Manual Planimetry of the Medial Temporal Lobe Versus Automated Volumetry of the Hippocampus in the Diagnosis of Alzheimer's Disease

Abstract

Introduction:Though a disproportionate rate of atrophy in the medial temporal lobe (MTA) represents a reliable marker of Alzheimer’s disease (AD) pathology, measurement of the MTA is not currently widely used in daily clinical practice. This is mainly because the methods available to date are sophisticated and difficult to implement in clinical practice (volumetric methods), are poorly explored (linear and planimetric methods), or lack objectivity (visual rating). Here, we aimed to compare the results of a manual planimetric measure (the yearly rate of absolute atrophy of the medial temporal lobe, 2D-yrA-MTL) with the results of an automated volumetric measure (the yearly rate of atrophy of the hippocampus, 3D-yrA-H).Methods:A series of 1.5T MRI studies on 290 subjects in the age range of 65–85 years, including patients with AD (n = 100), mild cognitive impairment (MCI) (n = 100), and matched controls (n = 90) from the AddNeuroMed study, were examined by two independent subgroups of researchers: one in charge of volumetric measures and the other in charge of planimetric measures.Results:The means of both methods were significantly different between AD and the other two diagnostic groups. In the differential diagnosis of AD against controls, 3D-yrA-H performed significantly better than 2D-yrA-MTL while differences were not statistically significant in the differential diagnosis of AD against MCI.Conclusion:Automated volumetry of the hippocampus is superior to manual planimetry of the MTL in the diagnosis of AD. Nevertheless, the 2D-yrAMTL is a simpler method that could be easily implemented in clinical practice when volumetry is not available.

A ‘Comprehensive Visual Rating Scale’ for predicting progression to dementia in patients with mild cognitive impairment

“…A visual rating scale, such as CVRS better reflects the observations of a clinician on brain MRI and is a simple score that might be useful for assessing an individual in a primary clinical setting. In contrast, automated imaging analysis tools are more appropriate for detailed research with group analyses in a longitudinal follow-up [ 39 ].…”

AVRA: Automatic visual ratings of atrophy from MRI images using recurrent convolutional neural networks

“…This nuance might be important information for the physician diagnosing dementia, but in research single integer scores have typically been used following the original definitions of the rating scales. Previous attempts of (semi-)automatic atrophy measures have output a continuous measure [17,18,63,19]. The main advantages of using a continuous measure of atrophy are 1) atrophy evolves continuously and thus it is reasonable to describe its degree through a continuous measure, and 2) it provides more detailed information about the severity of the atrophy.…”

Predicting progression to dementia with “comprehensive visual rating scale” and machine learning algorithms

“…Additionally, the CVRS is a cost-effective diagnostic tool ideally suited for implementation in clinical practice ( 15 ). In contrast, automated image analysis tools are more appropriate for detailed research that includes group analyses and a longitudinal follow-up ( 34 ). We attempted to utilize a good combination of multi-modal and highly accessible data for the predictive models by considering conventional demographic and cognitive information such as clinical data, MRI features such as CVRS score, and cortical thickness.…”