Skip to main content
Journal cover image

Evaluating renal lesions using deep-learning based extension of dual-energy FoV in dual-source CT-A retrospective pilot study.

Publication ,  Journal Article
Schwartz, FR; Clark, DP; Ding, Y; Ramirez-Giraldo, JC; Badea, CT; Marin, D
Published in: Eur J Radiol
June 2021

PURPOSE: Dual-source (DS) CT, dual-energy (DE) field of view (FoV) is limited to the size of the smaller detector array. The purpose was to establish a deep learning-based approach to DE extrapolation by estimating missing image data using data from both tubes to evaluate renal lesions. METHOD: A DE extrapolation deep-learning (DEEDL) algorithm had been trained on DECT data of 50 patients using a DSCT with DE-FoV = 33 cm (Somatom Flash). Data from 128 patients with known renal lesions falling within DE-FoV was retrospectively collected (100/140 kVp; reference dataset 1). A smaller DE-FoV = 20 cm was simulated excluding the renal lesion of interest (dataset 2) and the DEEDL was applied to this dataset. Output from the DEEDL algorithm was evaluated using ReconCT v14.1 and Syngo.via. Mean attenuation values in lesions on mixed images (HU) were compared calculating the root-mean-squared-error (RMSE) between the datasets using MATLAB R2019a. RESULTS: The DEEDL algorithm performed well reproducing the image data of the kidney lesions (Bosniak 1 and 2: 125, Bosniak 2F: 6, Bosniak 3: 1 and Bosniak 4/(partially) solid: 32) with RSME values of 10.59 HU, 15.7 HU for attenuation, virtual non-contrast, respectively. The measurements performed in dataset 1 and 2 showed strong correlation with linear regression (r2: attenuation = 0.89, VNC = 0.63, iodine = 0.75), lesions were classified as enhancing with an accuracy of 0.91. CONCLUSION: This DEEDL algorithm can be used to reconstruct a full dual-energy FoV from restricted data, enabling reliable HU value measurements in areas not covered by the smaller FoV and evaluation of renal lesions.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Eur J Radiol

DOI

EISSN

1872-7727

Publication Date

June 2021

Volume

139

Start / End Page

109734

Location

Ireland

Related Subject Headings

  • Tomography, X-Ray Computed
  • Retrospective Studies
  • Reproducibility of Results
  • Radiography, Dual-Energy Scanned Projection
  • Pilot Projects
  • Nuclear Medicine & Medical Imaging
  • Kidney
  • Humans
  • Deep Learning
  • Contrast Media
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Schwartz, F. R., Clark, D. P., Ding, Y., Ramirez-Giraldo, J. C., Badea, C. T., & Marin, D. (2021). Evaluating renal lesions using deep-learning based extension of dual-energy FoV in dual-source CT-A retrospective pilot study. Eur J Radiol, 139, 109734. https://doi.org/10.1016/j.ejrad.2021.109734
Schwartz, Fides R., Darin P. Clark, Yuqin Ding, Juan Carlos Ramirez-Giraldo, Cristian T. Badea, and Daniele Marin. “Evaluating renal lesions using deep-learning based extension of dual-energy FoV in dual-source CT-A retrospective pilot study.Eur J Radiol 139 (June 2021): 109734. https://doi.org/10.1016/j.ejrad.2021.109734.
Schwartz FR, Clark DP, Ding Y, Ramirez-Giraldo JC, Badea CT, Marin D. Evaluating renal lesions using deep-learning based extension of dual-energy FoV in dual-source CT-A retrospective pilot study. Eur J Radiol. 2021 Jun;139:109734.
Schwartz, Fides R., et al. “Evaluating renal lesions using deep-learning based extension of dual-energy FoV in dual-source CT-A retrospective pilot study.Eur J Radiol, vol. 139, June 2021, p. 109734. Pubmed, doi:10.1016/j.ejrad.2021.109734.
Schwartz FR, Clark DP, Ding Y, Ramirez-Giraldo JC, Badea CT, Marin D. Evaluating renal lesions using deep-learning based extension of dual-energy FoV in dual-source CT-A retrospective pilot study. Eur J Radiol. 2021 Jun;139:109734.
Journal cover image

Published In

Eur J Radiol

DOI

EISSN

1872-7727

Publication Date

June 2021

Volume

139

Start / End Page

109734

Location

Ireland

Related Subject Headings

  • Tomography, X-Ray Computed
  • Retrospective Studies
  • Reproducibility of Results
  • Radiography, Dual-Energy Scanned Projection
  • Pilot Projects
  • Nuclear Medicine & Medical Imaging
  • Kidney
  • Humans
  • Deep Learning
  • Contrast Media