Alzheimer's disease diagnosis based on the Hippocampal Unified Multi-Atlas Network (HUMAN) algorithm

Nicola Amoroso, Marianna La Rocca, Roberto Bellotti, Annarita Fanizzi, Alfonso Monaco, Sabina Tangaro

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background: Hippocampal atrophy is a supportive feature for the diagnosis of probable Alzheimer's disease (AD). However, even for an expert neuroradiologist, tracing the hippocampus and measuring its volume is a time consuming and extremely challenging task. Accordingly, the development of reliable fully-automated segmentation algorithms is of paramount importance. Materials and methods: The present study evaluates (i) the precision and the robustness of the novel Hippocampal Unified Multi-Atlas Network (HUMAN) segmentation algorithm and (ii) its clinical reliability for AD diagnosis. For these purposes, we used a mixed cohort of 456 subjects and their T1 weighted magnetic resonance imaging (MRI) brain scans. The cohort included 145 controls (CTRL), 217 mild cognitive impairment (MCI) subjects and 94 AD patients from Alzheimer's Disease Neuroimaging Initiative (ADNI). For each subject the baseline, repeat, 12 and 24 month follow-up scans were available. Results: HUMAN provides hippocampal volumes with a 3% precision; volume measurements effectively reveal AD, with an area under the curve (AUC) AUC1=0.08±0.02. Segmented volumes can also reveal the subtler effects present in MCI subjects, AUC2=0.76±0.05. The algorithm is stable and reproducible over time, even for 24 month follow-up scans. Conclusions: The experimental results demonstrate HUMAN is a precise segmentation algorithm, besides hippocampal volumes, provided by HUMAN, can effectively support the diagnosis of Alzheimer's disease and become a useful tool for other neuroimaging applications.

Original languageEnglish
Article number6
Number of pages6
JournalBioMedical Engineering Online
Volume17
Issue number1
DOIs
Publication statusPublished - Jan 22 2018

Fingerprint

Atlases
Alzheimer Disease
Neuroimaging
Volume measurement
Magnetic resonance
Area Under Curve
Atrophy
Hippocampus
Brain
Magnetic Resonance Imaging
Imaging techniques

Keywords

  • Alzheimer's disease
  • Hippocampal Segmentation
  • MCI
  • Multi-atlas
  • Neural Networks

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Biomaterials
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Alzheimer's disease diagnosis based on the Hippocampal Unified Multi-Atlas Network (HUMAN) algorithm. / Amoroso, Nicola; Rocca, Marianna La; Bellotti, Roberto; Fanizzi, Annarita; Monaco, Alfonso; Tangaro, Sabina.

In: BioMedical Engineering Online, Vol. 17, No. 1, 6, 22.01.2018.

Research output: Contribution to journalArticle

Amoroso, Nicola ; Rocca, Marianna La ; Bellotti, Roberto ; Fanizzi, Annarita ; Monaco, Alfonso ; Tangaro, Sabina. / Alzheimer's disease diagnosis based on the Hippocampal Unified Multi-Atlas Network (HUMAN) algorithm. In: BioMedical Engineering Online. 2018 ; Vol. 17, No. 1.
@article{97de8f4a01534674a27f441d843b544a,
title = "Alzheimer's disease diagnosis based on the Hippocampal Unified Multi-Atlas Network (HUMAN) algorithm",
abstract = "Background: Hippocampal atrophy is a supportive feature for the diagnosis of probable Alzheimer's disease (AD). However, even for an expert neuroradiologist, tracing the hippocampus and measuring its volume is a time consuming and extremely challenging task. Accordingly, the development of reliable fully-automated segmentation algorithms is of paramount importance. Materials and methods: The present study evaluates (i) the precision and the robustness of the novel Hippocampal Unified Multi-Atlas Network (HUMAN) segmentation algorithm and (ii) its clinical reliability for AD diagnosis. For these purposes, we used a mixed cohort of 456 subjects and their T1 weighted magnetic resonance imaging (MRI) brain scans. The cohort included 145 controls (CTRL), 217 mild cognitive impairment (MCI) subjects and 94 AD patients from Alzheimer's Disease Neuroimaging Initiative (ADNI). For each subject the baseline, repeat, 12 and 24 month follow-up scans were available. Results: HUMAN provides hippocampal volumes with a 3{\%} precision; volume measurements effectively reveal AD, with an area under the curve (AUC) AUC1=0.08±0.02. Segmented volumes can also reveal the subtler effects present in MCI subjects, AUC2=0.76±0.05. The algorithm is stable and reproducible over time, even for 24 month follow-up scans. Conclusions: The experimental results demonstrate HUMAN is a precise segmentation algorithm, besides hippocampal volumes, provided by HUMAN, can effectively support the diagnosis of Alzheimer's disease and become a useful tool for other neuroimaging applications.",
keywords = "Alzheimer's disease, Hippocampal Segmentation, MCI, Multi-atlas, Neural Networks",
author = "Nicola Amoroso and Rocca, {Marianna La} and Roberto Bellotti and Annarita Fanizzi and Alfonso Monaco and Sabina Tangaro",
year = "2018",
month = "1",
day = "22",
doi = "10.1186/s12938-018-0439-y",
language = "English",
volume = "17",
journal = "BioMedical Engineering Online",
issn = "1475-925X",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Alzheimer's disease diagnosis based on the Hippocampal Unified Multi-Atlas Network (HUMAN) algorithm

AU - Amoroso, Nicola

AU - Rocca, Marianna La

AU - Bellotti, Roberto

AU - Fanizzi, Annarita

AU - Monaco, Alfonso

AU - Tangaro, Sabina

PY - 2018/1/22

Y1 - 2018/1/22

N2 - Background: Hippocampal atrophy is a supportive feature for the diagnosis of probable Alzheimer's disease (AD). However, even for an expert neuroradiologist, tracing the hippocampus and measuring its volume is a time consuming and extremely challenging task. Accordingly, the development of reliable fully-automated segmentation algorithms is of paramount importance. Materials and methods: The present study evaluates (i) the precision and the robustness of the novel Hippocampal Unified Multi-Atlas Network (HUMAN) segmentation algorithm and (ii) its clinical reliability for AD diagnosis. For these purposes, we used a mixed cohort of 456 subjects and their T1 weighted magnetic resonance imaging (MRI) brain scans. The cohort included 145 controls (CTRL), 217 mild cognitive impairment (MCI) subjects and 94 AD patients from Alzheimer's Disease Neuroimaging Initiative (ADNI). For each subject the baseline, repeat, 12 and 24 month follow-up scans were available. Results: HUMAN provides hippocampal volumes with a 3% precision; volume measurements effectively reveal AD, with an area under the curve (AUC) AUC1=0.08±0.02. Segmented volumes can also reveal the subtler effects present in MCI subjects, AUC2=0.76±0.05. The algorithm is stable and reproducible over time, even for 24 month follow-up scans. Conclusions: The experimental results demonstrate HUMAN is a precise segmentation algorithm, besides hippocampal volumes, provided by HUMAN, can effectively support the diagnosis of Alzheimer's disease and become a useful tool for other neuroimaging applications.

AB - Background: Hippocampal atrophy is a supportive feature for the diagnosis of probable Alzheimer's disease (AD). However, even for an expert neuroradiologist, tracing the hippocampus and measuring its volume is a time consuming and extremely challenging task. Accordingly, the development of reliable fully-automated segmentation algorithms is of paramount importance. Materials and methods: The present study evaluates (i) the precision and the robustness of the novel Hippocampal Unified Multi-Atlas Network (HUMAN) segmentation algorithm and (ii) its clinical reliability for AD diagnosis. For these purposes, we used a mixed cohort of 456 subjects and their T1 weighted magnetic resonance imaging (MRI) brain scans. The cohort included 145 controls (CTRL), 217 mild cognitive impairment (MCI) subjects and 94 AD patients from Alzheimer's Disease Neuroimaging Initiative (ADNI). For each subject the baseline, repeat, 12 and 24 month follow-up scans were available. Results: HUMAN provides hippocampal volumes with a 3% precision; volume measurements effectively reveal AD, with an area under the curve (AUC) AUC1=0.08±0.02. Segmented volumes can also reveal the subtler effects present in MCI subjects, AUC2=0.76±0.05. The algorithm is stable and reproducible over time, even for 24 month follow-up scans. Conclusions: The experimental results demonstrate HUMAN is a precise segmentation algorithm, besides hippocampal volumes, provided by HUMAN, can effectively support the diagnosis of Alzheimer's disease and become a useful tool for other neuroimaging applications.

KW - Alzheimer's disease

KW - Hippocampal Segmentation

KW - MCI

KW - Multi-atlas

KW - Neural Networks

UR - http://www.scopus.com/inward/record.url?scp=85040861248&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040861248&partnerID=8YFLogxK

U2 - 10.1186/s12938-018-0439-y

DO - 10.1186/s12938-018-0439-y

M3 - Article

AN - SCOPUS:85040861248

VL - 17

JO - BioMedical Engineering Online

JF - BioMedical Engineering Online

SN - 1475-925X

IS - 1

M1 - 6

ER -