Employing a hybrid positron emission tomography (PET)/magnetic resonance imaging (MRI) model to assess predictive features of Alzheimer’s disease (AD), researchers noted a 100 percent sensitivity rate and a 93 percent sensitivity rate for distinguishing between AD and normal cognition, according to a study presented at the recent Society of Nuclear Medicine and Molecular Imaging (SNMMI) conference in Chicago.
Assessing predictive hippocampal radiomic features with a multimodal combination of positron emission tomography (PET) and magnetic resonance imaging (MRI) may lead to earlier detection of Alzheimer’s disease (AD), according to new research presented at the recent Society of Nuclear Medicine and Molecular Imaging (SNMMI) conference in Chicago.
Noting key early predictive features for AD, ranging from glucose metabolism to decreased cerebral blood flow and hippocampal atrophy, researchers assessed a multiparametric imaging model for differentiating between AD, mild cognitive impairment (MCI) and normal cognition (NC) in 159 patients.1 The imaging model included the use of arterial spin-labeling (ASL) T1-weighted MRI and 18F-fluorodeoxyglucose PET (18F-FDG PET), according to the study.
With the fivefold cross-validation logistic regression model, the researchers found an area under the curve (AUC) of 98 percent as well as a 93 percent specificity rate and a 100 percent sensitivity rate for differentiating between AD and NC.1
For the differentiation of AD and MCI, the study authors noted an AUC of 85 percent, 88 percent sensitivity and 73 percent specificity. The multiparametric imaging model also demonstrated an AUC of 86 percent, 80 percent sensitivity and 81 percent specificity for differentiating between MCI and NC, according to the study.1
“Our findings demonstrate that multi-dimensional imaging of the hippocampal radiomics benefits the identification of early AD and may provide a potential biomarker for clinical applications in AD,” noted Jie Lu, M.D., who is affiliated with the Department of Radiology and Nuclear Medicine at Xuanwu Hospital and Capital Medical University in Beijing, China, and colleagues.
(Editor’s note: For related content, see “GE HealthCare Debuts New PET/MRI System at SNMMI Conference,” “FDA Clears AI-Powered MRI Software to Assess for Brain Atrophy” and “Brain PET Study Suggests Link Between Early Amyloid Accumulation and Repetitive Subconcussive Trauma.”)
Reference
1. Chen Z, Yan S, Bi S, Cui B, Yang H, Lu J. Early diagnosis of Alzheimer’s disease using multiparametric hippocampal signatures with 18F-FDG PET/MR radiomics. Poster presented at Society of Nuclear Medicine and Molecular Imaging (SNMMI) 2023 Annual Meeting June 24-June 27, Chicago. Available at: https://am.snmmi.org/imis/SNMMI-AM . Accessed June 29, 2023.
Mammography Study Compares False Positives Between AI and Radiologists in DBT Screening
May 8th 2025For DBT breast cancer screening, 47 percent of radiologist-only flagged false positives involved mass presentations whereas 40 percent of AI-only flagged false positive cases involved benign calcifications, according to research presented at the recent American Roentgen Ray Society (ARRS) conference.
MRI Study at ARRS Raises Questions About Disparities in Detection of MASLD
May 3rd 2025New research revealed that Hispanic Americans with evidence of hepatic steatosis on MRI but no formal diagnosis of MASLD had over a fourfold higher risk of developing hepatocellular carcinoma in comparison to those who had a formal diagnosis of MASLD.
FDA Clears MRI-Based AI Segmentation of Organs at Risk During Radiation Therapy
May 2nd 2025Capable of segmenting over 37 organs and structures in the head, neck and pelvis, the MR Contour DL software is currently being showcased at the European Society for Radiotherapy and Oncology (ESTRO) conference.
Study Examines CT-Based AI Detection of Incidental Abdominal Aortic Aneurysms
April 29th 2025The AI software Viz AAA offered a sensitivity of 87.5 percent in detecting abdominal aortic aneurysms on contrast-enhanced CT, according to new retrospective research presented at the American Roentgen Ray Society (ARRS) conference.