Noise-robust breathing-phase estimation on marker-free, ultra low dose X-ray projections for real-time tumor localization via surrogate structures

Dellmann, Max F.W.; Jerg, Katharina I.; Stratemeier, Johanna; Heiman, Ron; Hesser, Jürgen; Aschenbrenner, Katharina P.; Blessing, Manuel

doi:10.1016/j.zemedi.2021.04.001

Cited by 1 publication

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 9 DVF from DIR were then Principal Component Analysis, with 3 PCA correlations and support vectors maintained in this method. Applying Siddon's method [26], we generated x-ray images at various stages to those used for learning, with varying respiration frequency and amplitude and crane directions. There were no embedded calibration devices on this client, thus true 3D lump localization was not accessible to assess our approach.…”

Section: Proposed Workmentioning

confidence: 99%

Biomedical image restoration using machine learning GPU acceleration approach for precision improvement

Hazela

Aarti

Khandelwal

et al. 2022

ijhs

View full text Add to dashboard Cite

Focusing the image in a single x-ray projection, an algorithm proposed for actual time volumetric image rebuilt and 3-dimensional location of the lump. Using the Principal Component Analysis (PCA) initialize the parameterized Deformation Vector Fields (DVF) of pulmonary movement. By adjusting the PCA coefficients, applied the DVF applied to optimize the reference image so that, the simulated projection of the rebuilt image matches the observed projection. The digital phantom & patient information was used to evaluate the technique. The phantom has an average relative image rebuilt error of 7.5 percent and a 3-dimensional location of the lump inaccuracy of 0.9 mm, correspondingly. The patient's location of the lump inaccuracy is less than 2 mm. On a GPU NVIDIA C1060, recreating a single volumetric image from every projection takes about 0.2 & 0.3 secs for patient and phantom. From a single image, clinical relevance could lead to reliable 3-dimensional lump tracking.

show abstract

Section: Proposed Workmentioning

confidence: 99%