Identifying individual tissues, so-called tissue segmentation, in diabetic foot ulcer (DFU) images is a challenging task and little work has been published, largely due to the limited availability of a clinical image dataset. To address this gap, we have created a DFUTissue dataset for the research community to evaluate wound tissue segmentation algorithms. The dataset contains 110 images with tissues labeled by wound experts and 600 unlabeled images. Additionally, we conducted a pilot study on segmenting wound characteristics including fibrin, granulation, and callus using deep learning. Due to the limited amount of annotated data, our framework consists of both supervised learning (SL) and semi-supervised learning (SSL) phases. In the SL phase, we propose a hybrid model featuring a Mix Transformer (MiT-b3) in the encoder and a CNN in the decoder, enhanced by the integration of a parallel spatial and channel squeeze-and-excitation (P-scSE) module known for its efficacy in improving boundary accuracy. The SSL phase employs a pseudo-labeling-based approach, iteratively identifying and incorporating valuable unlabeled images to enhance overall segmentation performance. Comparative evaluations with state-of-the-art methods are conducted for both SL and SSL phases. The SL achieves a Dice Similarity Coefficient (DSC) of 84.89%, which has been improved to 87.64% in the SSL phase. Furthermore, the results are benchmarked against two widely used SSL approaches: Generative Adversarial Networks and Cross-Consistency Training. Additionally, our hybrid model outperforms the state-of-the-art methods with a 92.99% DSC in performing binary segmentation of DFU wound areas when tested on the Chronic Wound dataset. Codes and data are available at this https URL.

Electronic Health Records (EHRs) are digital records of patient information, often containing unstructured clinical text. Named Entity Recognition (NER) is essential in EHRs for extracting key medical entities like problems, tests, and treatments to support downstream clinical applications. This paper explores prompt-based medical entity recognition using large language models (LLMs), specifically GPT-4o and DeepSeek-R1, guided by various prompt engineering techniques, including zero-shot, few-shot, and an ensemble approach. Among all strategies, GPT-4o with prompt ensemble achieved the highest classification performance with an F1-score of 0.95 and recall of 0.98, outperforming DeepSeek-R1 on the task. The ensemble method improved reliability by aggregating outputs through embedding-based similarity and majority voting.

The powerful jets of blazars have been historically considered as likely sites of high-energy cosmic-ray acceleration. However, particulars of the launched jet and the locations of leptonic and hadronic jet loading remain unclear. In the case when leptonic and hadronic particle injection occur jointly, a temporal correlation between synchrotron radiation and neutrino production is expected. We use a first catalog of millimeter (mm) wavelength blazar light curves from the Atacama Cosmology Telescope for a time-dependent correlation with twelve years of muon neutrino events from the IceCube South Pole Neutrino Observatory. Such mm emission is known to trace activity of the bright jet base, which is often self-absorbed at lower frequencies and potentially gamma-ray opaque. We perform an analysis of the population, as well as analyses of individual, selected sources. We do not observe a significant signal from the stacked population. TXS 0506+056 is found as the most significant, individual source, though this detection is not globally significant in our analysis of selected AGN. Our results suggest that the majority of mm-bright blazars are neutrino dim. In general, it is possible that many blazars have lighter, leptonic jets, or that only selected blazars provide exceptional conditions for neutrino production.

The IceCube Neutrino Observatory has observed extragalactic astrophysical neutrinos with an apparently isotropic distribution. Only a small fraction of the observed astrophysical neutrinos can be explained by known sources. Neutrino production is thought to occur in energetic environments that are ultimately powered by the gravitational collapse of dense regions of the large-scale mass distribution in the universe. Whatever their identity, neutrino sources likely trace this large-scale mass distribution. The clustering of neutrinos with a tracer of the large-scale structure may provide insight into the distribution of neutrino sources with respect to redshift and the identity of neutrino sources. We implement a two-point angular cross-correlation of the Northern sky track events with an infrared galaxy catalog derived from WISE and 2MASS source catalogs that trace the nearby large-scale structure. No statistically significant correlation is found between the neutrinos and this infrared galaxy catalog. We find that < ~54% of the diffuse muon neutrino flux can be attributed to sources correlated with the galaxy catalog with 90% confidence. Additionally, when assuming that the neutrino source comoving density evolves following a power-law in redshift, $dN_s/dV \propto (1+z)^{k}$, we find that sources with negative evolution, in particular k < -1.75, are disfavored at the 90% confidence level

Recent efforts on solving inverse problems in imaging via deep neural networks use architectures inspired by a fixed number of iterations of an optimization method. The number of iterations is typically quite small due to difficulties in training networks corresponding to more iterations; the resulting solvers cannot be run for more iterations at test time without incurring significant errors. This paper describes an alternative approach corresponding to an infinite number of iterations, yielding a consistent improvement in reconstruction accuracy above state-of-the-art alternatives and where the computational budget can be selected at test time to optimize context-dependent trade-offs between accuracy and computation. The proposed approach leverages ideas from Deep Equilibrium Models, where the fixed-point iteration is constructed to incorporate a known forward model and insights from classical optimization-based reconstruction methods.

Scientists across disciplines often use data from the internet to conduct research, generating valuable insights about human behavior. However, as generative AI relying on massive text corpora becomes increasingly valuable, platforms have greatly restricted access to data through official channels. As a result, researchers will likely engage in more web scraping to collect data, introducing new challenges and concerns for researchers. This paper proposes a comprehensive framework for web scraping in social science research for U.S.-based researchers, examining the legal, ethical, institutional, and scientific factors that researchers should consider when scraping the web. We present an overview of the current regulatory environment impacting when and how researchers can access, collect, store, and share data via scraping. We then provide researchers with recommendations to conduct scraping in a scientifically legitimate and ethical manner. We aim to equip researchers with the relevant information to mitigate risks and maximize the impact of their research amidst this evolving data access landscape.

Proper segmentation of organs-at-risk is important for radiation therapy, surgical planning, and diagnostic decision-making in medical image analysis. While deep learning-based segmentation architectures have made significant progress, they often fail to balance segmentation accuracy with computational efficiency. Most of the current state-of-the-art methods either prioritize performance at the cost of high computational complexity or compromise accuracy for efficiency. This paper addresses this gap by introducing an efficient dual-line decoder segmentation network (EDLDNet). The proposed method features a noisy decoder, which learns to incorporate structured perturbation at training time for better model robustness, yet at inference time only the noise-free decoder is executed, leading to lower computational cost. Multi-Scale convolutional Attention Modules (MSCAMs), Attention Gates (AGs), and Up-Convolution Blocks (UCBs) are further utilized to optimize feature representation and boost segmentation performance. By leveraging multi-scale segmentation masks from both decoders, we also utilize a mutation-based loss function to enhance the model's generalization. Our approach outperforms SOTA segmentation architectures on four publicly available medical imaging datasets. EDLDNet achieves SOTA performance with an 84.00% Dice score on the Synapse dataset, surpassing baseline model like UNet by 13.89% in Dice score while significantly reducing Multiply-Accumulate Operations (MACs) by 89.7%. Compared to recent approaches like EMCAD, our EDLDNet not only achieves higher Dice score but also maintains comparable computational efficiency. The outstanding performance across diverse datasets establishes EDLDNet's strong generalization, computational efficiency, and robustness. The source code, pre-processed data, and pre-trained weights will be available at this https URL .

Neural networks often operate in the overparameterized regime, in which there are far more parameters than training samples, allowing the training data to be fit perfectly. That is, training the network effectively learns an interpolating function, and properties of the interpolant affect predictions the network will make on new samples. This manuscript explores how properties of such functions learned by neural networks of depth greater than two layers. Our framework considers a family of networks of varying depths that all have the same capacity but different representation costs. The representation cost of a function induced by a neural network architecture is the minimum sum of squared weights needed for the network to represent the function; it reflects the function space bias associated with the architecture. Our results show that adding additional linear layers to the input side of a shallow ReLU network yields a representation cost favoring functions with low mixed variation -- that is, it has limited variation in directions orthogonal to a low-dimensional subspace and can be well approximated by a single- or multi-index model. This bias occurs because minimizing the sum of squared weights of the linear layers is equivalent to minimizing a low-rank promoting Schatten quasi-norm of a single "virtual" weight matrix. Our experiments confirm this behavior in standard network training regimes. They additionally show that linear layers can improve generalization and the learned network is well-aligned with the true latent low-dimensional linear subspace when data is generated using a multi-index model.

We present a search for the diffuse extremely-high-energy neutrino flux using $12.6$ years of IceCube data. The nonobservation of neutrinos with energies well above $10 \, \mathrm{PeV}$ constrains the all-flavor neutrino flux at $10^{18} \, \mathrm{eV}$ to a level of $E^2 \Phi_{\nu_e + \nu_\mu + \nu_\tau} \simeq 10^{-8} \, \mathrm{GeV} \, \mathrm{cm}^{-2} \, \mathrm{s}^{-1} \, \mathrm{sr}^{-1}$, the most stringent limit to date. Using these data, we constrain the proton fraction of ultra-high-energy cosmic rays (UHECRs) above $\simeq 30 \, \mathrm{EeV}$ to be $\lesssim 70\,$% (at $90\,$% CL) if the cosmological evolution of the sources is comparable to or stronger than the star formation rate. This is the first result to disfavor the ``proton-only" hypothesis for UHECRs in this evolution regime using neutrino data. This result complements direct air-shower measurements by being insensitive to uncertainties associated with hadronic interaction models. We also evaluate the tension between IceCube's nonobservation and the $\sim 200 \, \mathrm{PeV}$ KM3NeT neutrino candidate (KM3-230213A), finding it to be $\sim 2.9 \sigma$ based on a joint-livetime fit between neutrino datasets.

Inspired by their success in solving challenging inverse problems in computer vision, implicit neural representations (INRs) have been recently proposed for reconstruction in low-dose/sparse-view X-ray computed tomography (CT). An INR represents a CT image as a small-scale neural network that takes spatial coordinates as inputs and outputs attenuation values. Fitting an INR to sinogram data is similar to classical model-based iterative reconstruction methods. However, training INRs with losses and gradient-based algorithms can be prohibitively slow, taking many thousands of iterations to converge. This paper investigates strategies to accelerate the optimization of INRs for CT reconstruction. In particular, we propose two approaches: (1) using a modified loss function with improved conditioning, and (2) an algorithm based on the alternating direction method of multipliers. We illustrate that both of these approaches significantly accelerate INR-based reconstruction of a synthetic breast CT phantom in a sparse-view setting.

Neutrino oscillations at the highest energies and longest baselines provide a natural quantum interferometer with which to study the structure of spacetime and test the fundamental principles of quantum mechanics. If the metric of spacetime has a quantum mechanical description, there is a generic expectation that its fluctuations at the Planck scale would introduce non-unitary effects that are inconsistent with the standard unitary time evolution of quantum mechanics. Neutrinos interacting with such fluctuations would lose their quantum coherence, deviating from the expected oscillatory flavor composition at long distances and high energies. The IceCube South Pole Neutrino Observatory is a billion-ton neutrino telescope situated in the deep ice of the Antarctic glacier. Atmospheric neutrinos detected by IceCube in the energy range 0.5--10 TeV have been used to test for coherence loss in neutrino propagation. No evidence of anomalous neutrino decoherence was observed, leading to the strongest experimental limits on neutrino-quantum gravity interactions to date, significantly surpassing expectations from natural Planck-scale models. The resulting constraint on the effective decoherence strength parameter within an energy-independent decoherence model is $\Gamma_0\leq 1.17\times10^{-15}$~eV, improving upon past limits by a factor of 30. For decoherence effects scaling as E$^2$, limits are advanced by more than six orders of magnitude beyond past measurements.

Trusted Execution Environments, such as Intel SGX, use hardware supports to ensure the confidentiality and integrity of applications against a compromised cloud system. However, side channels like access patterns remain for adversaries to exploit and obtain sensitive information. Common approaches use oblivious programs or primitives, such as ORAM, to make access patterns oblivious to input data, which are challenging to develop. This demonstration shows a prototype SGX-MR-Prot for efficiently protecting access patterns of SGX-based data-intensive applications and minimizing developers' efforts. SGX-MR-Prot uses the MapReduce framework to regulate application dataflows to reduce the cost of access-pattern protection and hide the data oblivious details from SGX developers. This demonstration will allow users to intuitively understand the unique contributions of the framework-based protection approach via interactive exploration and visualization.

Deep neural networks have been applied successfully to a wide variety of inverse problems arising in computational imaging. These networks are typically trained using a forward model that describes the measurement process to be inverted, which is often incorporated directly into the network itself. However, these approaches are sensitive to changes in the forward model: if at test time the forward model varies (even slightly) from the one the network was trained for, the reconstruction performance can degrade substantially. Given a network trained to solve an initial inverse problem with a known forward model, we propose two novel procedures that adapt the network to a change in the forward model, even without full knowledge of the change. Our approaches do not require access to more labeled data (i.e., ground truth images). We show these simple model adaptation approaches achieve empirical success in a variety of inverse problems, including deblurring, super-resolution, and undersampled image reconstruction in magnetic resonance imaging.

We study depth separation in infinite-width neural networks, where complexity is controlled by the overall squared $\ell_2$-norm of the weights (sum of squares of all weights in the network). Whereas previous depth separation results focused on separation in terms of width, such results do not give insight into whether depth determines if it is possible to learn a network that generalizes well even when the network width is unbounded. Here, we study separation in terms of the sample complexity required for learnability. Specifically, we show that there are functions that are learnable with sample complexity polynomial in the input dimension by norm-controlled depth-3 ReLU networks, yet are not learnable with sub-exponential sample complexity by norm-controlled depth-2 ReLU networks (with any value for the norm). We also show that a similar statement in the reverse direction is not possible: any function learnable with polynomial sample complexity by a norm-controlled depth-2 ReLU network with infinite width is also learnable with polynomial sample complexity by a norm-controlled depth-3 ReLU network.

We explore how the fundamental problems in quantum molecular dynamics can be modelled using classical simulators (emulators) of quantum computers and the actual quantum hardware available to us today. The list of problems we tackle includes propagation of a free wave packet, vibration of a harmonic oscillator, and tunneling through a barrier. Each of these problems starts with the initial wave packet setup. Although Qiskit provides a general method for initializing wavefunctions, in most cases it generates deep quantum circuits. While these circuits perform well on noiseless simulators, they suffer from excessive noise on quantum hardware. To overcome this issue, we designed a shallower quantum circuit for preparing a Gaussian-like initial wave packet, which improves the performance on real hardware. Next, quantum circuits are implemented to apply the kinetic and potential energy operators for the evolution of a wavefunction over time. The results of our modelling on classical emulators of quantum hardware agree perfectly with the results obtained using the traditional (classical) methods. This serves as a benchmark and demonstrates that the quantum algorithms and Qiskit codes we developed are accurate. However, the results obtained on the actual quantum hardware available today, such as IBM's superconducting qubits and IonQ's trapped ions, indicate large discrepancies due to hardware limitations. This work highlights both the potential and challenges of using quantum computers to solve fundamental quantum molecular dynamics problems.

Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural network taking spatial coordinates as inputs. However, unlike traditional pixel representations, little is known about the sample complexity of estimating images using INRs in the context of linear inverse problems. Towards this end, we study the sampling requirements for recovery of a continuous domain image from its low-pass Fourier coefficients by fitting a single hidden-layer INR with ReLU activation and a Fourier features layer using a generalized form of weight decay regularization. Our key insight is to relate minimizers of this non-convex parameter space optimization problem to minimizers of a convex penalty defined over an infinite-dimensional space of measures. We identify a sufficient number of samples for which an image realized by a width-1 INR is exactly recoverable by solving the INR training problem, and give a conjecture for the general width-$W$ case. To validate our theory, we empirically assess the probability of achieving exact recovery of images realized by low-width single hidden-layer INRs, and illustrate the performance of INR on super-resolution recovery of more realistic continuous domain phantom images.

Quantum Computing (QC) refers to an emerging paradigm that inherits and builds with the concepts and phenomena of Quantum Mechanic (QM) with the significant potential to unlock a remarkable opportunity to solve complex and computationally intractable problems that scientists could not tackle previously. In recent years, tremendous efforts and progress in QC mark a significant milestone in solving real-world problems much more efficiently than classical computing technology. While considerable progress is being made to move quantum computing in recent years, significant research efforts need to be devoted to move this domain from an idea to a working paradigm. In this paper, we conduct a systematic survey and categorize papers, tools, frameworks, platforms that facilitate quantum computing and analyze them from an application and Quantum Computing perspective. We present quantum Computing Layers, Characteristics of Quantum Computer platforms, Circuit Simulator, Open-source Tools Cirq, TensorFlow Quantum, ProjectQ that allow implementing quantum programs in Python using a powerful and intuitive syntax. Following that, we discuss the current essence, identify open challenges and provide future research direction. We conclude that scores of frameworks, tools and platforms are emerged in the past few years, improvement of currently available facilities would exploit the research activities in the quantum research community.