Enhancing signal detectability in learning-based CT reconstruction with a model observer inspired loss function
This addresses a critical issue for medical imaging in screening and diagnosis, though it appears incremental as it modifies the training loss rather than introducing a new paradigm.
The paper tackles the problem of deep neural networks wiping out small, low-contrast features in sparse-view CT reconstructions when trained with pixel-wise losses, and demonstrates improved signal detectability using a model observer inspired loss function on synthetic breast CT data.
Deep neural networks used for reconstructing sparse-view CT data are typically trained by minimizing a pixel-wise mean-squared error or similar loss function over a set of training images. However, networks trained with such pixel-wise losses are prone to wipe out small, low-contrast features that are critical for screening and diagnosis. To remedy this issue, we introduce a novel training loss inspired by the model observer framework to enhance the detectability of weak signals in the reconstructions. We evaluate our approach on the reconstruction of synthetic sparse-view breast CT data, and demonstrate an improvement in signal detectability with the proposed loss.