Uncertainty Estimation and Out-of-Distribution Detection for Deep Learning-Based Image Reconstruction using the Local Lipschitz.

Accurate image reconstruction is at the heart of diagnostics in medical imaging. Supervised deep learning-based approaches have been investigated for solving inverse problems including image reconstruction. However, these trained models encounter unseen data distributions that are widely shifted from training data during deployment. Therefore, it is essential to assess whether a given input falls within the training data distribution. Current uncertainty estimation approaches focus on providing an uncertainty map to radiologists, rather than assessing the training distribution fit. In this work, we propose a method based on the local Lipschitz metric to distinguish out-of-distribution images from in-distribution with an area under the curve of 99.94% for True Positive Rate versus False Positive Rate. We demonstrate a very strong relationship between the local Lipschitz value and mean absolute error (MAE), supported by a Spearman's rank correlation coefficient of 0.8475, to determine an uncertainty estimation threshold for optimal performance. Through the identification of false positives, we demonstrate the local Lipschitz and MAE relationship can guide data augmentation and reduce uncertainty. Our study was validated using the AUTOMAP architecture for sensor-to-image Magnetic Resonance Imaging (MRI) reconstruction. We demonstrate our approach outperforms baseline techniques of Monte-Carlo dropout and deep ensembles as well as the state-of-the-art Mean Variance Estimation (MVE) network approach. We expand our application scope to MRI denoising and Computed Tomography (CT) sparse-to-full view reconstructions using UNET architectures. We show our approach is applicable to various architectures and applications, especially in medical imaging, where preserving diagnostic accuracy of reconstructed images remains paramount.

Incident dementia and long-term exposure to constituents of fine particle air pollution: A national cohort study in the United States.

Growing evidence suggests that fine particulate matter (PM2.5) likely increases the risks of dementia, yet little is known about the relative contributions of different constituents. Here, we conducted a nationwide population-based cohort study (2000 to 2017) by integrating the Medicare Chronic Conditions Warehouse database and two independently sourced datasets of high-resolution PM2.5 major chemical composition, including black carbon (BC), organic matter (OM), nitrate (NO3-), sulfate (SO42-), ammonium (NH4+), and soil dust (DUST). To investigate the impact of long-term exposure to PM2.5 constituents on incident all-cause dementia and Alzheimer's disease (AD), hazard ratios for dementia and AD were estimated using Cox proportional hazards models, and penalized splines were used to evaluate potential nonlinear concentration-response (C-R) relationships. Results using two exposure datasets consistently indicated higher rates of incident dementia and AD for an increased exposure to PM2.5 and its major constituents. An interquartile range increase in PM2.5 mass was associated with a 6 to 7% increase in dementia incidence and a 9% increase in AD incidence. For different PM2.5 constituents, associations remained significant for BC, OM, SO42-, and NH4+ for both end points (even after adjustments of other constituents), among which BC and SO42- showed the strongest associations. All constituents had largely linear C-R relationships in the low exposure range, but most tailed off at higher exposure concentrations. Our findings suggest that long-term exposure to PM2.5 is significantly associated with higher rates of incident dementia and AD and that SO42-, BC, and OM related to traffic and fossil fuel combustion might drive the observed associations.

Image reconstruction by domain-transform manifold learning.

Image reconstruction is essential for imaging applications across the physical and life sciences, including optical and radar systems, magnetic resonance imaging, X-ray computed tomography, positron emission tomography, ultrasound imaging and radio astronomy. During image acquisition, the sensor encodes an intermediate representation of an object in the sensor domain, which is subsequently reconstructed into an image by an inversion of the encoding function. Image reconstruction is challenging because analytic knowledge of the exact inverse transform may not exist a priori, especially in the presence of sensor non-idealities and noise. Thus, the standard reconstruction approach involves approximating the inverse function with multiple ad hoc stages in a signal processing chain, the composition of which depends on the details of each acquisition strategy, and often requires expert parameter tuning to optimize reconstruction performance. Here we present a unified framework for image reconstruction-automated transform by manifold approximation (AUTOMAP)-which recasts image reconstruction as a data-driven supervised learning task that allows a mapping between the sensor and the image domain to emerge from an appropriate corpus of training data. We implement AUTOMAP with a deep neural network and exhibit its flexibility in learning reconstruction transforms for various magnetic resonance imaging acquisition strategies, using the same network architecture and hyperparameters. We further demonstrate that manifold learning during training results in sparse representations of domain transforms along low-dimensional data manifolds, and observe superior immunity to noise and a reduction in reconstruction artefacts compared with conventional handcrafted reconstruction methods. In addition to improving the reconstruction performance of existing acquisition methodologies, we anticipate that AUTOMAP and other learned reconstruction approaches will accelerate the development of new acquisition strategies across imaging modalities.