@article{WengHeidenreichMetzetal.2021,
  author    = {Weng, Andreas M. and Heidenreich, Julius F. and Metz, Corona and Veldhoen, Simon and Bley, Thorsten A. and Wech, Tobias},
  title     = {Deep learning-based segmentation of the lung in MR-images acquired by a stack-of-spirals trajectory at ultra-short echo-times},
  series = {BMC Medical Imaging},
  volume    = {21},
  journal   = {BMC Medical Imaging},
  doi       = {10.1186/s12880-021-00608-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-260520},
  year      = {2021},
  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 S{\o}rensen-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.},
  language  = {en}
}
@article{PetritschPannbeckerWengetal.2021,
  author    = {Petritsch, Bernhard and Pannbecker, Pauline and Weng, Andreas M. and Grunz, Jan-Peter and Veldhoen, Simon and Bley, Thorsten A. and Kosmala, Aleksander},
  title     = {Split-filter dual-energy CT pulmonary angiography for the diagnosis of acute pulmonary embolism: a study on image quality and radiation dose},
  series = {Quantitative Imaging in Medicine and Surgery},
  volume    = {11},
  journal   = {Quantitative Imaging in Medicine and Surgery},
  number    = {5},
  doi       = {10.21037/qims-20-740},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-231456},
  pages     = {1817-1827},
  year      = {2021},
  abstract  = {Background: Computed tomography (CT) pulmonary angiography is the diagnostic reference standard in suspected pulmonary embolism (PE). Favorable results for dual-energy CT (DECT) images have been reported for this condition. Nowadays, dual-energy data acquisition is feasible with different technical options, including a single-source split-filter approach. Therefore, the aim of this retrospective study was to investigate image quality and radiation dose of thoracic split-filter DECT in comparison to conventional single-energy CT in patients with suspected PE. Methods: A total of 110 CT pulmonary angiographies were accomplished either as standard single-energy CT with automatic tube voltage selection (ATVS) (n=58), or as split-filter DECT (n=52). Objective [pulmonary artery CT attenuation, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR)] and subjective image quality [four-point Likert scale; three readers (R)] were compared among the two study groups. Size-specific dose estimates (SSDE), dose-length-product (DLP) and volume CT dose index (CTDIvol) were assessed for radiation dose analysis. Results: Split-filter DECT images yielded 67.7\% higher SNR (27.0 vs. 16.1; P<0.001) and 61.9\% higher CNR (22.5 vs. 13.9; P<0.001) over conventional single-energy images, whereas CT attenuation was significantly lower (344.5 vs. 428.2 HU; P=0.013). Subjective image quality was rated good or excellent in 93.0\%/98.3\%/77.6\% (R1/R2/R3) of the single-energy CT scans, and 84.6\%/82.7\%/80.8\% (R1/R2/R3) of the split-filter DECT scans. SSDE, DLP and CTDIvol were significantly lower for conventional single-energy CT compared to split-filter DECT (all P<0.05), which was associated with 26.7\% higher SSDE. Conclusions: In the diagnostic workup of acute PE, the split-filter allows for dual-energy data acquisition from single-source single-layer CT scanners. The existing opportunity to assess pulmonary "perfusion" based on analysis of iodine distribution maps is associated with higher radiation dose in terms of increased SSDE than conventional single-energy CT with ATVS. Moreover, a proportion of up to 3.8\% non-diagnostic examinations in the current reference standard test for PE is not negligible.},
  language  = {en}
}