Share Email Print

Proceedings Paper

Image reconstruction using priors from deep learning
Author(s): Devi Ayyagari; Nisha Ramesh; Dimitri Yatsenko; Tolga Tasdizen; Cristain Atria
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Tomosynthesis, i.e. reconstruction of 3D volumes using projections from a limited perspective is a classical inverse, ill-posed or under constrained problem. Data insufficiency leads to reconstruction artifacts that vary in severity depending on the particular problem, the reconstruction method and also on the object being imaged. Machine learning has been used successfully in tomographic problems where data is insufficient, but the challenge with machine learning is that it introduces bias from the learning dataset. A novel framework to improve the quality of the tomosynthesis reconstruction that limits the learning dataset bias by maintaining consistency with the observed data is proposed. Convolutional Neural Networks (CNN) are embedded as regularizers in the reconstruction process to introduce the expected features and characterstics of the likely imaged object. The minimization of the objective function keeps the solution consistent with the observations and limits the bias introduced by the machine learning regularizers, improving the quality of the reconstruction. The proposed method has been developed and studied in the specific problem of Cone Beam Tomosynthesis Flouroscopy (CBT-fluoroscopy)1 but it is a general framework that can be applied to any image reconstruction problem that is limited by data insufficiency.

Paper Details

Date Published: 2 March 2018
PDF: 7 pages
Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 105740H (2 March 2018); doi: 10.1117/12.2293766
Show Author Affiliations
Devi Ayyagari, nView Medical Inc. (United States)
Nisha Ramesh, The Univ. of Utah (United States)
Dimitri Yatsenko, Baylor College of Medicine (United States)
Tolga Tasdizen, The Univ. of Utah (United States)
Cristain Atria, nView Medical Inc. (United States)

Published in SPIE Proceedings Vol. 10574:
Medical Imaging 2018: Image Processing
Elsa D. Angelini; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top