An official website of the United States government
ABSTRACT We perform cosmological zoom-in simulations of 19 relaxed cluster-mass haloes with the inclusion of adiabatic gas in the cold dark matter (CDM) and self-interacting dark matter (SIDM) models. These clusters are selected as dynamically relaxed clusters from a parent simulation with $$M_{\rm 200} \simeq (1\!-\!3)\times 10^{15}{\, \rm M_\odot }$$. Both the dark matter and the intracluster gas distributions in SIDM appear more spherical than their CDM counterparts. Mock X-ray images are generated based on the simulations and are compared to the real X-ray images of 84 relaxed clusters selected from the Chandra and ROSAT archives. We perform ellipse fitting for the isophotes of mock and real X-ray images and obtain the ellipticities at cluster-centric radii of $$r\simeq 0.1\!-\!0.2R_{\rm 200}$$. The X-ray isophotes in SIDM models with increasing cross-sections are rounder than their CDM counterparts, which manifests as a systematic shift in the distribution function of ellipticities. Unexpectedly, the X-ray morphology of the observed non-cool-core clusters agrees better with SIDM models with cross-section $$(\sigma /m)= 0.5\!-\!1\, {\rm cm}^2\, {\rm g}^{-1}$$ than CDM and SIDM with $$(\sigma /m)=0.1\, {\rm cm}^2\, {\rm g}^{-1}$$. Our statistical analysis indicates that the latter two models are disfavoured at the $$68{{\ \rm per\ cent}}$$ confidence level (as conservative estimates). This conclusion is not altered by shifting the radial range of measurements or applying a temperature selection criterion. However, the primary uncertainty originates from the lack of baryonic physics in the adiabatic model, such as cooling, star formation and feedback effects, which still have the potential to reconcile CDM simulations with observations.
more »
« less
This content will become publicly available on June 1, 2026
Uncertainty Estimation for Dual View X-ray Mammographic Image Registration Using Deep Ensembles
Abstract Techniques are developed for generating uncertainty estimates for convolutional neural network (CNN)-based methods for registering the locations of lesions between the craniocaudal (CC) and mediolateral oblique (MLO) mammographic X-ray image views. Multi-view lesion correspondence is an important task that clinicians perform for characterizing lesions during routine mammographic exams. Automated registration tools can aid in this task, yet if the tools also provide confidence estimates, they can be of greater value to clinicians, especially in cases involving dense tissue where lesions may be difficult to see. A set of deep ensemble-based techniques, which leverage a negative log-likelihood (NLL)-based cost function, are implemented for estimating uncertainties. The ensemble architectures involve significant modifications to an existing CNN dual-view lesion registration algorithm. Three architectural designs are evaluated, and different ensemble sizes are compared using various performance metrics. The techniques are tested on synthetic X-ray data, real 2D X-ray data, and slices from real 3D X-ray data. The ensembles generate covariance-based uncertainty ellipses that are correlated with registration accuracy, such that the ellipse sizes can give a clinician an indication of confidence in the mapping between the CC and MLO views. The results also show that the ellipse sizes can aid in improving computer-aided detection (CAD) results by matching CC/MLO lesion detects and reducing false alarms from both views, adding to clinical utility. The uncertainty estimation techniques show promise as a means for aiding clinicians in confidently establishing multi-view lesion correspondence, thereby improving diagnostic capability.
more »
« less
- Award ID(s):
- 2242412
- PAR ID:
- 10633144
- Publisher / Repository:
- Springer
- Date Published:
- Journal Name:
- Journal of Imaging Informatics in Medicine
- Volume:
- 38
- Issue:
- 3
- ISSN:
- 2948-2933
- Page Range / eLocation ID:
- 1829 to 1845
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Anthropogenic global change is occurring at alarming rates, leading to increased urgency in the ability to monitor wildlife health in real time. Monitoring sentinel marine species, such as bottlenose dolphins, is particularly important due to extensive anthropogenic modifications to their habitats. The most common non-invasive method of monitoring cetacean health is documentation of skin lesions, often associated with poor health or disease, but the current methodology is inefficient and imprecise. Recent advancements in technology, such as machine learning, can provide researchers with more efficient ecological monitoring methods to address health questions at both the population and the individual levels. Our work develops a machine learning model to classify skin lesions on the understudied Tamanend's bottlenose dolphins (Tursiops erebennus) of the Chesapeake Bay, using manual estimates of lesion presence in photographs. We assess the model's performance and find that our best model performs with a high mean average precision (65.6 %–86.8 %), and generally increased accuracy with improved photo quality. We also demonstrate the model's ability to address ecological questions across scales by generating model-based estimates of lesion prevalence and testing the effect of gregariousness on health status. At the population level, our model accurately estimates a prevalence of 72.1 % spot and 27.3 % fringe ring lesions, with a slight underprediction compared to manual estimates (82.2 % and 32.1 %). On the other hand, we find that individual-level analyses from the model predictions may be more sensitive to data quality, and thus, some individual scale questions may not be feasible to address if data quality is inconsistent. Manually, we do find that lesion presence in individuals suggests a positive relationship between lesion presence and gregariousness. This work demonstrates that object detection models on photographic data are reasonably successful, highly efficient, and provide initial estimates on the health status of understudied populations of bottlenose dolphins.more » « less
-
Abstract Background Low specificity in current breast imaging modalities leads to increased unnecessary follow-ups and biopsies. The purpose of this study is to evaluate the efficacy of combining the quantitative parameters of high-definition microvasculature imaging (HDMI) and 2D shear wave elastography (SWE) with clinical factors (lesion depth and age) for improving breast lesion differentiation. Methods In this prospective study, from June 2016 through April 2021, patients with breast lesions identified on diagnostic ultrasound and recommended for core needle biopsy were recruited. HDMI and SWE were conducted prior to biopsies. Two new HDMI parameters, Murray’s deviation and bifurcation angle, and a new SWE parameter, mass characteristic frequency, were included for quantitative analysis. Lesion malignancy prediction models based on HDMI only, SWE only, the combination of HDMI and SWE, and the combination of HDMI, SWE and clinical factors were trained via elastic net logistic regression with 70% (360/514) randomly selected data and validated with the remaining 30% (154/514) data. Prediction performances in the validation test set were compared across models with respect to area under the ROC curve as well as sensitivity and specificity based on optimized threshold selection. Results A total of 508 participants (mean age, 54 years ± 15), including 507 female participants and 1 male participant, with 514 suspicious breast lesions (range, 4–72 mm, median size, 13 mm) were included. Of the lesions, 204 were malignant. The SWE-HDMI prediction model, combining quantitative parameters from SWE and HDMI, with AUC of 0.973 (95% CI 0.95–0.99), was significantly higher than the result predicted with the SWE model or HDMI model alone. With an optimal cutoff of 0.25 for the malignancy probability, the sensitivity and specificity were 95.5% and 89.7%, respectively. The specificity was further improved with the addition of clinical factors. The corresponding model defined as the SWE-HDMI-C prediction model had an AUC of 0.981 (95% CI 0.96–1.00). Conclusions The SWE-HDMI-C detection model, a combination of SWE estimates, HDMI quantitative biomarkers and clinical factors, greatly improved the accuracy in breast lesion characterization.more » « less
-
Multi-View Clustering (MVC) aims to find the cluster structure shared by multiple views of a particular dataset. Existing MVC methods mainly integrate the raw data from different views, while ignoring the high-level information. Thus, their performance may degrade due to the conflict between heterogeneous features and the noises existing in each individual view. To overcome this problem, we propose a novel Multi-View Ensemble Clustering (MVEC) framework to solve MVC in an Ensemble Clustering (EC) way, which generates Basic Partitions (BPs) for each view individually and seeks for a consensus partition among all the BPs. By this means, we naturally leverage the complementary information of multi-view data in the same partition space. Instead of directly fusing BPs, we employ the low-rank and sparse decomposition to explicitly consider the connection between different views and detect the noises in each view. Moreover, the spectral ensemble clustering task is also involved by our framework with a carefully designed constraint, making MVEC a unified optimization framework to achieve the final consensus partition. Experimental results on six real-world datasets show the efficacy of our approach compared with both MVC and EC methods.more » « less
-
null (Ed.)Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Qlearning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration. By enforcing the diversity between agents using Bootstrap with random initialization, we show that these different ideas are largely orthogonal and can be fruitfully integrated, together further improving the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments.more » « less
