An improved random forests approach for interactive lobar segmentation on emphysema detection
- PDF / 1,540,657 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 0 Downloads / 189 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL PAPER
An improved random forests approach for interactive lobar segmentation on emphysema detection Qiang Li1 • Lei Chen2 • Xiangju Li3 • Shuyue Xia4 • Yan Kang1,5 Received: 11 December 2018 / Accepted: 19 April 2019 Ó Springer Nature Switzerland AG 2019
Abstract Emphysema is one of the most widespread diseases in chronic diseases. Early diagnosis is crucial in slowing down the decline in the lung function of patients. Nowadays, it mainly relies on the pulmonary function test, which suffers from two drawbacks: the pulmonary function test cannot reflect the severity of patients with heterogeneous emphysema accurately and diagnose dyspnea patients. Hence, we propose an approach to analyze emphysema based on computed tomography (CT) images, which can detect the location of emphysema on each lung lobe. For the cases that cannot be automatically segmented, a random forests-based multi-task learning method with granular computing perspective is designed for interactive lobar segmentation. The effectiveness of the proposed emphysema detection method is demonstrated with the CT dataset from 93 patients with chronic obstructive pulmonary diseases. The accuracy of the presented lobar segmentation technique is proved on the CT images that cannot segment lobes. The experimental results show that the proposed interactive lobar segmentation method on locate emphysema about lobes could detect early symptoms of emphysema and reduce 17:2% of missing diagnosis. Keywords Random forests Lobar segmentation Chronic obstructive pulmonary disease Pulmonary function test Emphysema Granular computing
1 Introduction & Yan Kang [email protected] Qiang Li [email protected] Lei Chen [email protected] Xiangju Li [email protected] Shuyue Xia [email protected] 1
Sino-dutch Biomedical and Information Engineering School, Northeastern University, Shenyang, Liaoning, China
2
Neusoft Medical Systems Ltd., Shenyang, Liaoning, China
3
School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China
4
The Central Hospital Affiliated to Shenyang Medical College, Shenyang, Liaoning, China
5
Neusoft Intelligent Medical Research Institute, Shenyang, Liaoning, China
Emphysema, as one of the most common chronic obstructive pulmonary diseases (COPD), is one of the main causes of death in China (Rabe et al. 2007; Vogelmeier et al. 2017; Vestbo et al. 2013; Buist et al. 2007; Zhou et al. 2016). Wang et al. selected 57,779 individuals from China Pulmonary Health study between June, 2012, and May, 2015, of whom 50,991 (21,446 men and 29,545 women) have reliable post-bronchodilator results and are included in the final analysis to diagnose COPD. The overall prevalence of spirometry-defined COPD is 8:6%, accounting for 99.9 million people with COPD in China (Wang et al. 2018). Early emphysematous diagnosis that relies on the pulmonary function test (Culver et al. 2017) is crucial to slowing down the decline in the lung function of patients, and the loc
Data Loading...
