Reliable deep-learning-based phase imaging with uncertainty quantification.
Ontology highlight
ABSTRACT:
SUBMITTER: Xue Y
PROVIDER: S-EPMC8329751 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Measurement of blood oxygen saturation (sO2) by optical imaging oximetry provides invaluable insight into local tissue functions and metabolism. Despite different embodiments and modalities, all label-free optical-imaging oximetry techniques utilize the same principle of sO2-dependent spectral contrast from haemoglobin. Traditional approaches for quantifying sO2 often rely on analytical models that are fitted by the spectral measurements. These approaches in practice suffer from uncertainties due to biological variability, tissue geometry, light scattering, systemic spectral bias, and variations in the experimental conditions. Here, we propose a new data-driven approach, termed deep spectral learning (DSL), to achieve oximetry that is highly robust to experimental variations and, more importantly, able to provide uncertainty quantification for each sO2 prediction. To demonstrate the robustness and generalizability of DSL, we analyse data from two visible light optical coherence tomography (vis-OCT) setups across two separate in vivo experiments on rat retinas. Predictions made by DSL are highly adaptive to experimental variabilities as well as the depth-dependent backscattering spectra. Two neural-network-based models are tested and compared with the traditional least-squares fitting (LSF) method. The DSL-predicted sO2 shows significantly lower mean-square errors than those of the LSF. For the first time, we have demonstrated en face maps of retinal oximetry along with a pixel-wise confidence assessment. Our DSL overcomes several limitations of traditional approaches and provides a more flexible, robust, and reliable deep learning approach for in vivo non-invasive label-free optical oximetry.
| S-EPMC6864044 | biostudies-literature
Project description:Reliable uncertainty quantification for statistical models is crucial in various downstream applications, especially for drug design and discovery where mistakes may incur a large amount of cost. This topic has therefore absorbed much attention and a plethora of methods have been proposed over the past years. The approaches that have been reported so far can be mainly categorized into two classes: distance-based approaches and Bayesian approaches. Although these methods have been widely used in many scenarios and shown promising performance with their distinct superiorities, being overconfident on out-of-distribution examples still poses challenges for the deployment of these techniques in real-world applications. In this study we investigated a number of consensus strategies in order to combine both distance-based and Bayesian approaches together with post-hoc calibration for improved uncertainty quantification in QSAR (Quantitative Structure-Activity Relationship) regression modeling. We employed a set of criteria to quantitatively assess the ranking and calibration ability of these models. Experiments based on 24 bioactivity datasets were designed to make critical comparison between the model we proposed and other well-studied baseline models. Our findings indicate that the hybrid framework proposed by us can robustly enhance the model ability of ranking absolute errors. Together with post-hoc calibration on the validation set, we show that well-calibrated uncertainty quantification results can be obtained in domain shift settings. The complementarity between different methods is also conceptually analyzed.
| S-EPMC8454160 | biostudies-literature
Project description:BackgroundMyocardial perfusion reserve index (MPRI) in magnetic resonance imaging (MRI) is an important indicator of ischemia, and its measurement typically involves manual procedures. The purposes of this study were to develop a fully automatic method for estimating the MPRI and to evaluate its performance.MethodsThe method consisted of segmenting the myocardium in dynamic contrast-enhanced (DCE) myocardial perfusion MRI data using Monte Carlo dropout U-Net, dividing the myocardium into segments based on landmark localization with machine learning, and estimating the MPRI after the calculation of the left ventricular and myocardial contrast upslopes. The proposed method was compared with a reference method, which involved manual adjustments of the myocardial contours and upslope ranges.ResultsIn test subjects, MPRIs measured by the proposed technique correlated with those by the manual reference in segmental assessment [intraclass correlation coefficient (ICC) =0.75, 95% CI: 0.70-0.79, P<0.001]. The automatic and reference MPRI values showed a mean difference of -0.02 and 95% limits of agreement of (-0.86, 0.82).ConclusionsThe proposed automatic method is based on deep learning segmentation and machine learning landmark detection for MPRI measurements in DCE perfusion MRI. It holds the potential to efficiently and quantitatively assess myocardial ischemia without any user's interaction.
| S-EPMC10722070 | biostudies-literature
Project description:Bayesian deep learning (BDL) has emerged as a powerful technique for quantifying uncertainty in classification tasks, surpassing the effectiveness of traditional models by aligning with the probabilistic nature of real-world data. This alignment allows for informed decision-making by not only identifying the most likely outcome but also quantifying the surrounding uncertainty. Such capabilities hold great significance in fields like medical diagnoses and autonomous driving, where the consequences of misclassification are substantial. To further improve uncertainty quantification, the research community has introduced Bayesian model ensembles, which combines multiple Bayesian models to enhance predictive accuracy and uncertainty quantification. These ensembles have exhibited superior performance compared to individual Bayesian models and even non-Bayesian counterparts. In this study, we propose a novel approach that leverages the power of Bayesian ensembles for enhanced uncertainty quantification. The proposed method exploits the disparity between predicted positive and negative classes and employes it as a ranking metric for model selection. For each instance or sample, the ensemble's output for each class is determined by selecting the top 'k' models based on this ranking. Experimental results on different medical image classifications demonstrate that the proposed method consistently outperforms or achieves comparable performance to conventional Bayesian ensemble. This investigation highlights the practical application of Bayesian ensemble techniques in refining predictive performance and enhancing uncertainty evaluation in image classification tasks.
| S-EPMC10825337 | biostudies-literature
Project description:Quantitative predictions of the physical state of the Earth's subsurface are routinely based on numerical solutions of complex coupled partial differential equations together with estimates of the uncertainties in the material parameters. The resulting high-dimensional problems are computationally prohibitive even for state-of-the-art solver solutions. In this study, we introduce a hybrid physics-based machine learning technique, the non-intrusive reduced basis method, to construct reliable, scalable, and interpretable surrogate models. Our approach, to combine physical process models with data-driven machine learning techniques, allows us to overcome limitations specific to each individual component, and it enables us to carry out probabilistic analyses, such as global sensitivity studies and uncertainty quantification for real-case non-linearly coupled physical problems. It additionally provides orders of magnitude computational gain, while maintaining an accuracy higher than measurement errors. Although in this study we use a thermo-hydro-mechanical reservoir application to illustrate these features, all the theory described is equally valid and applicable to a wider range of geoscientific applications.
| S-EPMC9582207 | biostudies-literature
Project description:Single-pixel imaging (SPI) has the advantages of high-speed acquisition over a broad wavelength range and system compactness. Deep learning (DL) is a powerful tool that can achieve higher image quality than conventional reconstruction approaches. Here, we propose a Bayesian convolutional neural network (BCNN) to approximate the uncertainty of the DL predictions in SPI. Each pixel in the predicted image represents a probability distribution rather than an image intensity value, indicating the uncertainty of the prediction. We show that the BCNN uncertainty predictions are correlated to the reconstruction errors. When the BCNN is trained and used in practical applications where the ground truths are unknown, the level of the predicted uncertainty can help to determine whether system, data, or network adjustments are needed. Overall, the proposed BCNN can provide a reliable tool to indicate the confidence levels of DL predictions as well as the quality of the model and dataset for many applications of SPI.
| S-EPMC10923550 | biostudies-literature
Project description:Even though ghost imaging (GI), an unconventional imaging method, has received increased attention by researchers during the last decades, imaging speed is still not satisfactory. Once the data-acquisition method and the system parameters are determined, only the processing method has the potential to accelerate image-processing significantly. However, both the basic correlation method and the compressed sensing algorithm, which are often used for ghost imaging, have their own problems. To overcome these challenges, a novel deep learning ghost imaging method is proposed in this paper. We modified the convolutional neural network that is commonly used in deep learning to fit the characteristics of ghost imaging. This modified network can be referred to as ghost imaging convolutional neural network. Our simulations and experiments confirm that, using this new method, a target image can be obtained faster and more accurate at low sampling rate compared with conventional GI method.
| S-EPMC5915577 | biostudies-literature
Project description:ObjectiveTo develop and validate a deep learning algorithm that could automate the annotation of scleral spur (SS) and segmentation of anterior chamber (AC) structures for measurements of AC, iris, and angle width parameters in anterior segment OCT (ASOCT) scans.DesignCross-sectional study.SubjectsData from 2 population-based studies (i.e., the Singapore Chinese Eye Study and Singapore Malay Eye Study) and 1 clinical study on angle-closure disease were included in algorithm development. A separate clinical study on angle-closure disease was used for external validation.MethodImage contrast of ASOCT scans were first enhanced with CycleGAN. We utilized a heat map regression approach with coarse-to-fine framework for SS annotation. Then, an ensemble network of U-Net, full resolution residual network, and full resolution U-Net was used for structure segmentation. Measurements obtained from predicted SSs and structure segmentation were measured and compared with measurements obtained from manual SS annotation and structure segmentation (i.e., ground truth).Main outcome measuresWe measured Euclidean distance and intraclass correlation coefficients (ICC) to evaluate SS annotation and Dice similarity coefficient for structure segmentation. The ICC, Bland-Altman plot, and repeatability coefficient were used to evaluate agreement and precision of measurements.ResultsFor SS annotation, our algorithm achieved a Euclidean distance of 124.7 μm, ICC ≥ 0.95, and a 3.3% error rate. For structure segmentation, we obtained Dice similarity coefficient ≥ 0.91 for cornea, iris, and AC segmentation. For angle width measurements, ≥ 95% of data points were within the 95% limits-of-agreement in Bland-Altman plot with insignificant systematic bias (all P > 0.12). The ICC ranged from 0.71-0.87 for angle width measurements, 0.54 for IT750, 0.83-0.85 for other iris measurements, and 0.89-0.99 for AC measurements. Using the same SS coordinates from a human expert, measurements obtained from our algorithm were generally less variable than measurements obtained from a semiautomated angle assessment program.ConclusionWe developed a deep learning algorithm that could automate SS annotation and structure segmentation in ASOCT scans like human experts, in both open-angle and angle-closure eyes. This algorithm reduces the time needed and subjectivity in obtaining ASOCT measurements.Financial disclosuresThe author(s) have no proprietary or commercial interest in any materials discussed in this article.
| S-EPMC10587633 | biostudies-literature
Project description:PurposeTo develop a rapid 2D MR fingerprinting technique with a submillimeter in-plane resolution using a deep learning-based tissue quantification approach.MethodsA rapid and high-resolution MR fingerprinting technique was developed for brain T1 and T2 quantification. The 2D acquisition was performed using a FISP-based MR fingerprinting sequence and a spiral trajectory with 0.8-mm in-plane resolution. A deep learning-based method was used to replace the standard template matching method for improved tissue characterization. A novel network architecture (i.e., residual channel attention U-Net) was proposed to improve high-resolution details in the estimated tissue maps. Quantitative brain imaging was performed with 5 adults and 2 pediatric subjects, and the performance of the proposed approach was compared with several existing methods in the literature.ResultsIn vivo measurements with both adult and pediatric subjects show that high-quality T1 and T2 mapping with 0.8-mm in-plane resolution can be achieved in 7.5 seconds per slice. The proposed deep learning method outperformed existing algorithms in tissue quantification with improved accuracy. Compared with the standard U-Net, high-resolution details in brain tissues were better preserved by the proposed residual channel attention U-Net. Experiments on pediatric subjects further demonstrated the potential of the proposed technique for fast pediatric neuroimaging. Alongside reduced data acquisition time, a 5-fold acceleration in tissue property mapping was also achieved with the proposed method.ConclusionA rapid and high-resolution MR fingerprinting technique was developed, which enables high-quality T1 and T2 quantification with 0.8-mm in-plane resolution in 7.5 seconds per slice.
| S-EPMC8210473 | biostudies-literature
Project description:Equation learning aims to infer differential equation models from data. While a number of studies have shown that differential equation models can be successfully identified when the data are sufficiently detailed and corrupted with relatively small amounts of noise, the relationship between observation noise and uncertainty in the learned differential equation models remains unexplored. We demonstrate that for noisy datasets there exists great variation in both the structure of the learned differential equation models and their parameter values. We explore how to exploit multiple datasets to quantify uncertainty in the learned models, and at the same time draw mechanistic conclusions about the target differential equations. We showcase our results using simulation data from a relatively straightforward agent-based model (ABM) which has a well-characterized partial differential equation description that provides highly accurate predictions of averaged ABM behaviours in relevant regions of parameter space. Our approach combines equation learning methods with Bayesian inference approaches so that a quantification of uncertainty can be given by the posterior parameter distribution of the learned model.
| S-EPMC8548080 | biostudies-literature