Chronic Obstructive Pulmonary Disease affects up to 24 million people in the United States and is projected to be the 3rd leading cause of death worldwide by 2020. COPD has been traditionally dichotomized into the clinical phenotypes of emphysema and chronic bronchitis. Although spirometry is critical for diagnosis of COPD, FEV1 may be of limited value in a classification scheme designed to illuminate differences in disease mechanism among individuals. Computed tomographic (CT) imaging of the lung is a tool that may fulfill the need of new biomarkers to: facilitate the creation and testing of novel therapies, act as surrogate endpoints for clinical trials and provide researchers with the ability to reduce the heterogeneity of a cohort of subjects with COPD into more homogeneous subgroups to assist in monitoring study endpoints Airway Inspector is a open source software tool based on Slicer 2.x developed at Brigham and Women's Hospital for the analysis of chest CT scans for the analysis of emphysema and airway disease. The tool was conceived to analysis low resolution CT scans bringing the gap between retrospective data and new emerging CT technologies. The success of the tool in the COPD clinical community is supported by the array of peer- review publications that have used the tool to define metrics of disease that enable hypothesis driven research. Beside the existence of alternative commercial applications, Airway Inspector is the only freely available maintained platform for COPD research. In spite of its success, Airway Inspector is limited to a discontinued version of Slicer. The broad objective of this proposal is to support the refactoring and development of Airway Inspector as a platform for image-based COPD research. This goal will be achieved by the creation of the Chest Imaging Biomarker Platform (CIBP) library that integrates novel algorithm solutions to lung image analysis that have been developed in our laboratory. Those solutions include: robust lung extraction, parenchymal tissue classification based on local density, airway, fissure and pulmonary vascular extraction based on scale-space particles and airway labeling based on Hidden Markov Models. That software platform will be used to create workflows that will be integrated in Slicer 4 for their deployment in the clinical community. Slicer 4 is a NIH supported open software general purpose imaging software platform that is specifically designed to integrate solutions like Airway Inspector. The workflows will provide an end-to-end solution for the clinical to obtain phenotypes to characterize emphysema, airway disease and pulmonary vascular remodeling.
Chronic Obstructive Pulmonary Disease (COPD) affects up to 24 million people in the United States and is projected to be the 3rd leading cause of death worldwide by 202 and, unlike many other diseases, only rudimentary standards are available for describing the severity and the heterogeneity of COPD. Biomarkers computed from CT images of the chest are critical to define new clinical associations and endpoints as well as to explore genetic associations hence proving a benefit to the public health. This proposal builds on updating, enhancing and disseminating Airway Inspector, an open source and freely available software package for chest CT image-based biomarker extraction.
| Ash, Samuel Y; Rahaghi, Farbod N; Come, Carolyn E et al. (2018) Pruning of the Pulmonary Vasculature in Asthma. The Severe Asthma Research Program (SARP) Cohort. Am J Respir Crit Care Med 198:39-50 |
| Diaz, Alejandro A; Martinez, Carlos H; Harmouche, Rola et al. (2018) Pectoralis muscle area and mortality in smokers without airflow obstruction. Respir Res 19:62 |
| González, Germán; Ash, Samuel Y; Vegas-Sánchez-Ferrero, Gonzalo et al. (2018) Disease Staging and Prognosis in Smokers Using Deep Learning in Chest Computed Tomography. Am J Respir Crit Care Med 197:193-203 |
| Onieva, Jorge Onieva; Serrano, Germán González; Young, Thomas P et al. (2018) Multiorgan structures detection using deep convolutional neural networks. Proc SPIE Int Soc Opt Eng 10574: |
| González, Germán; Washko, George R; Estépar, Raúl San José (2018) Deep learning for biomarker regression: application to osteoporosis and emphysema on chest CT scans. Proc SPIE Int Soc Opt Eng 10574: |
| Cano-Espinosa, Carlos; González, Germán; Washko, George R et al. (2018) Automated Agatston Score Computation in non-ECG Gated CT Scans Using Deep Learning. Proc SPIE Int Soc Opt Eng 10574: |
| Vegas-Sánchez-Ferrero, Gonzalo; Ledesma-Carbayo, Maria J; Washko, George R et al. (2018) Autocalibration method for non-stationary CT bias correction. Med Image Anal 44:115-125 |
| Ross, James C; Castaldi, Peter J; Cho, Michael H et al. (2018) Longitudinal Modeling of Lung Function Trajectories in Smokers with and without Chronic Obstructive Pulmonary Disease. Am J Respir Crit Care Med 198:1033-1042 |
| Campo, Mónica Iturrioz; Pascau, Javier; José Estépar, Raúl San (2018) EMPHYSEMA QUANTIFICATION ON SIMULATED X-RAYS THROUGH DEEP LEARNING TECHNIQUES. Proc IEEE Int Symp Biomed Imaging 2018:273-276 |
| Ash, Samuel Y; Harmouche, Rola; Putman, Rachel K et al. (2018) Association between acute respiratory disease events and the MUC5B promoter polymorphism in smokers. Thorax 73:1071-1074 |
Showing the most recent 10 out of 60 publications
