ADMultiImg: A novel missing modality transfer learning based CAD system for diagnosis of MCI due to AD using incomplete multi-modality imaging data

Xiaonan Liu, Kewei Chen, Teresa Wu, David Weidman, Fleming Lure, Jing Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Alzheimer's Disease (AD) is the most common cause of dementia and currently has no cure. Treatments targeting early stages of AD such as Mild Cognitive Impairment (MCI) may be most effective to deaccelerate AD, thus attracting increasing attention. However, MCI has substantial heterogeneity in that it can be caused by various underlying conditions, not only AD. To detect MCI due to AD, NIA-AA published updated consensus criteria in 2011, in which the use of multi-modality images was highlighted as one of the most promising methods. It is of great interest to develop a CAD system based on automatic, quantitative analysis of multi-modality images and machine learning algorithms to help physicians more adequately diagnose MCI due to AD. The challenge, however, is that multi-modality images are not universally available for many patients due to cost, access, safety, and lack of consent. We developed a novel Missing Modality Transfer Learning (MMTL) algorithm capable of utilizing whatever imaging modalities are available for an MCI patient to diagnose the patient's likelihood of MCI due to AD. Furthermore, we integrated MMTL with radiomics steps including image processing, feature extraction, and feature screening, and a post-processing for uncertainty quantification (UQ), and developed a CAD system called "ADMultiImg" to assist clinical diagnosis of MCI due to AD using multi-modality images together with patient demographic and genetic information. Tested on ADNI date, our system can generate a diagnosis with high accuracy even for patients with only partially available image modalities (AUC=0.94), and therefore may have broad clinical utility.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2018
Subtitle of host publicationComputer-Aided Diagnosis
PublisherSPIE
Volume10575
ISBN (Electronic)9781510616394
DOIs
StatePublished - Jan 1 2018
EventMedical Imaging 2018: Computer-Aided Diagnosis - Houston, United States
Duration: Feb 12 2018Feb 15 2018

Other

OtherMedical Imaging 2018: Computer-Aided Diagnosis
CountryUnited States
CityHouston
Period2/12/182/15/18

Fingerprint

impairment
computer aided design
learning
Computer aided design
Alzheimer Disease
Imaging techniques
Learning algorithms
machine learning
physicians
Cognitive Dysfunction
Transfer (Psychology)
pattern recognition
quantitative analysis
Uncertainty
Area Under Curve
image processing
Dementia
Learning systems
Feature extraction
safety

Keywords

  • ADNI
  • Alzheimer's Disease
  • Mild Cognitive Impairment
  • Missing Modality Transfer Learning
  • NIA-AA criteria
  • Uncertainty Quantification

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

ADMultiImg : A novel missing modality transfer learning based CAD system for diagnosis of MCI due to AD using incomplete multi-modality imaging data. / Liu, Xiaonan; Chen, Kewei; Wu, Teresa; Weidman, David; Lure, Fleming; Li, Jing.

Medical Imaging 2018: Computer-Aided Diagnosis. Vol. 10575 SPIE, 2018. 105750I.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, X, Chen, K, Wu, T, Weidman, D, Lure, F & Li, J 2018, ADMultiImg: A novel missing modality transfer learning based CAD system for diagnosis of MCI due to AD using incomplete multi-modality imaging data. in Medical Imaging 2018: Computer-Aided Diagnosis. vol. 10575, 105750I, SPIE, Medical Imaging 2018: Computer-Aided Diagnosis, Houston, United States, 2/12/18. https://doi.org/10.1117/12.2293698
Liu, Xiaonan ; Chen, Kewei ; Wu, Teresa ; Weidman, David ; Lure, Fleming ; Li, Jing. / ADMultiImg : A novel missing modality transfer learning based CAD system for diagnosis of MCI due to AD using incomplete multi-modality imaging data. Medical Imaging 2018: Computer-Aided Diagnosis. Vol. 10575 SPIE, 2018.
@inproceedings{e11b2212616940f39365c6b4f09a66a0,
title = "ADMultiImg: A novel missing modality transfer learning based CAD system for diagnosis of MCI due to AD using incomplete multi-modality imaging data",
abstract = "Alzheimer's Disease (AD) is the most common cause of dementia and currently has no cure. Treatments targeting early stages of AD such as Mild Cognitive Impairment (MCI) may be most effective to deaccelerate AD, thus attracting increasing attention. However, MCI has substantial heterogeneity in that it can be caused by various underlying conditions, not only AD. To detect MCI due to AD, NIA-AA published updated consensus criteria in 2011, in which the use of multi-modality images was highlighted as one of the most promising methods. It is of great interest to develop a CAD system based on automatic, quantitative analysis of multi-modality images and machine learning algorithms to help physicians more adequately diagnose MCI due to AD. The challenge, however, is that multi-modality images are not universally available for many patients due to cost, access, safety, and lack of consent. We developed a novel Missing Modality Transfer Learning (MMTL) algorithm capable of utilizing whatever imaging modalities are available for an MCI patient to diagnose the patient's likelihood of MCI due to AD. Furthermore, we integrated MMTL with radiomics steps including image processing, feature extraction, and feature screening, and a post-processing for uncertainty quantification (UQ), and developed a CAD system called {"}ADMultiImg{"} to assist clinical diagnosis of MCI due to AD using multi-modality images together with patient demographic and genetic information. Tested on ADNI date, our system can generate a diagnosis with high accuracy even for patients with only partially available image modalities (AUC=0.94), and therefore may have broad clinical utility.",
keywords = "ADNI, Alzheimer's Disease, Mild Cognitive Impairment, Missing Modality Transfer Learning, NIA-AA criteria, Uncertainty Quantification",
author = "Xiaonan Liu and Kewei Chen and Teresa Wu and David Weidman and Fleming Lure and Jing Li",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2293698",
language = "English (US)",
volume = "10575",
booktitle = "Medical Imaging 2018",
publisher = "SPIE",

}

TY - GEN

T1 - ADMultiImg

T2 - A novel missing modality transfer learning based CAD system for diagnosis of MCI due to AD using incomplete multi-modality imaging data

AU - Liu, Xiaonan

AU - Chen, Kewei

AU - Wu, Teresa

AU - Weidman, David

AU - Lure, Fleming

AU - Li, Jing

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Alzheimer's Disease (AD) is the most common cause of dementia and currently has no cure. Treatments targeting early stages of AD such as Mild Cognitive Impairment (MCI) may be most effective to deaccelerate AD, thus attracting increasing attention. However, MCI has substantial heterogeneity in that it can be caused by various underlying conditions, not only AD. To detect MCI due to AD, NIA-AA published updated consensus criteria in 2011, in which the use of multi-modality images was highlighted as one of the most promising methods. It is of great interest to develop a CAD system based on automatic, quantitative analysis of multi-modality images and machine learning algorithms to help physicians more adequately diagnose MCI due to AD. The challenge, however, is that multi-modality images are not universally available for many patients due to cost, access, safety, and lack of consent. We developed a novel Missing Modality Transfer Learning (MMTL) algorithm capable of utilizing whatever imaging modalities are available for an MCI patient to diagnose the patient's likelihood of MCI due to AD. Furthermore, we integrated MMTL with radiomics steps including image processing, feature extraction, and feature screening, and a post-processing for uncertainty quantification (UQ), and developed a CAD system called "ADMultiImg" to assist clinical diagnosis of MCI due to AD using multi-modality images together with patient demographic and genetic information. Tested on ADNI date, our system can generate a diagnosis with high accuracy even for patients with only partially available image modalities (AUC=0.94), and therefore may have broad clinical utility.

AB - Alzheimer's Disease (AD) is the most common cause of dementia and currently has no cure. Treatments targeting early stages of AD such as Mild Cognitive Impairment (MCI) may be most effective to deaccelerate AD, thus attracting increasing attention. However, MCI has substantial heterogeneity in that it can be caused by various underlying conditions, not only AD. To detect MCI due to AD, NIA-AA published updated consensus criteria in 2011, in which the use of multi-modality images was highlighted as one of the most promising methods. It is of great interest to develop a CAD system based on automatic, quantitative analysis of multi-modality images and machine learning algorithms to help physicians more adequately diagnose MCI due to AD. The challenge, however, is that multi-modality images are not universally available for many patients due to cost, access, safety, and lack of consent. We developed a novel Missing Modality Transfer Learning (MMTL) algorithm capable of utilizing whatever imaging modalities are available for an MCI patient to diagnose the patient's likelihood of MCI due to AD. Furthermore, we integrated MMTL with radiomics steps including image processing, feature extraction, and feature screening, and a post-processing for uncertainty quantification (UQ), and developed a CAD system called "ADMultiImg" to assist clinical diagnosis of MCI due to AD using multi-modality images together with patient demographic and genetic information. Tested on ADNI date, our system can generate a diagnosis with high accuracy even for patients with only partially available image modalities (AUC=0.94), and therefore may have broad clinical utility.

KW - ADNI

KW - Alzheimer's Disease

KW - Mild Cognitive Impairment

KW - Missing Modality Transfer Learning

KW - NIA-AA criteria

KW - Uncertainty Quantification

UR - http://www.scopus.com/inward/record.url?scp=85046269705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046269705&partnerID=8YFLogxK

U2 - 10.1117/12.2293698

DO - 10.1117/12.2293698

M3 - Conference contribution

AN - SCOPUS:85046269705

VL - 10575

BT - Medical Imaging 2018

PB - SPIE

ER -