[HTML][HTML] A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …
uncertainties during both optimization and decision making processes. They have been …
Deep learning in biomedical optics
This article reviews deep learning applications in biomedical optics with a particular
emphasis on image formation. The review is organized by imaging domains within …
emphasis on image formation. The review is organized by imaging domains within …
[HTML][HTML] Live-dead assay on unlabeled cells using phase imaging with computational specificity
Existing approaches to evaluate cell viability involve cell staining with chemical reagents.
However, the step of exogenous staining makes these methods undesirable for rapid …
However, the step of exogenous staining makes these methods undesirable for rapid …
Single-cell cytometry via multiplexed fluorescence prediction by label-free reflectance microscopy
Traditional imaging cytometry uses fluorescence markers to identify specific structures but is
limited in throughput by the labeling process. We develop a label-free technique that …
limited in throughput by the labeling process. We develop a label-free technique that …
Bayesian deep learning for reliable oral cancer image classification
In medical imaging, deep learning-based solutions have achieved state-of-the-art
performance. However, reliability restricts the integration of deep learning into practical …
performance. However, reliability restricts the integration of deep learning into practical …
Visible light optical coherence tomography angiography (vis-OCTA) facilitates local microvascular oximetry in the human retina
We report herein the first visible light optical coherence tomography angiography (vis-OCTA)
for human retinal imaging. Compared to the existing vis-OCT systems, we devised a …
for human retinal imaging. Compared to the existing vis-OCT systems, we devised a …
Uncertainty quantification implementations in human hemodynamic flows
Background and objective Human hemodynamic modeling is usually influenced by
uncertainties occurring from a considerable unavailability of information linked to the …
uncertainties occurring from a considerable unavailability of information linked to the …
BlindNet: an untrained learning approach toward computational imaging with model uncertainty
The solution of an inverse problem in computational imaging (CI) often requires the
knowledge of the physical model and/or the object. However, in many practical applications …
knowledge of the physical model and/or the object. However, in many practical applications …
Beta network for boundary detection under nondeterministic labels
M Li, D Chen, S Liu - Knowledge-Based Systems, 2023 - Elsevier
Supervised data are not always uncontroversial, especially for boundary detection tasks.
Considering that we have a portrait, the face contour is naturally the most salient boundary …
Considering that we have a portrait, the face contour is naturally the most salient boundary …
Uncertainty quantification for deep unrolling-based computational imaging
Deep unrolling is an emerging deep learning-based image reconstruction methodology that
bridges the gap between model-based and purely deep learning-based image …
bridges the gap between model-based and purely deep learning-based image …