Fully Automated Atlas-Based Hippocampus Volumetry for Clinical Routine: Validation in Subjects with Mild Cognitive Impairment from the ADNI Cohort

Abstract

Hippocampus volumetry based on magnetic resonance imaging (MRI) has not yet been translated into everyday clinical diagnostic patient care, at least in part due to limited availability of appropriate software tools. In the present study, we evaluate a fully-automated and computationally efficient processing pipeline for atlas based hippocampal volumetry using freely available Statistical Parametric Mapping (SPM) software in 198 amnestic mild cognitive impairment (MCI) subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI1). Subjects were grouped into MCI stable and MCI to probable Alzheimer's disease (AD) converters according to follow-up diagnoses at 12, 24, and 36 months. Hippocampal grey matter volume (HGMV) was obtained from baseline T1-weighted MRI and then corrected for total intracranial volume and age. Average processing time per subject was less than 4 minutes on a standard PC. The area under the receiver operator characteristic curve of the corrected HGMV for identification of MCI to probable AD converters within 12, 24, and 36 months was 0.78, 0.72, and 0.71, respectively. Thus, hippocampal volume computed with the fully-automated processing pipeline provides similar power for prediction of MCI to probable AD conversion as computationally more expensive methods. The whole processing pipeline has been made freely available as an SPM8 toolbox. It is easily set up and integrated into everyday clinical patient care.

Optimization of Statistical Single Subject Analysis of Brain FDG PET for the Prognosis of Mild Cognitive Impairment-to-Alzheimer’s Disease Conversion

“…The effect was statistically significant (two-sided p = 0.046). To put this into perspective, it might be noted that many studies suggest a capping of prognostic accuracy in MCI patients considerably below 100%, independent of the criteria and/or biomarkers used [28,[51][52][53][54]. Therefore, not only the relative improvement by 14%, but also the final absolute value of AUC = 0.832 appears rather remarkable, particularly as it can be achieved rather easily without extra costs, i.e., using standard FDG PET acquisition protocols (no dynamic imaging of the full time course of FDG concentration in tissue starting with i.v.…”

“…Unified segmentation was guided by freely available tissue probability maps (TPM) with 1 mm isotropic resolution generated from a sample of 662 healthy elderly subjects [27]. The latter might provide better performance in the elderly patients with suspected neurodegenerative disease than the 2 mm TPM from healthy young adults provided by SPM [28].…”

Structural imaging of hippocampal subfields in healthy aging and Alzheimer’s disease

“…Brewer et al, 2009;Chupin et al, 2009;Fischl et al, 2002;Leung et al, 2010;Morra et al, 2008;Patenaude et al, 2011), enabling less time-consuming and more reproducible segmentations of the structure. From this perspective, major efforts have been made to provide fully automated methods that could be used in clinical routine (Suppa et al, 2015a(Suppa et al, , 2015b.…”

Translating research findings into clinical practice: a systematic and critical review of neuroimaging-based clinical tools for brain disorders

“…Two of the eight tools (ADABOOST 35 and Qure 25 ) are designed to specifically perform a single type of analysis (hippocampus segmentation and gross abnormality identification, respectively). On the contrary, the other six tools (DIADEM 36,37 , Icobrain [38][39][40][41] , Jung Diagnostics 27,42,43 , Neu-roQuant 24,[44][45][46][47][48][49][50][51] , Quantib 52,53 , volBrain 54,55 ) are designed to extract multiple types of information from the data and/or evaluate multiple disorders.…”

“…Following these encouraging findings, some research teams have been developing imaging-based tools for making inferences at the level of the individual [24][25][26][27] . Through these tools, clinicians can upload the brain images of individual patients and receive an automatic report of the brain abnormalities detected.…”