctive AI led to a 17.6 percent higher detection rate for breast cancer and a three percent increase in positive predictive value for recalls.
After propensity score matching in a study of over 3,000 women with a personal history of breast cancer, researchers found that surveillance breast MRI facilitated a 59 percent lower risk in advanced presentations of second breast cancers.
The appropriate use criteria (AUC) reflect updates to the 2013 AUC for amyloid PET and new criteria for tau PET in the diagnosis and monitoring of patients with mild cognitive impairment (MCI).
In a recent interview, Arlene Sussman, M.D., discussed her experience in leading vRad’s teleradiology breast imaging service, how to foster personalized care in breast cancer screening, utilizing AI to help mitigate daunting worklists and improving access to subspecialty care.
Survey results revealed that 71 percent of clinicians preferred adjunctive AI in facilitating triage of brain MRI scans and 58 percent were comfortable utilizing AI triage without input from radiologists.
For hepatocellular carcinoma screening, a 19-study meta-analysis found the abbreviated MRI sequencing protocol of T2-weighted MRI, diffusion-weighted imaging (DWI) and hepatobiliary phase (HBP) imaging offered 88 percent sensitivity and 93 percent specificity.
In patients with high-risk, hormone sensitive prostate cancer who had no evidence of metastasis on conventional imaging, PSMA PET revealed polymetastatic disease in 24 percent of patients and M1 disease staging in 46 percent of patients.
Adjunctive AI offered greater than seven percent increases in sensitivity, specificity, and accuracy for ultrasound detection of ovarian cancer in comparison to unassisted clinicians who lacked ultrasound expertise, according to findings from new international multicenter research.
For patients with localized prostate cancer and PI-RADS 3 or higher lesions, MRI-guided micro-ultrasound multifiber focal laser ablation had an 18 percent recurrence rate at one year, according to newly published research.
In the third part of a three-part interview from the recent RSNA conference, Mark Traill, M.D., discusses the potential of image-based risk assessment artificial intelligence (AI) algorithms in bolstering adherence to screening protocols for women at high risk for breast cancer.
Seventy percent of LR-M hepatocellular carcinoma (HCC) cases were associated with rapid growth in comparison to 12.5 percent of LR-4 HCCs and 28.5 percent of LR-4 HCCs, according to a new study.
Catch up on video interviews from the recent 2024 Radiological Society of North America (RSNA) conference.
In the second part of a three-part interview from the recent RSNA conference, Mark Traill, M.D., emphasizes patience and monitoring with the assessment of AI to ensure optimal use of the technology to help ease the strain of increasing breast imaging volume.
In the first of a three-part interview from the recent RSNA conference, Mark Traill, M.D., discusses current challenges in breast radiology and the potential of AI to help mitigate some of these issues.
In a new study involving nearly 600 biopsy-naïve men, researchers found that only 4 percent of those with negative prostate MRI had clinically significant prostate cancer after three years of active monitoring.
Convolutional neural network-enabled segmentation of brain MRI offered a 25.7 percent higher specificity than a radiomic model for differentiating radionecrosis and metastatic progression in patients treated with stereotactic radiosurgery for brain metastases.
Ten-minute and five-minute knee MRI exams with compressed sequences facilitated by deep learning offered nearly equivalent sensitivity and specificity as an 18-minute conventional MRI knee exam, according to research presented recently at the RSNA conference.
The use of an adjunctive machine learning model led to 17 and 21 percent improvements in the AUC and sensitivity rate, respectively, for PET/MRI in diagnosing extraprostatic tumor extension in patients with primary prostate cancer.
A CT-based radiomic model offered over 10 percent higher specificity and positive predictive value for high-risk lung adenocarcinoma in comparison to a radiographic model, according to external validation testing in a recent study.
