Výsledky vyhledávání - "Rahman, Obaidullah"

Report

Deep learning based workflow for accelerated industrial X-ray Computed Tomography

Autor: Rahman, Obaidullah, Venkatakrishnan, Singanallur V., Scime, Luke, Brackman, Paul, Frederick, Curtis, Dehoff, Ryan, Paquit, Vincent, Ziabari, Amirkoushyar

X-ray computed tomography (XCT) is an important tool for high-resolution non-destructive characterization of additively-manufactured metal components. XCT reconstructions of metal components may have beam hardening artifacts such as cupping and strea

Externí odkaz: http://arxiv.org/abs/2309.14371

Zobrazit plný text záznamu

Report

Design of Novel Loss Functions for Deep Learning in X-ray CT

Autor: Rahman, Obaidullah, Sauer, Ken D., Nagare, Madhuri, Bouman, Charles A., Melnyk, Roman, Tang, Jie, Nett, Brian

Deep learning (DL) shows promise of advantages over conventional signal processing techniques in a variety of imaging applications. The networks' being trained from examples of data rather than explicitly designed allows them to learn signal and nois

Externí odkaz: http://arxiv.org/abs/2309.14367

Zobrazit plný text záznamu

Report

Statistically Adaptive Filtering for Low Signal Correction in X-ray Computed Tomography

Autor: Rahman, Obaidullah, Sauer, Ken D., Bouman, Charles A., Melnyk, Roman, Nett, Brian

Low x-ray dose is desirable in x-ray computed tomographic (CT) imaging due to health concerns. But low dose comes with a cost of low signal artifacts such as streaks and low frequency bias in the reconstruction. As a result, low signal correction is

Externí odkaz: http://arxiv.org/abs/2309.13406

Zobrazit plný text záznamu

Report

MBIR Training for a 2.5D DL network in X-ray CT

Autor: Rahman, Obaidullah, Nagare, Madhuri, Sauer, Ken D., Bouman, Charles A., Melnyk, Roman, Nett, Brian, Tang, Jie

In computed tomographic imaging, model based iterative reconstruction methods have generally shown better image quality than the more traditional, faster filtered backprojection technique. The cost we have to pay is that MBIR is computationally expen

Externí odkaz: http://arxiv.org/abs/2309.13399

Zobrazit plný text záznamu

Report

Direct Iterative Reconstruction of Multiple Basis Material Images in Photon-counting Spectral CT

Autor: Rahman, Obaidullah, Sauer, Ken, Evans, Connor, Roeder, Ryan

In this work, we perform direct material reconstruction from spectral CT data using a model based iterative reconstruction (MBIR) approach. Material concentrations are measured in volume fractions, whose total is constrained by a maximum of unity. A

Externí odkaz: http://arxiv.org/abs/2309.13397

Zobrazit plný text záznamu