Thoracic Abnormality Detection with Data Adaptive Structure Estimation
- 1 January 2012
- book chapter
- Published by Springer Nature in Lecture Notes in Computer Science
- Vol. 15, 74-81
Abstract
Automatic detection of lung tumors and abnormal lymph nodes are useful in assisting lung cancer staging. This paper presents a novel detection method, by first identifying all abnormalities, then differentiating between lung tumors and abnormal lymph nodes based on their degree of overlap with the lung field and mediastinum. Regression-based appearance model and graph-based structure labeling are designed to estimate the actual lung field and mediastinum from the pathology-affected thoracic images adaptively. The proposed method is simple, effective and generalizable, and can be potentially applicable to other medical imaging domains as well. Promising results are demonstrated based on our evaluations on clinical PET-CT data sets from lung cancer patients.Keywords
This publication has 12 references indexed in Scilit:
- Mediastinal atlas creation from 3-D chest computed tomography images: Application to automated detection and station mapping of lymph nodesMedical Image Analysis, 2012
- Human brain labeling using image similarities2011
- Automatic tumour volume delineation in respiratory‐gated PET imagesJournal of Medical Imaging and Radiation Oncology, 2011
- Mixture of Segmenters with Discriminative Spatial Regularization and Sparse Weight Selection2011
- Multi-stage Learning for Robust Lung Segmentation in Challenging CT Volumes2011
- Discriminative Pathological Context Detection in Thoracic Images Based on Multi-level Inference2011
- Stratified learning of local anatomical context for lung nodules in CT images2010
- Lymph node detection in 3-D chest CT using a spatial prior probability2010
- A framework for automated tumor detection in thoracic FDG pet images using texture-based features2009
- Toward automated segmentation of the pathological lung in CTIEEE Transactions on Medical Imaging, 2005