Skip to main content

Table 3 Predictor and outcome variables of second multiple linear regression analysis with their according F-statistic

From: Impact of deep learning image reconstruction on volumetric accuracy and image quality of pulmonary nodules with different morphologies in low-dose CT

Outcome variable

APEvolume

 

Soft tissue kernel

Lung kernel

Predictor variable (main effects)

F-statistic

p-value

F-statistic

p-value

Reconstruction algorithm

15.77

3.9E-10***

76.74

< 2.2E-16***

Nodule morphology

71.32

< 2.2E-16***

13.13

2.2E-06***

Nodule diameter

56.29

< 2.2E-16***

66.09

< 2.2E-16***

Predictor variable (interaction effects)

    

Reconstruction algorithm – Nodule morphology

4.31

2.5E-04***

4.05

4.8E-04***

Reconstruction algorithm – Nodule diameter

2.73

3.6E-04***

4.09

2.1E-07***

Nodule morphology – Nodule diameter

50.29

< 2.2E-16***

15.03

< 2.2E-16***

  1. Two sub models were made for each of the reconstruction kernel (soft tissue and lung), both at a standardized radiation dose. Abbreviations: APEvolume: Absolute percentage volumetric error. (Significance codes: ***p < 0.001, **p < 0.01, *p < 0.1, ns not significant)
Back to article page

Cancer Imaging

ISSN: 1470-7330

Contact us