Lesion detection and characterization with context driven approximation in thoracic FDG PET-CT images of NSCLC studies

Yang Song, Weidong Cai, Heng Huang, Xiaogang Wang, Yun Zhou, Michael J. Fulham, David Dagan Feng

Research output: Contribution to journalArticle

Abstract

We present a lesion detection and characterization method for 18μrm F-fluorodeoxyglucose positron emission tomography - computed tomography (FDG PET-CT) images of the thorax in the evaluation of patients with primary nonsmall cell lung cancer (NSCLC) with regional nodal disease. Lesion detection can be difficult due to low contrast between lesions and normal anatomical structures. Lesion characterization is also challenging due to similar spatial characteristics between the lung tumors and abnormal lymph nodes. To tackle these problems, we propose a context driven approximation (CDA) method. There are two main components of our method. First, a sparse representation technique with region-level contexts was designed for lesion detection. To discriminate low-contrast data with sparse representation, we propose a reference consistency constraint and a spatial consistent constraint. Second, a multi-atlas technique with image-level contexts was designed to represent the spatial characteristics for lesion characterization. To accommodate inter-subject variation in a multi-atlas model, we propose an appearance constraint and a similarity constraint. The CDA method is effective with a simple feature set, and does not require parametric modeling of feature space separation. The experiments on a clinical FDG PET-CT dataset show promising performance improvement over the state-of-the-art.

Original languageEnglish (US)
Article number6634250
Pages (from-to)408-421
Number of pages14
JournalIEEE Transactions on Medical Imaging
Volume33
Issue number2
DOIs
StatePublished - Feb 2014

Fingerprint

Positron emission tomography
Non-Small Cell Lung Carcinoma
Tomography
Thorax
Atlases
Tumors
Cells
Lymph Nodes
Lung
Positron Emission Tomography Computed Tomography
Experiments
Neoplasms

Keywords

  • Approximation
  • characterization
  • detection
  • multi-atlas model
  • sparse representation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software

Cite this

Lesion detection and characterization with context driven approximation in thoracic FDG PET-CT images of NSCLC studies. / Song, Yang; Cai, Weidong; Huang, Heng; Wang, Xiaogang; Zhou, Yun; Fulham, Michael J.; Feng, David Dagan.

In: IEEE Transactions on Medical Imaging, Vol. 33, No. 2, 6634250, 02.2014, p. 408-421.

Research output: Contribution to journalArticle

Song, Yang ; Cai, Weidong ; Huang, Heng ; Wang, Xiaogang ; Zhou, Yun ; Fulham, Michael J. ; Feng, David Dagan. / Lesion detection and characterization with context driven approximation in thoracic FDG PET-CT images of NSCLC studies. In: IEEE Transactions on Medical Imaging. 2014 ; Vol. 33, No. 2. pp. 408-421.
@article{b6191a14f2bd4d269ab77dccf5c94f3d,
title = "Lesion detection and characterization with context driven approximation in thoracic FDG PET-CT images of NSCLC studies",
abstract = "We present a lesion detection and characterization method for 18μrm F-fluorodeoxyglucose positron emission tomography - computed tomography (FDG PET-CT) images of the thorax in the evaluation of patients with primary nonsmall cell lung cancer (NSCLC) with regional nodal disease. Lesion detection can be difficult due to low contrast between lesions and normal anatomical structures. Lesion characterization is also challenging due to similar spatial characteristics between the lung tumors and abnormal lymph nodes. To tackle these problems, we propose a context driven approximation (CDA) method. There are two main components of our method. First, a sparse representation technique with region-level contexts was designed for lesion detection. To discriminate low-contrast data with sparse representation, we propose a reference consistency constraint and a spatial consistent constraint. Second, a multi-atlas technique with image-level contexts was designed to represent the spatial characteristics for lesion characterization. To accommodate inter-subject variation in a multi-atlas model, we propose an appearance constraint and a similarity constraint. The CDA method is effective with a simple feature set, and does not require parametric modeling of feature space separation. The experiments on a clinical FDG PET-CT dataset show promising performance improvement over the state-of-the-art.",
keywords = "Approximation, characterization, detection, multi-atlas model, sparse representation",
author = "Yang Song and Weidong Cai and Heng Huang and Xiaogang Wang and Yun Zhou and Fulham, {Michael J.} and Feng, {David Dagan}",
year = "2014",
month = "2",
doi = "10.1109/TMI.2013.2285931",
language = "English (US)",
volume = "33",
pages = "408--421",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Lesion detection and characterization with context driven approximation in thoracic FDG PET-CT images of NSCLC studies

AU - Song, Yang

AU - Cai, Weidong

AU - Huang, Heng

AU - Wang, Xiaogang

AU - Zhou, Yun

AU - Fulham, Michael J.

AU - Feng, David Dagan

PY - 2014/2

Y1 - 2014/2

N2 - We present a lesion detection and characterization method for 18μrm F-fluorodeoxyglucose positron emission tomography - computed tomography (FDG PET-CT) images of the thorax in the evaluation of patients with primary nonsmall cell lung cancer (NSCLC) with regional nodal disease. Lesion detection can be difficult due to low contrast between lesions and normal anatomical structures. Lesion characterization is also challenging due to similar spatial characteristics between the lung tumors and abnormal lymph nodes. To tackle these problems, we propose a context driven approximation (CDA) method. There are two main components of our method. First, a sparse representation technique with region-level contexts was designed for lesion detection. To discriminate low-contrast data with sparse representation, we propose a reference consistency constraint and a spatial consistent constraint. Second, a multi-atlas technique with image-level contexts was designed to represent the spatial characteristics for lesion characterization. To accommodate inter-subject variation in a multi-atlas model, we propose an appearance constraint and a similarity constraint. The CDA method is effective with a simple feature set, and does not require parametric modeling of feature space separation. The experiments on a clinical FDG PET-CT dataset show promising performance improvement over the state-of-the-art.

AB - We present a lesion detection and characterization method for 18μrm F-fluorodeoxyglucose positron emission tomography - computed tomography (FDG PET-CT) images of the thorax in the evaluation of patients with primary nonsmall cell lung cancer (NSCLC) with regional nodal disease. Lesion detection can be difficult due to low contrast between lesions and normal anatomical structures. Lesion characterization is also challenging due to similar spatial characteristics between the lung tumors and abnormal lymph nodes. To tackle these problems, we propose a context driven approximation (CDA) method. There are two main components of our method. First, a sparse representation technique with region-level contexts was designed for lesion detection. To discriminate low-contrast data with sparse representation, we propose a reference consistency constraint and a spatial consistent constraint. Second, a multi-atlas technique with image-level contexts was designed to represent the spatial characteristics for lesion characterization. To accommodate inter-subject variation in a multi-atlas model, we propose an appearance constraint and a similarity constraint. The CDA method is effective with a simple feature set, and does not require parametric modeling of feature space separation. The experiments on a clinical FDG PET-CT dataset show promising performance improvement over the state-of-the-art.

KW - Approximation

KW - characterization

KW - detection

KW - multi-atlas model

KW - sparse representation

UR - http://www.scopus.com/inward/record.url?scp=84894075255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894075255&partnerID=8YFLogxK

U2 - 10.1109/TMI.2013.2285931

DO - 10.1109/TMI.2013.2285931

M3 - Article

C2 - 24235248

AN - SCOPUS:84894075255

VL - 33

SP - 408

EP - 421

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 2

M1 - 6634250

ER -