Skip to main content

Influence of background lung characteristics on nodule detection with computed tomography.

Publication ,  Journal Article
Li, B; Smith, TB; Choudhury, KR; Harrawood, B; Ebner, L; Roos, JE; Rubin, GD
Published in: J Med Imaging (Bellingham)
March 2020

We sought to characterize local lung complexity in chest computed tomography (CT) and to characterize its impact on the detectability of pulmonary nodules. Forty volumetric chest CT scans were created by embedding between three and five simulated 5-mm lung nodules into one of three volumetric chest CT datasets. Thirteen radiologists evaluated 157 nodules, resulting in 2041 detection opportunities. Analyzing the substrate CT data prior to nodule insertion, 14 image features were measured within a region around each nodule location. A generalized linear mixed-effects statistical model was fit to the data to verify the contribution of each metric on detectability. The model was tuned for simplicity, interpretability, and generalizability using stepwise regression applied to the primary features and their interactions. We found that variables corresponding to each of five categories (local structural distractors, local intensity, global context, local vascularity, and contiguity with structural distractors) were significant ( p < 0.01 ) factors in a standardized model. Moreover, reader-specific models conveyed significant differences among readers with significant distraction (missed detections) influenced by local intensity- versus local-structural characteristics being mutually exclusive. Readers with significant local intensity distraction ( n = 10 ) detected substantially fewer lung nodules than those who were significantly distracted by local structure ( n = 2 ), 46.1% versus 65.3% mean nodules detected, respectively.

Duke Scholars

Published In

J Med Imaging (Bellingham)

DOI

ISSN

2329-4302

Publication Date

March 2020

Volume

7

Issue

2

Start / End Page

022409

Location

United States

Related Subject Headings

  • 4003 Biomedical engineering
  • 3202 Clinical sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Li, B., Smith, T. B., Choudhury, K. R., Harrawood, B., Ebner, L., Roos, J. E., & Rubin, G. D. (2020). Influence of background lung characteristics on nodule detection with computed tomography. J Med Imaging (Bellingham), 7(2), 022409. https://doi.org/10.1117/1.JMI.7.2.022409
Li, Boning, Taylor B. Smith, Kingshuk R. Choudhury, Brian Harrawood, Lukas Ebner, Justus E. Roos, and Geoffrey D. Rubin. “Influence of background lung characteristics on nodule detection with computed tomography.J Med Imaging (Bellingham) 7, no. 2 (March 2020): 022409. https://doi.org/10.1117/1.JMI.7.2.022409.
Li B, Smith TB, Choudhury KR, Harrawood B, Ebner L, Roos JE, et al. Influence of background lung characteristics on nodule detection with computed tomography. J Med Imaging (Bellingham). 2020 Mar;7(2):022409.
Li, Boning, et al. “Influence of background lung characteristics on nodule detection with computed tomography.J Med Imaging (Bellingham), vol. 7, no. 2, Mar. 2020, p. 022409. Pubmed, doi:10.1117/1.JMI.7.2.022409.
Li B, Smith TB, Choudhury KR, Harrawood B, Ebner L, Roos JE, Rubin GD. Influence of background lung characteristics on nodule detection with computed tomography. J Med Imaging (Bellingham). 2020 Mar;7(2):022409.

Published In

J Med Imaging (Bellingham)

DOI

ISSN

2329-4302

Publication Date

March 2020

Volume

7

Issue

2

Start / End Page

022409

Location

United States

Related Subject Headings

  • 4003 Biomedical engineering
  • 3202 Clinical sciences