This study addresses the challenge of reconstructing sparse signals, a frequent occurrence in the context of overdispersed photon-limited imaging. While the noise behavior in such imaging settings is typically modeled using a Poisson distribution, the negative binomial distribution is more suitable in overdispersed scenarios where the noise variance exceeds the signal mean. Knowledge of the maximum and minimum signal intensity can be effectively utilized within the computational framework to enhance the accuracy of signal reconstruction. In this paper, we use a gradient-based method for sparse signal recovery that leverages a negative binomial distribution for noise modeling, enforces bound constraints to adhere to upper and lower signal intensity thresholds, and employs a sparsity-promoting regularization term. The numerical experiments we present demonstrate that the incorporation of these features significantly improves the reconstruction of sparse signals from overdispersed measurements.
more »
« less
This content will become publicly available on January 1, 2025
Domain Expansion via Network Adaptation for Solving Inverse Problems
Deep learning-based methods deliver state-of-the-art performance for solving inverse problems that arise in computational imaging. These methods can be broadly divided into two groups: (1) learn a network to map measurements to the signal estimate, which is known to be fragile; (2) learn a prior for the signal to use in an optimization-based recovery. Despite the impressive results from the latter approach, many of these methods also lack robustness to shifts in data distribution, measurements, and noise levels. Such domain shifts result in a performance gap and in some cases introduce undesired artifacts in the estimated signal. In this paper, we explore the qualitative and quantitative effects of various domain shifts and propose a flexible and parameter efficient framework that adapts pretrained networks to such shifts. We demonstrate the effectiveness of our method for a number of reconstruction tasks that involve natural image, MRI, and CT imaging domains under distribution, measurement model, and noise level shifts. Our experiments demonstrate that our method achieves competitive performance compared to independently fully trained networks, while requiring significantly fewer additional parameters, and outperforms several domain adaptation techniques.
more »
« less
- Award ID(s):
- 2043134
- NSF-PAR ID:
- 10504938
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Transactions on Computational Imaging
- Volume:
- 10
- ISSN:
- 2573-0436
- Page Range / eLocation ID:
- 549 to 559
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that deep-learning-based image reconstruction methods are sensitive to perturbations and are less robust than traditional methods: Neural networks (i) may be sensitive to small, yet adversarially-selected perturbations, (ii) may perform poorly under distribution shifts, and (iii) may fail to recover small but important features in an image. In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods. We find, contrary to prior works, that both trained and un-trained methods are vulnerable to adversarial perturbations. Moreover, both trained and un-trained methods tuned for a particular dataset suffer very similarly from distribution shifts. Finally, we demonstrate that an image reconstruction method that achieves higher reconstruction quality, also performs better in terms of accurately recovering fine details. Our results indicate that the state-of-the-art deep-learning-based image reconstruction methods provide improved performance than traditional methods without compromising robustness.more » « less
-
Deep learning based image reconstruction methods outperform traditional methods. However, neural networks suffer from a performance drop when applied to images from a different distribution than the training images. For example, a model trained for reconstructing knees in accelerated magnetic resonance imaging (MRI) does not reconstruct brains well, even though the same network trained on brains reconstructs brains perfectly well. Thus there is a distribution shift performance gap for a given neural network, defined as the difference in performance when training on a distribution P and training on another distribution Q, and evaluating both models on Q. In this work, we propose a domain adaptation method for deep learning based compressive sensing that relies on self-supervision during training paired with test-time training at inference. We show that for four natural distribution shifts, this method essentially closes the distribution shift performance gap for state-of-the-art architectures for accelerated MRI.more » « less
-
Domain adaptation techniques using deep neural networks have been mainly used to solve the distribution shift problem in homogeneous domains where data usually share similar feature spaces and have the same dimensionalities. Nevertheless, real world applications often deal with heterogeneous domains that come from completely different feature spaces with different dimensionalities. In our remote sensing application, two remote sensing datasets collected by an active sensor and a passive one are heterogeneous. In particular, CALIOP actively measures each atmospheric column. In this study, 25 measured variables/features that are sensitive to cloud phase are used and they are fully labeled. VIIRS is an imaging radiometer, which collects radiometric measurements of the surface and atmosphere in the visible and infrared bands. Recent studies have shown that passive sensors may have difficulties in prediction cloud/aerosol types in complicated atmospheres (e.g., overlapping cloud and aerosol layers, cloud over snow/ice surface, etc.). To overcome the challenge of the cloud property retrieval in passive sensor, we develop a novel VAE based approach to learn domain invariant representation that capture the spatial pattern from multiple satellite remote sensing data (VDAM), to build a domain invariant cloud property retrieval method to accurately classify different cloud types (labels) in the passive sensing dataset. We further exploit the weight based alignment method on the label space to learn a powerful domain adaptation technique that is pertinent to the remote sensing application. Experiments demonstrate our method outperforms other state-of-the-art machine learning methods and achieves higher accuracy in cloud property retrieval in the passive satellite dataset.more » « less
-
Yap, Pew-Thian (Ed.)Diffusion weighted imaging (DWI) with multiple, high b-values is critical for extracting tissue microstructure measurements; however, high b-value DWI images contain high noise levels that can overwhelm the signal of interest and bias microstructural measurements. Here, we propose a simple denoising method that can be applied to any dataset, provided a low-noise, single-subject dataset is acquired using the same DWI sequence. The denoising method uses a one-dimensional convolutional neural network (1D-CNN) and deep learning to learn from a low-noise dataset, voxel-by-voxel. The trained model can then be applied to high-noise datasets from other subjects. We validated the 1D-CNN denoising method by first demonstrating that 1D-CNN denoising resulted in DWI images that were more similar to the noise-free ground truth than comparable denoising methods, e.g., MP-PCA, using simulated DWI data. Using the same DWI acquisition but reconstructed with two common reconstruction methods, i.e. SENSE1 and sum-of-square, to generate a pair of low-noise and high-noise datasets, we then demonstrated that 1D-CNN denoising of high-noise DWI data collected from human subjects showed promising results in three domains: DWI images, diffusion metrics, and tractography. In particular, the denoised images were very similar to a low-noise reference image of that subject, more than the similarity between repeated low-noise images (i.e. computational reproducibility). Finally, we demonstrated the use of the 1D-CNN method in two practical examples to reduce noise from parallel imaging and simultaneous multi-slice acquisition. We conclude that the 1D-CNN denoising method is a simple, effective denoising method for DWI images that overcomes some of the limitations of current state-of-the-art denoising methods, such as the need for a large number of training subjects and the need to account for the rectified noise floor.more » « less
