Computed Tomography Features of Lung Structure Have Utility for Differentiating Malignant and Benign Pulmonary Nodules

Document Type

Article

Publication Date

1-12-2022

Publication Title

Chronic Obstr Pulm Dis

Abstract

Background: Chronic obstructive pulmonary disease (COPD) is a known co-morbidity for lung cancer independent of smoking history. Quantitative computed tomography (qCT) imaging features related to COPD have shown promise in the assessment of lung cancer risk. We hypothesize that qCT features from the lung, lobe, and airway tree related to the location of the pulmonary nodule can be used to provide informative malignancy risk assessment.

Methods: One-hundred and eighty-three qCT features were extracted from 278 subjects with a solitary pulmonary nodule of known diagnosis (71 malignant, 207 benign). These included histogram and airway characteristics of the lungs, lobe, and segmental paths. Performances of the least absolute shrinkage and selection operator (LASSO) regression analysis and an ensemble of neural networks (ENN) were compared for feature set selection and classification on a testing cohort of 49 additional subjects (15 malignant, 34 benign).

Results: TheThe LASSO and ENN methods produced different features sets for classification with LASSO selecting fewer (7) qCT features than the ENN (17). The LASSO model with the highest performing training AUC (0.80) incorporated automatically extracted features and reader-measured nodule diameter with a testing AUC of 0.62. The ENN model with the highest performing AUC (0.77) also incorporated qCT and reader diameter but maintained higher testing performance (AUC = 0.79).

Conclusions: Automatically extracted qCT imaging features of the lung can be informative of the differentiation between subjects with malignant pulmonary nodules and those with benign pulmonary nodules, without requiring nodule segmentation and analysis.

PubMed ID

35021316

ePublication

ePub ahead of print

Find It @ Sladen

Share

COinS