scholarly journals Lung segmentation in digital radiographs

1994 ◽  
Vol 7 (2) ◽  
pp. 79-84 ◽  
Author(s):  
Ewa Pietka
Keyword(s):  
Lung Segmentation ◽  
Digital Radiographs

scholarly journals Multi-stage transfer learning for lung segmentation using portable X-ray devices for patients with COVID-19

2021 ◽  
Vol 173 ◽  
pp. 114677
Author(s):  
Plácido L. Vidal ◽  
Joaquim de Moura ◽  
Jorge Novo ◽  
Marcos Ortega
Keyword(s):  
Transfer Learning ◽  
Lung Segmentation ◽  
X Ray ◽  
Multi Stage

scholarly journals Deep learning-based segmentation of the lung in MR-images acquired by a stack-of-spirals trajectory at ultra-short echo-times

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Andreas M. Weng ◽  
Julius F. Heidenreich ◽  
Corona Metz ◽  
Simon Veldhoen ◽  
Thorsten A. Bley ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Accurate Estimation ◽  
Dice Similarity Coefficient ◽  
Manual Segmentation ◽  
Pearson’S Correlation ◽  
Lung Volumes ◽  
Lung Segmentation ◽  
Pearson's Correlation ◽  
Lung Mri

Abstract Background Functional lung MRI techniques are usually associated with time-consuming post-processing, where manual lung segmentation represents the most cumbersome part. The aim of this study was to investigate whether deep learning-based segmentation of lung images which were scanned by a fast UTE sequence exploiting the stack-of-spirals trajectory can provide sufficiently good accuracy for the calculation of functional parameters. Methods In this study, lung images were acquired in 20 patients suffering from cystic fibrosis (CF) and 33 healthy volunteers, by a fast UTE sequence with a stack-of-spirals trajectory and a minimum echo-time of 0.05 ms. A convolutional neural network was then trained for semantic lung segmentation using 17,713 2D coronal slices, each paired with a label obtained from manual segmentation. Subsequently, the network was applied to 4920 independent 2D test images and results were compared to a manual segmentation using the Sørensen–Dice similarity coefficient (DSC) and the Hausdorff distance (HD). Obtained lung volumes and fractional ventilation values calculated from both segmentations were compared using Pearson’s correlation coefficient and Bland Altman analysis. To investigate generalizability to patients outside the CF collective, in particular to those exhibiting larger consolidations inside the lung, the network was additionally applied to UTE images from four patients with pneumonia and one with lung cancer. Results The overall DSC for lung tissue was 0.967 ± 0.076 (mean ± standard deviation) and HD was 4.1 ± 4.4 mm. Lung volumes derived from manual and deep learning based segmentations as well as values for fractional ventilation exhibited a high overall correlation (Pearson’s correlation coefficent = 0.99 and 1.00). For the additional cohort with unseen pathologies / consolidations, mean DSC was 0.930 ± 0.083, HD = 12.9 ± 16.2 mm and the mean difference in lung volume was 0.032 ± 0.048 L. Conclusions Deep learning-based image segmentation in stack-of-spirals based lung MRI allows for accurate estimation of lung volumes and fractional ventilation values and promises to replace the time-consuming step of manual image segmentation in the future.

scholarly journals Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem

2020 ◽  
Vol 4 (1) ◽  
Author(s):  
Johannes Hofmanninger ◽  
Forian Prayer ◽  
Jeanny Pan ◽  
Sebastian Röhrich ◽  
Helmut Prosch ◽  
...  
Keyword(s):  
Lung Segmentation ◽  
Routine Imaging

Merging parametric active contours within homogeneous image regions for MRI-based lung segmentation

2003 ◽  
Vol 22 (2) ◽  
pp. 189-199 ◽  
Author(s):  
N. Ray ◽  
S.T. Acton ◽  
T. Altes ◽  
E.E. de Lange ◽  
J.R. Brookeman
Keyword(s):  
Active Contours ◽  
Lung Segmentation ◽  
Parametric Active Contours

142. Clinical Magnification Error in Lateral Spinal Digital Radiographs

2007 ◽  
Vol 7 (5) ◽  
pp. 68S
Author(s):  
Bheesma Ravi ◽  
Raja Rampersaud
Keyword(s):  
Digital Radiographs

Comparison of two software packages for determining radiographic bone aluminium equivalent values

2013 ◽  
Vol 9 (3-4) ◽  
pp. 219-222 ◽  
Author(s):  
C.I. O'Connor-Robison ◽  
B.D. Nielsen
Keyword(s):  
Standard Deviation ◽  
Bone Mineral Content ◽  
Optical Density ◽  
Digital Technology ◽  
Mineral Content ◽  
Lateral View ◽  
Digital Analysis ◽  
Densitometric Analysis ◽  
Digital Radiographs ◽  
Software Packages

Radiographic photodensitometry has been used to track changes in bone mineral content in the distal limb of horses through traditional film radiographs. With increasing popularity of digital radiographs, the technique has been adapted for digital technology. The objective of this study was to validate and describe the analysis of digital radiographs and to compare traditional densitometric analysis to digital analysis. Twelve traditional and 12 digital radiographs were taken of the left third metacarpal (MCIII) of 12 horses with an aluminium stepwedge penetrometer attached to the radiographic cassette. Both medial-lateral and dorsal-palmar views were represented. The traditional and digital radiographs were each analysed using two different methods to compare results. Analysis involved determining optical density at each step of the aluminium stepwedge, plotting optical density verses mm Al, and then determining the equation of the subsequent line. The optical density of each cortice was inserted into the equation and radiographic bone aluminium equivalents (RBAE) in mm Al for each cortice was determined. Total RBAE was also examined 1 cm distal to the nutrient foramen of the MCIII. Data were analysed using Proc CORR (SAS v. 9.1) and are reported as mean ± standard deviation. Total RBAE on the dorsal-palmar view from traditional radiographs averaged 286±154 mm Al for digital analysis and 292±173 mm Al for densitometric analysis (R2=0.98). Total RBAE on medial-lateral view from the digital radiographs averaged 539±137 mm Al for digital analysis and 530±165 mm Al for densitometric analysis (R2=0.95). The results demonstrate high correlations between analyses, thereby validating that digital analysis yields similar results as densitometric analysis. Digital radiographs, with increased clarity as compared to traditional films, should allow greater ability to detect treatment differences in research trials, and monitor changes associated with training or nutrition.

Diagnostic yield of ink-jet prints from digital radiographs for the assessment of approximal carious lesions: ROC-analysis

2011 ◽  
Vol 79 (2) ◽  
pp. 277-282 ◽  
Author(s):  
Ralf K.W. Schulze ◽  
Stefanie Grimm ◽  
Dirk Schulze ◽  
Kai Voss ◽  
Hans-Peter Keller ◽  
...  
Keyword(s):  
Roc Analysis ◽  
Diagnostic Yield ◽  
Digital Radiographs ◽  
Carious Lesions ◽  
Ink Jet
Sign in / Sign up

Export Citation Format

Share Document