Sparse sampling and unsupervised learning of lung texture patterns in pulmonary emphysema: MESA COPD study

Häme, Yrjö; Angelini, Elsa D.; Parikh, Megha; Smith, Benjamin M.; Hoffman, Eric A.; Barr, R. Graham; Laine, Andrew F.

doi:10.1109/isbi.2015.7163828

Cited by 7 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate here the prediction ability using a constrained multivariate regression [6], and compare our method with two previous algorithms [5,6] (implemented with our training data, and setting the numbers of LTPs to 12 for comparison with a constant number of CT-based predictors). Intraclass correlation (ICC) values between predicted standard emphysema subtype scores and ground truth on the full dataset (N = 317), computed in a 4-fold cross validation manner, are reported in Table 1.…”

Section: Resultsmentioning

confidence: 99%

“…Most existing approaches for learning emphysema subtypes on CT are limited to texture-based features, which are sub-optimal due to the lack of spatial information. Previous studies [5,6] proposed to generate unsupervised lung texture patterns (LTPs) based on texture appearance, and to group them based on their spatial co-occurrence. However, such approaches only account for relative spatial occurrence at the scale of local regions of interest (ROIs).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Discovery of Spatially-Informed Lung Texture Patterns for Pulmonary Emphysema: The MESA COPD Study

Yang

Angelini

Balte

et al. 2017

Medical Image Computing and Computer Assisted Intervention − MICCAI 2017

Self Cite

View full text Add to dashboard Cite

Unsupervised discovery of pulmonary emphysema subtypes offers the potential for new definitions of emphysema on lung computed tomography (CT) that go beyond the standard subtypes identified on autopsy. Emphysema subtypes can be defined on CT as a variety of textures with certain spatial prevalence. However, most existing approaches for learning emphysema subtypes on CT are limited to texture features, which are sub-optimal due to the lack of spatial information. In this work, we exploit a standardized spatial mapping of the lung and propose a novel framework for combining spatial and texture information to discover spatially-informed lung texture patterns (sLTPs). Our spatial mapping is demonstrated to be a powerful tool to study emphysema spatial locations over different populations. The discovered sLTPs are shown to have high reproducibility, ability to encode standard emphysema subtypes, and significant associations with clinical characteristics.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Unsupervised Discovery of Spatially-Informed Lung Texture Patterns for Pulmonary Emphysema: The MESA COPD Study

Yang

Angelini

Balte

et al. 2017

Medical Image Computing and Computer Assisted Intervention − MICCAI 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…By contrast, our work models only imaging data, but we explicitly detect and characterize homogeneous sub-populations defined by similar groups of disease subtypes, which opens directions for future analysis. An additional work similar to ours is found in [8], which discovers disease subtypes in an unsupervised manner. However, it was conducted on a smaller data set and does not model patient clusters.…”

Section: Introductionmentioning

confidence: 86%

Unsupervised Discovery of Emphysema Subtypes in a Large Clinical Cohort

Binder¹,

Batmanghelich

Estépar

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Emphysema is one of the hallmarks of Chronic Obstructive Pulmonary Disorder (COPD), a devastating lung disease often caused by smoking. Emphysema appears on Computed Tomography (CT) scans as a variety of textures that correlate with disease subtypes. It has been shown that the disease subtypes and textures are linked to physiological indicators and prognosis, although neither is well characterized clinically. Most previous computational approaches to modeling emphysema imaging data have focused on supervised classification of lung textures in patches of CT scans. In this work, we describe a generative model that jointly captures heterogeneity of disease subtypes and of the patient population. We also describe a corresponding inference algorithm that simultaneously discovers disease subtypes and population structure in an unsupervised manner. This approach enables us to create image-based descriptors of emphysema beyond those that can be identified through manual labeling of currently defined phenotypes. By applying the resulting algorithm to a large data set, we identify groups of patients and disease subtypes that correlate with distinct physiological indicators.

show abstract

“…In two previous studies [17], [18], we proposed to use local textural patterns to generate unsupervised lung texture patterns (LTPs) followed by LTP-grouping based on their spatial co-occurrence in local neighborhoods. Such separate use of intensity and spatial information cannot guarantee spatial and textural homogeneity of the final LTPs.…”

Section: Introductionmentioning

confidence: 99%

Novel Subtypes of Pulmonary Emphysema Based on Spatially-Informed Lung Texture Learning: The Multi-Ethnic Study of Atherosclerosis (MESA) COPD Study

Yang

Angelini

Balte

et al. 2021

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Pulmonary emphysema overlaps considerably with chronic obstructive pulmonary disease (COPD), and is traditionally subcategorized into three subtypes previously identified on autopsy. Unsupervised learning of emphysema subtypes on computed tomography (CT) opens the way to new definitions of emphysema subtypes and eliminates the need of thorough manual labeling. However, CT-based emphysema subtypes have been limited to texture-based patterns without considering spatial location. In this work, we introduce a standardized spatial mapping of the lung for quantitative study of lung texture location and propose a novel framework for combining spatial and texture information to discover spatially-informed lung texture patterns (sLTPs) that represent novel emphysema subtype candidates. Exploiting two cohorts of full-lung CT scans from the MESA COPD (n=317) and EMCAP (n=22) studies, we first show that our spatial mapping enables population-wide study of emphysema spatial location. We then evaluate the characteristics of the sLTPs discovered on MESA COPD, and show that they are reproducible, able to encode standard emphysema subtypes, and associated with physiological symptoms.

show abstract

Sparse sampling and unsupervised learning of lung texture patterns in pulmonary emphysema: MESA COPD study

Cited by 7 publications

References 19 publications

Unsupervised Discovery of Spatially-Informed Lung Texture Patterns for Pulmonary Emphysema: The MESA COPD Study

Unsupervised Discovery of Spatially-Informed Lung Texture Patterns for Pulmonary Emphysema: The MESA COPD Study

Unsupervised Discovery of Emphysema Subtypes in a Large Clinical Cohort

Novel Subtypes of Pulmonary Emphysema Based on Spatially-Informed Lung Texture Learning: The Multi-Ethnic Study of Atherosclerosis (MESA) COPD Study

Contact Info

Product

Resources

About