Landmark-based deep multi-instance learning for brain disease diagnosis

Mingxia Liu, Jun Zhang, Ehsan Adeli, Dinggang Shen

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

In conventional Magnetic Resonance (MR) image based methods, two stages are often involved to capture brain structural information for disease diagnosis, i.e., 1) manually partitioning each MR image into a number of regions-of-interest (ROIs), and 2) extracting pre-defined features from each ROI for diagnosis with a certain classifier. However, these pre-defined features often limit the performance of the diagnosis, due to challenges in 1) defining the ROIs and 2) extracting effective disease-related features. In this paper, we propose a landmark-based deep multi-instance learning (LDMIL) framework for brain disease diagnosis. Specifically, we first adopt a data-driven learning approach to discover disease-related anatomical landmarks in the brain MR images, along with their nearby image patches. Then, our LDMIL framework learns an end-to-end MR image classifier for capturing both the local structural information conveyed by image patches located by landmarks and the global structural information derived from all detected landmarks. We have evaluated our proposed framework on 1526 subjects from three public datasets (i.e., ADNI-1, ADNI-2, and MIRIAD), and the experimental results show that our framework can achieve superior performance over state-of-the-art approaches.

Original languageEnglish
Pages (from-to)157-168
Number of pages12
JournalMedical Image Analysis
Volume43
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Brain Diseases
Magnetic resonance
Brain
Magnetic Resonance Spectroscopy
Learning
Classifiers

Keywords

  • Brain disease
  • Convolutional neural network
  • Landmark
  • Multi-instance learning

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Landmark-based deep multi-instance learning for brain disease diagnosis. / Liu, Mingxia; Zhang, Jun; Adeli, Ehsan; Shen, Dinggang.

In: Medical Image Analysis, Vol. 43, 01.01.2018, p. 157-168.

Research output: Contribution to journalArticle

Liu, Mingxia ; Zhang, Jun ; Adeli, Ehsan ; Shen, Dinggang. / Landmark-based deep multi-instance learning for brain disease diagnosis. In: Medical Image Analysis. 2018 ; Vol. 43. pp. 157-168.
@article{86c1ab6f8434496fa8bc314cab9788e2,
title = "Landmark-based deep multi-instance learning for brain disease diagnosis",
abstract = "In conventional Magnetic Resonance (MR) image based methods, two stages are often involved to capture brain structural information for disease diagnosis, i.e., 1) manually partitioning each MR image into a number of regions-of-interest (ROIs), and 2) extracting pre-defined features from each ROI for diagnosis with a certain classifier. However, these pre-defined features often limit the performance of the diagnosis, due to challenges in 1) defining the ROIs and 2) extracting effective disease-related features. In this paper, we propose a landmark-based deep multi-instance learning (LDMIL) framework for brain disease diagnosis. Specifically, we first adopt a data-driven learning approach to discover disease-related anatomical landmarks in the brain MR images, along with their nearby image patches. Then, our LDMIL framework learns an end-to-end MR image classifier for capturing both the local structural information conveyed by image patches located by landmarks and the global structural information derived from all detected landmarks. We have evaluated our proposed framework on 1526 subjects from three public datasets (i.e., ADNI-1, ADNI-2, and MIRIAD), and the experimental results show that our framework can achieve superior performance over state-of-the-art approaches.",
keywords = "Brain disease, Convolutional neural network, Landmark, Multi-instance learning",
author = "Mingxia Liu and Jun Zhang and Ehsan Adeli and Dinggang Shen",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.media.2017.10.005",
language = "English",
volume = "43",
pages = "157--168",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

TY - JOUR

T1 - Landmark-based deep multi-instance learning for brain disease diagnosis

AU - Liu, Mingxia

AU - Zhang, Jun

AU - Adeli, Ehsan

AU - Shen, Dinggang

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In conventional Magnetic Resonance (MR) image based methods, two stages are often involved to capture brain structural information for disease diagnosis, i.e., 1) manually partitioning each MR image into a number of regions-of-interest (ROIs), and 2) extracting pre-defined features from each ROI for diagnosis with a certain classifier. However, these pre-defined features often limit the performance of the diagnosis, due to challenges in 1) defining the ROIs and 2) extracting effective disease-related features. In this paper, we propose a landmark-based deep multi-instance learning (LDMIL) framework for brain disease diagnosis. Specifically, we first adopt a data-driven learning approach to discover disease-related anatomical landmarks in the brain MR images, along with their nearby image patches. Then, our LDMIL framework learns an end-to-end MR image classifier for capturing both the local structural information conveyed by image patches located by landmarks and the global structural information derived from all detected landmarks. We have evaluated our proposed framework on 1526 subjects from three public datasets (i.e., ADNI-1, ADNI-2, and MIRIAD), and the experimental results show that our framework can achieve superior performance over state-of-the-art approaches.

AB - In conventional Magnetic Resonance (MR) image based methods, two stages are often involved to capture brain structural information for disease diagnosis, i.e., 1) manually partitioning each MR image into a number of regions-of-interest (ROIs), and 2) extracting pre-defined features from each ROI for diagnosis with a certain classifier. However, these pre-defined features often limit the performance of the diagnosis, due to challenges in 1) defining the ROIs and 2) extracting effective disease-related features. In this paper, we propose a landmark-based deep multi-instance learning (LDMIL) framework for brain disease diagnosis. Specifically, we first adopt a data-driven learning approach to discover disease-related anatomical landmarks in the brain MR images, along with their nearby image patches. Then, our LDMIL framework learns an end-to-end MR image classifier for capturing both the local structural information conveyed by image patches located by landmarks and the global structural information derived from all detected landmarks. We have evaluated our proposed framework on 1526 subjects from three public datasets (i.e., ADNI-1, ADNI-2, and MIRIAD), and the experimental results show that our framework can achieve superior performance over state-of-the-art approaches.

KW - Brain disease

KW - Convolutional neural network

KW - Landmark

KW - Multi-instance learning

UR - http://www.scopus.com/inward/record.url?scp=85032831440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032831440&partnerID=8YFLogxK

U2 - 10.1016/j.media.2017.10.005

DO - 10.1016/j.media.2017.10.005

M3 - Article

C2 - 29107865

AN - SCOPUS:85032831440

VL - 43

SP - 157

EP - 168

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -