Radiomics approach for survival prediction in chronic obstructive pulmonary disease

被引:26
作者
Cho, Young Hoon [1 ,2 ,3 ]
Seo, Joon Beom [2 ,3 ]
Lee, Sang Min [2 ,3 ]
Kim, Namkug [2 ,3 ]
Yun, Jihye [2 ,3 ]
Hwang, Jeong Eun [2 ,3 ]
Lee, Jae Seung [4 ]
Oh, Yeon-Mok [4 ]
Do Lee, Sang [4 ]
Loh, Li-Cher [5 ]
Ong, Choo-Khoom [5 ]
机构
[1] Korea Univ, Coll Med, Guro Hosp, Dept Radiol, 148 Gurodong Ro, Seoul 08308, South Korea
[2] Univ Ulsan, Coll Med, Asan Med Ctr, Dept Radiol, Seoul 138736, South Korea
[3] Univ Ulsan, Coll Med, Asan Med Ctr, Res Inst Radiol, Seoul 138736, South Korea
[4] Univ Ulsan, Coll Med, Asan Med Ctr, Div Pulm & Crit Care Med, 388-1 Pungnap Dong, Seoul 138736, South Korea
[5] RCSI & UCD Malaysia Campus, Dept Med, 4 Jalan Sepoy Lines, George Town 10450, Penang, Malaysia
关键词
Pulmonary disease; chronic obstructive; Computer-assisted radiographic image interpretation; Tomography; X-ray computed; Survival analysis; Thorax; HALF-MAXIMUM METHOD; QUANTITATIVE ASSESSMENT; COMPUTED-TOMOGRAPHY; NONRIGID REGISTRATION; CHEST CT; EMPHYSEMA; COPD; MANAGEMENT; QUANTIFICATION; BIOMARKER;
D O I
10.1007/s00330-021-07747-7
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
100231 [临床病理学]; 100902 [航空航天医学];
摘要
Objectives To apply radiomics analysis for overall survival prediction in chronic obstructive pulmonary disease (COPD), and evaluate the performance of the radiomics signature (RS). Methods This study included 344 patients from the Korean Obstructive Lung Disease (KOLD) cohort. External validation was performed on a cohort of 112 patients. In total, 525 chest CT-based radiomics features were semi-automatically extracted. The five most useful features for survival prediction were selected by least absolute shrinkage and selection operation (LASSO) Cox regression analysis and used to generate a RS. The ability of the RS for classifying COPD patients into high or low mortality risk groups was evaluated with the Kaplan-Meier survival analysis and Cox proportional hazards regression analysis. Results The five features remaining after the LASSO analysis were %LAA(-950), AWT_Pi10_6(th), AWT_Pi10_heterogeneity, %WA_heterogeneity, and VA(18mm). The RS demonstrated a C-index of 0.774 in the discovery group and 0.805 in the validation group. Patients with a RS greater than 1.053 were classified into the high-risk group and demonstrated worse overall survival than those in the low-risk group in both the discovery (log-rank test, < 0.001; hazard ratio [HR], 5.265) and validation groups (log-rank test, < 0.001; HR, 5.223). For both groups, RS was significantly associated with overall survival after adjustments for patient age and body mass index. Conclusions A radiomics approach for survival prediction and risk stratification in COPD patients is feasible, and the constructed radiomics model demonstrated acceptable performance. The RS derived from chest CT data of COPD patients was able to effectively identify those at increased risk of mortality.
引用
收藏
页码:7316 / 7324
页数:9
相关论文
共 39 条
[1]
The path to personalised medicine in COPD [J].
Agusti, Alvar .
THORAX, 2014, 69 (09) :857-864
[2]
Thoracic cavity segmentation algorithm using multiorgan extraction and surface fitting in volumetric CT [J].
Bae, JangPyo ;
Kim, Namkug ;
Lee, Sang Min ;
Seo, Joon Beom ;
Kim, Hee Chan .
MEDICAL PHYSICS, 2014, 41 (04)
[3]
Chronic obstructive pulmonary disease [J].
Barnes, Peter J. ;
Burney, Peter G. J. ;
Silverman, Edwin K. ;
Celli, Bartolome R. ;
Vestbo, Jorgen ;
Wedzicha, Jadwiga A. ;
Wouters, Emiel F. M. .
NATURE REVIEWS DISEASE PRIMERS, 2015, 1
[4]
Lung Topology Characteristics in patients with Chronic Obstructive Pulmonary Disease [J].
Belchi, Francisco ;
Pirashvili, Mariam ;
Conway, Joy ;
Bennett, Michael ;
Djukanovic, Ratko ;
Brodzki, Jacek .
SCIENTIFIC REPORTS, 2018, 8
[5]
X-tile: A new bio-informatics tool for biomarker assessment and outcome-based cut-point optimization [J].
Camp, RL ;
Dolled-Filhart, M ;
Rimm, DL .
CLINICAL CANCER RESEARCH, 2004, 10 (21) :7252-7259
[6]
Quantitative assessment of pulmonary vascular alterations in chronic obstructive lung disease: Associations with pulmonary function test and survival in the KOLD cohort [J].
Cho, Young Hoon ;
Lee, Sang Min ;
Seo, Joon Beom ;
Kim, Namkug ;
Bae, Jang Pyo ;
Lee, Jae Seung ;
Oh, Yeon-Mok ;
Do-Lee, Sang .
EUROPEAN JOURNAL OF RADIOLOGY, 2018, 108 :276-282
[7]
Cho Young Hoon, 2018, [Journal of the Korean Society of Radiology (JKSR), 대한영상의학회지], V78, P1, DOI 10.3348/jksr.2018.78.1.1
[8]
Comparison of a New Integral-Based Half-Band Method for CT Measurement of Peripheral Airways in COPD With a Conventional Full-Width Half-Maximum Method Using Both Phantom and Clinical CT Images [J].
Cho, Young Hoon ;
Seo, Joon Beom ;
Kim, Namkug ;
Lee, Hyun Joo ;
Hwang, Hye Jeon ;
Kim, Eun Young ;
Oh, Sang Young .
JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 2015, 39 (03) :428-436
[9]
Using Pulmonary Imaging to Move Chronic Obstructive Pulmonary Disease beyond FEV1 [J].
Coxson, Harvey O. ;
Leipsic, Jonathon ;
Parraga, Grace ;
Sin, Don D. .
AMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE, 2014, 190 (02) :135-144
[10]
Computed Tomographic Measures of Pulmonary Vascular Morphology in Smokers and Their Clinical Implications [J].
Estepar, Raul San Jose ;
Kinney, Gregory L. ;
Black-Shinn, Jennifer L. ;
Bowler, Russell P. ;
Kindlmann, Gordon L. ;
Ross, James C. ;
Kikinis, Ron ;
Han, MeiLan K. ;
Come, Carolyn E. ;
Diaz, Alejandro A. ;
Cho, Michael H. ;
Hersh, Craig P. ;
Schroeder, Joyce D. ;
Reilly, John J. ;
Lynch, David A. ;
Crapo, James D. ;
Wells, J. Michael ;
Dransfield, Mark T. ;
Hokanson, John E. ;
Washko, George R. .
AMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE, 2013, 188 (02) :231-239