Diagnostic Efficacy of Structural MRI in Patients With Mild-to-Moderate Alzheimer Disease: Automated Volumetric Assessment Versus Visual Assessment

• Published in: American journal of roentgenology (1976) Vol. 208; no. 3; pp. 617 - 623
• Main Authors: Min, Jeeyoung, Moon, Won-Jin, Jeon, Ji Young, Choi, Jin Woo, Moon, Yeon-Sil, Han, Seol-Heui
• Format: Journal Article
• Language: English
• Published: United States 01.03.2017
• Subjects: Aged; Aged, 80 and over; Alzheimer Disease - diagnostic imaging; Alzheimer Disease - pathology; Cerebral Ventricles - diagnostic imaging; Cerebral Ventricles - pathology; Female; Hippocampus - diagnostic imaging; Hippocampus - pathology; Humans; Image Interpretation, Computer-Assisted - methods; Machine Learning; Magnetic Resonance Imaging - methods; Male; Middle Aged; Observer Variation; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; Scheltens scale; medial temporal lobe; volumetry; Alzheimer disease; MRI; quantitative
• ISSN: 0361-803X; 1546-3141; 1546-3141
• DOI: 10.2214/AJR.16.16894

The purpose of this study was to compare the diagnostic efficacies of an automated volumetric assessment tool and visual assessment in the evaluation of medial temporal lobar atrophy in mild-to-moderate Alzheimer disease (AD). This retrospective study included 30 patients with mild-to-moderate AD and 25 age-matched healthy control subjects undergoing MRI with a 3D fast spoiled gradient recalled-echo sequence at 3 T. The images were processed with fully automated volumetric analysis software. To assess medial temporal lobe (MTL) atrophy, two MTL indexes, which took into account the volumes of the hippocampus and the inferior lateral ventricle, were calculated with the automated volumetric assessment software. In addition, two neuroradiologists assessed MTL atrophy visually using the Scheltens scale. ROC curve analysis was used to compare the diagnostic performances of the two methods. The weighted kappa statistic was used to assess the intrarater and interrater reliability of visual inspection. The automated volumetric assessment tool had moderate sensitivity (63.3%) and high specificity (100%) in differentiating patients with mild-to-moderate AD from control subjects. Visual inspection showed sensitivity of 63.3% and specificity of 92.0%. The diagnostic performance was not significantly different between the two methods (p = 0.536-0.906). Intraobserver reliability for visual inspection was 0.858 and 0.902 for the two reviewers, and interobserver reliability was 0.692-0.780. Both the automated volumetric assessment tool and visual inspection can be used to evaluate MTL atrophy and differentiate patients with AD from healthy individuals with good diagnostic accuracy. Thus, the automated tool can be a useful and efficient adjunct in clinical practice for evaluating MTL atrophy in the diagnosis of AD.