Tunable neural networks for CT image formation
- 1 May 2023
- journal article
- research article
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 10 (03), 033501
- https://doi.org/10.1117/1.jmi.10.3.033501
Abstract
Optimization of CT image quality typically involves balancing variance and bias. In traditional filtered back-projection, this trade-off is controlled by the filter cutoff frequency. In model-based iterative reconstruction, the regularization strength parameter often serves the same function. Deep neural networks (DNNs) typically do not provide this tunable control over output image properties. Models are often trained to minimize the expected mean squared error, which penalizes both variance and bias in image outputs but does not offer any control over the trade-off between the two. We propose a method for controlling the output image properties of neural networks with a new loss function called weighted covariance and bias (WCB). Our proposed method uses multiple noise realizations of the input images during training to allow for separate weighting matrices for the variance and bias penalty terms. Moreover, we show that tuning these weights enables targeted penalization of specific image features with spatial frequency domain penalties. To evaluate our method, we present a simulation study using digital anthropomorphic phantoms, physical simulation of CT measurements, and image formation with various algorithms. We show that the WCB loss function offers a greater degree of control over trade-offs between variance and bias, whereas mean-squared error provides only one specific image quality configuration. We also show that WCB can be used to control specific image properties including variance, bias, spatial resolution, and the noise correlation of neural network outputs. Finally, we present a method to optimize the proposed weights for a spiculated lung nodule shape discrimination task. Our results demonstrate this new image quality can control the image properties of DNN outputs and optimize image quality for task-specific performance.Keywords
This publication has 17 references indexed in Scilit:
- Deep learning for tomographic image reconstructionNature Machine Intelligence, 2020
- Unpaired Image Denoising Using a Generative Adversarial Network in X-Ray CTIEEE Access, 2019
- Approximating the Ideal Observer and Hotelling Observer for Binary Signal Detection Tasks by Use of Supervised Learning MethodsIEEE Transactions on Medical Imaging, 2019
- Unbiased statistical image reconstruction in low-dose CTPublished by SPIE-Intl Soc Optical Eng ,2019
- Task-Driven Optimization of Fluence Field and Regularization for Model-Based Iterative Reconstruction in Computed TomographyIEEE Transactions on Medical Imaging, 2017
- Model-based iterative reconstruction for flat-panel cone-beam CT with focal spot blur, detector blur, and correlated noisePhysics in Medicine & Biology, 2015
- A Simple Low-Dose X-Ray CT Simulation From High-Dose ScanIEEE Transactions on Nuclear Science, 2015
- Wiener filter for filtered back projection in digital breast tomosynthesisProceedings of SPIE, 2012
- 4D XCAT phantom for multimodality imaging researchMedical Physics, 2010
- Why do commercial CT scanners still employ traditional, filtered back-projection for image reconstruction?Inverse Problems, 2009