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 language | English (US) |
---|---|
Article number | 6634250 |
Pages (from-to) | 408-421 |
Number of pages | 14 |
Journal | IEEE Transactions on Medical Imaging |
Volume | 33 |
Issue number | 2 |
DOIs | |
State | Published - Feb 2014 |
Fingerprint
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 journal › Article
}
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 -