Journal
IET IMAGE PROCESSING
Volume 14, Issue 16, Pages 4340-4348Publisher
WILEY
DOI: 10.1049/iet-ipr.2019.1171
Keywords
neural nets; image denoising; image classification; image segmentation; diseases; medical image processing; computerised tomography; lung; learning (artificial intelligence); novel superpixel-based algorithm; lung images; convolutional neural network; random forest; lung diseases; juxta-pleural nodules; individual anatomical varieties; superpixel approach; segment lungs; automatic fashion; accurate fashion; authors; image preprocessing; lung segmenting; segmentation refining; lung CT image; fractional-order grey similarity approach; CNN-RF model; correcting lung contours; accurate lung segmentation results
Categories
Funding
- National Natural Science Foundation of China [62007028, 41631175, 61702068]
- Key Project of Ministry of Education [DCA170302]
- Social Science Foundation of Jiangsu Province of China [15TQB005]
- Priority Academic Program Development of Jiangsu Higher Education Institutions [1643320H111]
- Post graduate Research & Practice Innovation Program of Jiangsu Province [KYCX19_0733]
Ask authors/readers for more resources
Accurately segmenting lungs from CT images is a fundamental step for quantitative analysis of lung diseases. However, it is still a challenging task because of some interferential factors, such as juxta-pleural nodules, pulmonary inflammation, as well as individual anatomical varieties. In this study, with the combination of a superpixel approach and a hybrid model composed of convolutional neural network and random forest (CNN-RF), the authors propose a novel algorithm to segment lungs from CT images in an automatic and accurate fashion. The authors' lung segmentation covers three main stages: image preprocessing, lung segmenting and segmentation refining. A lung CT image denoised with a fractional-order grey similarity approach is first segmented to a set of superpixels, and the CNN-RF model is then employed to classify the superpixels and identify lungs from the CT image. The segmentation result is further refined by separating the left and right lungs, eliminating trachea, and correcting lung contours. Experiments show that their algorithm can generate more accurate lung segmentation results with 94.98% Jaccard's index and 97.99% Dice similarity coefficient, compared with ground truths, and it achieved better results compared with several feature-based machine learning techniques and current methods on lung segmentation.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available