Artificial Intelligence (AI) is transforming healthcare by enhancing diagnostics, personalizing treatment planning, and streamlining patient care. Yet, its adoption is hindered by persistent ethical challenges, including algorithmic bias, lack of transparency, privacy risks, and unclear accountability. Existing international frameworks articulate high-level principles but seldom provide operational guidance for clinical deployment. We bridge this gap by synthesizing trust dimensions for healthcare, with measurable metrics for fairness, explainability, privacy, accountability, and robustness, and proposing the Healthcare AI Trustworthiness Index (HAITI), a composite, context-aware readiness score with explicit normalization, weighting, and uncertainty reporting. We outline a development–deployment–governance blueprint and present two case studies (diagnostic bias mitigation; privacy-preserving federated learning). Together, these contributions translate ethical principles into measurable practices that can foster trust, improve equity, and accelerate responsible AI integration in clinical settings.

With increasing computational power, scientists often employ high-fidelity simulations to study complex scientific phenomena. However, these simulations remain slow and costly in terms of computation and storage, prompting the use of faster low-fidelity alternatives. Yet, the distribution gap between low- and high-fidelity data, due to missing fine-scale details and simplified physics, hampers accurate scientific understanding. To overcome these challenges, we propose a neural operator-based framework for multi-fidelity prediction on unstructured data. Our framework leverages a graph neural operator to effectively map low-fidelity data to the high-fidelity counterparts. It further incorporates a spectral-based module that captures fine-scale details, enhancing the reconstruction of high-fidelity fields. Extensive experiments across diverse datasets demonstrate that our method consistently surpasses strong baselines, including state-of-the-art neural operators and learning methods for unstructured data, highlighting its robustness and effectiveness in bridging fidelity gaps.

With the growing computational power available for high-resolution ensemble simulations in scientific fields such as cosmology and oceanology, storage and computational demands present significant challenges. Current surrogate models fall short in the flexibility of point- or region-based predictions as the entire field reconstruction is required for each parameter setting, hence hindering the efficiency of parameter space exploration. Limitations exist in capturing physical attribute distributions and pinpointing optimal parameter configurations. In this work, we propose Explorable INR, a novel implicit neural representation-based surrogate model, designed to facilitate exploration and allow point-based spatial queries without computing full-scale field data. In addition, to further address computational bottlenecks of spatial exploration, we utilize probabilistic affine forms (PAFs) for uncertainty propagation through Explorable INR to obtain statistical summaries, facilitating various ensemble analysis and visualization tasks that are expensive with existing models. Furthermore, we reformulate the parameter exploration problem as optimization tasks using gradient descent and KL divergence minimization that ensures scalability. We demonstrate that the Explorable INR with the proposed approach for spatial and parameter exploration can significantly reduce computation and memory costs while providing effective ensemble analysis.

Sleep disorders have a major impact on both lifestyle and health. Effective sleep disorder prediction from lifestyle and physiological data can provide essential details for early intervention. This research utilizes three deep time series models and facilitates them with explainability approaches for sleep disorder prediction. Specifically, our approach adopts Temporal Convolutional Networks (TCN), Long Short-Term Memory (LSTM) for time series data analysis, and Temporal Fusion Transformer model (TFT). Meanwhile, the temporal attention mechanism and counterfactual explanation with SHapley Additive exPlanations (SHAP) approach are employed to ensure dependable, accurate, and interpretable predictions. Finally, using a large dataset of sleep health measures, our evaluation demonstrates the effect of our method in predicting sleep disorders.

Reliably reconstructing physical fields from sparse sensor data is a challenge that frequenty arises in many scientific domains. In practice, the process generating the data is often not known to sufficient accuracy. Therefore, there is a growing interest in the deep neural network route to the problem. In this work, we present a novel approach that learns a continuous representation of the field using implicit neural representations (INR). Specifically, after factorizing spatiotemporal variability into spatial and temporal components using the technique of separation of variables, the method learns relevant basis functions from sparsely sampled irregular data points to thus develop a continuous representation of the data. In experimental evaluations, the proposed model outperforms recent INR methods, offering superior reconstruction quality on simulation data from a state of the art climate model and on a second dataset that comprises of ultra-high resolution satellite-based sea surface temperature field. [Website for the Project: Both data and code are accessible.](https://xihaier.github.io/ICLR-2024-MMGN/)

In volume visualization transfer functions are widely used for mapping voxel properties to color and opacity. Typically, volume density data are scalars which require simple 1D transfer functions to achieve this mapping. If the volume densities are vectors of three channels, one can straightforwardly map each channel to either red, green or blue, which requires a trivial extension of the 1D transfer function editor. We devise a new method that applies to volume data with more than three channels. These types of data often arise in scientific scanning applications, where the data are separated into spectral bands or chemical elements. Our method expands on prior work in which a multivariate information display, RadViz, was fused with a radial color map, in order to visualize multi-band 2D images. In this work, we extend this joint interface to blended volume rendering. The information display allows users to recognize the presence and value distribution of the multivariate voxels and the joint volume rendering display visualizes their spatial distribution. We design a set of operators and lenses that allow users to interactively control the mapping of the multivariate voxels to opacity and color. This enables users to isolate or emphasize volumetric structures with desired multivariate properties. Furthermore, it turns out that our method also enables more insightful displays even for RGB data. We demonstrate our method with three datasets obtained from spectral electron microscopy, high energy X-ray scanning, and atmospheric science.

Abstract Visualizations have played a crucial role in helping quantum computing users explore quantum states in various quantum computing applications. Among them, Bloch Sphere is the widely‐used visualization for showing quantum states, which leverages angles to represent quantum amplitudes. However, it cannot support the visualization of quantum entanglement and superposition, the two essential properties of quantum computing. To address this issue, we propose VENUS, a novel visualization for quantum state representation. By explicitly correlating 2D geometric shapes based on the math foundation of quantum computing characteristics, VENUS effectively represents quantum amplitudes of both the single qubit and two qubits for quantum entanglement. Also, we use multiple coordinated semicircles to naturally encode probability distribution, making the quantum superposition intuitive to analyze. We conducted two well‐designed case studies and an in‐depth expert interview to evaluate the usefulness and effectiveness of VENUS. The result shows that VENUS can effectively facilitate the exploration of quantum states for the single qubit and two qubits.

Abstract Layer‐wise Relevance Propagation (LRP) is an emerging and widely‐used method for interpreting the prediction results of convolutional neural networks (CNN). LRP developers often select and employ different relevance backpropagation rules and parameters, to compute relevance scores on input images. However, there exists no obvious solution to define a “best” LRP model. A satisfied model is highly reliant on pertinent images and designers' goals. We develop a visual model designer, named as VisLRPDesigner, to overcome the challenges in the design and use of LRP models. Various LRP rules are unified into an integrated framework with an intuitive workflow of parameter setup. VisLRPDesigner thus allows users to interactively configure and compare LRP models. It also facilitates relevance‐based visual analysis with two important functions: relevance‐based pixel flipping and neuron ablation. Several use cases illustrate the benefits of VisLRPDesigner. The usability and limitation of the visual designer is evaluated by LRP users.

Existing interactive visualization tools for deep learning are mostly applied to the training, debugging, and refinement of neural network models working on natural images. However, visual analytics tools are lacking for the specific application of x-ray image classification with multiple structural attributes. In this paper, we present an interactive system for domain scientists to visually study the multiple attributes learning models applied to x-ray scattering images. It allows domain scientists to interactively explore this important type of scientific images in embedded spaces that are defined on the model prediction output, the actual labels, and the discovered feature space of neural networks. Users are allowed to flexibly select instance images, their clusters, and compare them regarding the specified visual representation of attributes. The exploration is guided by the manifestation of model performance related to mutual relationships among attributes, which often affect the learning accuracy and effectiveness. The system thus supports domain scientists to improve the training dataset and model, find questionable attributes labels, and identify outlier images or spurious data clusters. Case studies and scientists feedback demonstrate its functionalities and usefulness.

For real-world learning tasks (e.g., classification), graph-based models are commonly used to fuse the information distributed in diverse data sources, which can be heterogeneous, redundant, and incomplete. These models represent the relations in different datasets as pairwise links. However, these links cannot deal with high-order relations which connect multiple objects (e.g., in public health datasets, more than two patient groups admitted by the same hospital in 2014). In this article, we propose a visual analytics approach for the classification on heterogeneous datasets using the hypergraph model. The hypergraph is an extension to traditional graphs in which a hyperedge connects multiple vertices instead of just two. We model various high-order relations in heterogeneous datasets as hyperedges and fuse different datasets with a unified hypergraph structure. We use the hypergraph learning algorithm for predicting missing labels in the datasets. To allow users to inject their domain knowledge into the model-learning process, we augment the traditional learning algorithm in a number of ways. In addition, we also propose a set of visualizations which enable the user to construct the hypergraph structure and the parameters of the learning model interactively during the analysis. We demonstrate the capability of our approach via two real-world cases.

A wide variety of color schemes have been devised for mapping scalar data to color. We address the challenge of color-mapping multivariate data. While a number of methods can map low-dimensional data to color, for example, using bilinear or barycentric interpolation for two or three variables, these methods do not scale to higher data dimensions. Likewise, schemes that take a more artistic approach through color mixing and the like also face limits when it comes to the number of variables they can encode. Our approach does not have these limitations. It is data driven in that it determines a proper and consistent color map from first embedding the data samples into a circular interactive multivariate color mapping display (ICD) and then fusing this display with a convex (CIE HCL) color space. The variables (data attributes) are arranged in terms of their similarity and mapped to the ICD's boundary to control the embedding. Using this layout, the color of a multivariate data sample is then obtained via modified generalized barycentric coordinate interpolation of the map. The system we devised has facilities for contrast and feature enhancement, supports both regular and irregular grids, can deal with multi-field as well as multispectral data, and can produce heat maps, choropleth maps, and diagrams such as scatterplots.

Anomalous runtime behavior detection is one of the most important tasks for performance diagnosis in High Performance Computing (HPC). Most of the existing methods find anomalous executions based on the properties of individual functions, such as execution time. However, it is insufficient to identify abnormal behavior without taking into account the context of the executions, such as the invocations of children functions and the communications with other HPC nodes. We improve upon the existing anomaly detection approaches by utilizing the call stack structures of the executions, which record rich temporal and contextual information. With our call stack tree (CSTree) representation of the executions, we formulate the anomaly detection problem as finding anomalous tree structures in a call stack forest. The CSTrees are converted to vector representations using our proposed stack2vec embedding. Structural and temporal visualizations of CSTrees are provided to support users in the identification and verification of the anomalies during an active anomaly detection process. Three case studies of real-world HPC applications demonstrate the capabilities of our approach.

X-ray images obtained from synchrotron beamlines are large-scale, high-resolution and high-dynamic-range grayscale data encoding multiple complex properties of the measured materials. They are typically associated with a variety of metadata which increases their inherent complexity. There is a wealth of information embedded in these data but so far scientists lack modern exploration tools to unlock these hidden treasures. To bridge this gap, we propose MultiSciView , a multivariate scientific x-ray image visualization and exploration system for beamline-generated x-ray scattering data. Our system is composed of three complementary and coordinated interactive visualizations to enable a coordinated exploration across the images and their associated attribute and feature spaces . The first visualization features a multi-level scatterplot visualization dedicated for image exploration in attribute, image, and pixel scales. The second visualization is a histogram-based attribute cross filter by which users can extract desired subset patterns from data. The third one is an attribute projection visualization designed for capturing global attribute correlations. We demonstrate our framework by ways of a case study involving a real-world material scattering dataset. We show that our system can efficiently explore large-scale x-ray images, accurately identify preferred image patterns, anomalous images and erroneous experimental settings, and effectively advance the comprehension of material nanostructure properties.

We present the conformal magnifier, a novel interactive focus+context visualization technique that magnifies a region of interest (ROI) using conformal mapping. Our framework supports the arbitrary shape design of magnifiers for the user to enlarge the ROI while globally deforming the context region without any cropping. By using the mathematically well-defined conformal mapping theory and algorithm, the ROI is magnified with local shape preservation (angle distortion minimization), while the transition area between the focus and context regions is deformed smoothly and continuously. After the selection of a specified magnifier shape, our system can automatically magnify the ROI in real time with full resolution even for large volumetric data sets. These properties are important for many visualization applications, especially for the computer aided detection and diagnosis (CAD). Our framework is suitable for diverse applications, including the map visualization, and volumetric visualization. Experimental results demonstrate the effectiveness, robustness, and efficiency of our framework.

Practical volume visualization pipelines are never without compromises and errors. A delicate and often-studied component is the interpolation of off-grid samples, where aliasing can lead to misleading artifacts and blurring, potentially hiding fine details of critical importance. The verifiable visualization framework we describe aims to account for these errors directly in the volume generation stage, and we specifically target volumetric data obtained via computed tomography (CT) reconstruction. In this case the raw data are the X-ray projections obtained from the scanner and the volume data generation process is the CT algorithm. Our framework informs the CT reconstruction process of the specific filter intended for interpolation in the subsequent visualization process, and this in turn ensures an accurate interpolation there at a set tolerance. Here, we focus on fast trilinear interpolation in conjunction with an octree-type mixed resolution volume representation without T-junctions. Efficient rendering is achieved by a space-efficient and locality-optimized representation, which can straightforwardly exploit fast fixed-function pipelines on GPUs.