Segmenting lung fields in serial chest radiographs using both population and patient-specific shape statistics

Authors:
Yonghong Shi;Feihu Qi;Zhong Xue;Kyoko Ito;Hidenori Matsuo;Dinggang Shen
Affiliations:
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China;Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China;Section of Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA;Hidaka Hospital, Takasaki Gunma-Prefecture, Japan;Hidaka Hospital, Takasaki Gunma-Prefecture, Japan;Section of Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA
Venue:
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Year:
2006

Citing 2
Cited 2

Active shape models—their training and application

Computer Vision and Image Understanding
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2

Learning Longitudinal Deformations for Adaptive Segmentation of Lung Fields from Serial Chest Radiographs

MIAR '08 Proceedings of the 4th international workshop on Medical Imaging and Augmented Reality
A region based active contour method for x-ray lung segmentation using prior shape and low level features

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new deformable model using both population-based and patient-specific shape statistics to segment lung fields from serial chest radiographs. First, a modified scale-invariant feature transform (SIFT) local descriptor is used to characterize the image features in the vicinity of each pixel, so that the deformable model deforms in a way that seeks for the region with similar SIFT local descriptors. Second, the deformable model is constrained by both population-based and patient-specified shape statistics. Initially, population-based shape statistics takes most of the rules when the number of serial images is small; gradually, patient-specific shape statistics takes more rules after a sufficient number of segmentation results on the same patient have been obtained. The proposed deformable model can adapt to the shape variability of different patients, and obtain more robust and accurate segmentation results.