Search

Background. Breast cancer screening programs using mammography have led to significant mortality reduction in high-income countries. However, many low- and middle-income countries lack resources for mammographic screening. Handheld breast ultrasound (BUS) is a low-cost alternative but requires substantial training. Artificial intelligence (AI) enabled BUS may aid in both the detection (perception) and classification (interpretation) of breast cancer. Materials and Methods. This review (CRD42023493053) is reported in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) and SWiM (Synthesis Without Meta-analysis) guidelines. PubMed and Google Scholar were searched from January 1, 2016 to December 12, 2023. A meta-analysis was not attempted. Studies are grouped according to their AI task type, application time, and AI task. Study quality is assessed using the QUality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Results. Of 763 candidate studies, 314 total full texts were reviewed. 34 studies are included. The AI tasks of included studies are as follows: 1 frame selection, 6 detection, 11 segmentation, and 16 classification. In total, 5.7 million BUS images from over 185,000 patients were used for AI training or validation. A single study included a prospective testing set. 79% of studies were at high or unclear risk of bias. Conclusion. There has been encouraging development of AI for BUS. Despite studies demonstrating high performance across all identified tasks, the evidence supporting AI-enhanced BUS generally lacks robustness. High-quality model validation will be key to realizing the potential for AI-enhanced BUS in increasing access to screening in resource-limited environments.

We investigate the electronic structure of high-density layers of Sb dopants in a silicon host, so-called Si:Sb $\delta$-layers. We show that, in spite of the known challenges in producing highly confined Sb $\delta$-layers, sufficient confinement is created such that the lowest conduction band states ($\Gamma$ states, studied in depth in other silicon $\delta$-layers), become occupied and can be observed using angle-resolved photoemission spectroscopy. The electronic structure of the Si:Sb $\delta$-layers closely resembles that of Si:P systems, where the observed conduction band is near-parabolic and slightly anisotropic in the $\mathbf{k}_\parallel$ plane. The observed $\Gamma$ state extends ~ 1 nm in the out-of-plane direction, which is slightly wider than the 1/3 monolayer thick dopant distribution. This is caused by a small segregation of the dopant layer, which is nevertheless minimal when comparing with earlier published attempts. Our results serve to demonstrate that Sb is still a feasible dopant alternative for use in the semiconductor $\delta$-layer platform, providing similar electronic functionality to Si:P systems. Additionally, it has the advantages of being less expensive, more controllable, safer to handle, and more compatible with industrial patterning techniques. Si:Sb is therefore a viable platform for emerging quantum device applications.

In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on view-specific features, which can lead to trivial solutions. In this work, we introduce Random Token Fusion (RTF), a novel technique designed to enhance multi-view medical image analysis using vision transformers. By integrating randomness into the feature fusion process during training, RTF addresses the issue of overfitting and enhances the robustness and accuracy of diagnostic models without incurring any additional cost at inference. We validate our approach on standard mammography and chest X-ray benchmark datasets. Through extensive experiments, we demonstrate that RTF consistently improves the performance of existing fusion methods, paving the way for a new generation of multi-view medical foundation models., Comment: Originally published at the NeurIPS 2024 Workshop on Advancements In Medical Foundation Models: Explainability, Robustness, Security, and Beyond (AIM-FM)

In the initial stages of ITER operation, ELM mitigation systems need to be commissioned. This requires controlled flat-top operation in type-I ELMy H-mode regimes. Hydrogen or helium plasma discharges are used exclusively in these stages to ensure negligible production of neutrons from fusion reactions. With the expected higher L-H power threshold of hydrogen and helium plasmas compared to corresponding D and D/T plasmas, it is uncertain whether available auxiliary power systems are sufficient to operate in stable type-I ELMy H-mode. This has been investigated using integrated core and edge/SOL/divertor modelling with JINTRAC. Assuming that the L-H power threshold is well captured by the Martin08 scaling law, the presented simulations have found that 30 MW of ECRH power is likely required for the investigated hydrogen plasma scenarios, rather than the originally planned 20 MW in the 2016 Staged Approach ITER Baseline. However, past experiments have shown that a small helium fraction (~10 %) can considerably reduce the hydrogen plasma L-H power threshold. Assuming that these results extrapolate to ITER operation regimes, the 7.5MA/2.65T hydrogen plasma scenario is likely to access stable type-I ELMy H-mode operation also at 20 MW of ECRH., Comment: 22 pages, 10 figures

Existing roadside perception systems are limited by the absence of publicly available, large-scale, high-quality 3D datasets. Exploring the use of cost-effective, extensive synthetic datasets offers a viable solution to tackle this challenge and enhance the performance of roadside monocular 3D detection. In this study, we introduce the TUMTraf Synthetic Dataset, offering a diverse and substantial collection of high-quality 3D data to augment scarce real-world datasets. Besides, we present WARM-3D, a concise yet effective framework to aid the Sim2Real domain transfer for roadside monocular 3D detection. Our method leverages cheap synthetic datasets and 2D labels from an off-the-shelf 2D detector for weak supervision. We show that WARM-3D significantly enhances performance, achieving a +12.40% increase in mAP 3D over the baseline with only pseudo-2D supervision. With 2D GT as weak labels, WARM-3D even reaches performance close to the Oracle baseline. Moreover, WARM-3D improves the ability of 3D detectors to unseen sample recognition across various real-world environments, highlighting its potential for practical applications.

Swarms of drones offer an increased sensing aperture, and having them mimic behaviors of natural swarms enhances sampling by adapting the aperture to local conditions. We demonstrate that such an approach makes detecting and tracking heavily occluded targets practically feasible. While object classification applied to conventional aerial images generalizes poorly the randomness of occlusion and is therefore inefficient even under lightly occluded conditions, anomaly detection applied to synthetic aperture integral images is robust for dense vegetation, such as forests, and is independent of pre-trained classes. Our autonomous swarm searches the environment for occurrences of the unknown or unexpected, tracking them while continuously adapting its sampling pattern to optimize for local viewing conditions. In our real-life field experiments with a swarm of six drones, we achieved an average positional accuracy of 0.39 m with an average precision of 93.2% and an average recall of 95.9%. Here, adapted particle swarm optimization considers detection confidences and predicted target appearance. We show that sensor noise can effectively be included in the synthetic aperture image integration process, removing the need for a computationally costly optimization of high-dimensional parameter spaces. Finally, we present a complete hard- and software framework that supports low-latency transmission (approx. 80 ms round-trip time) and fast processing (approx. 600 ms per formation step) of extensive (70-120 Mbit/s) video and telemetry data, and swarm control for swarms of up to ten drones.

Current research in breast cancer Magnetic Resonance Imaging (MRI), especially with Artificial Intelligence (AI), faces challenges due to the lack of expert segmentations. To address this, we introduce the MAMA-MIA dataset, comprising 1506 multi-center dynamic contrast-enhanced MRI cases with expert segmentations of primary tumors and non-mass enhancement areas. These cases were sourced from four publicly available collections in The Cancer Imaging Archive (TCIA). Initially, we trained a deep learning model to automatically segment the cases, generating preliminary segmentations that significantly reduced expert segmentation time. Sixteen experts, averaging 9 years of experience in breast cancer, then corrected these segmentations, resulting in the final expert segmentations. Additionally, two radiologists conducted a visual inspection of the automatic segmentations to support future quality control studies. Alongside the expert segmentations, we provide 49 harmonized demographic and clinical variables and the pretrained weights of the well-known nnUNet architecture trained using the DCE-MRI full-images and expert segmentations. This dataset aims to accelerate the development and benchmarking of deep learning models and foster innovation in breast cancer diagnostics and treatment planning., Comment: 15 paes, 7 figures, 3 tables

An efficient numerical scheme for solving transport equations for tokamak plasmas within an integrated modelling framework is presented. The plasma transport equations are formulated as diffusion-advection equations in two coordinates (a temporal and a spatial) featuring stiff non-linearities. The presented numerical scheme aims to minimise computational costs, which are associated with repeated calls of numerically expensive physical models in a processes of time stepping and non-linear convergence within an integrated modelling framework. The spatial discretisation is based on the 4th order accurate Interpolated Differential Operator in Conservative Formulation, the time-stepping method is the 2nd order accurate implicit Runge-Kutta scheme, and an under-relaxed Picard iteration is used for accelerating non-linear convergence. Temporal and spatial accuracies of the scheme allow for coarse grids, and the implicit time-stepping method together with the non-linear convergence approach contributes to robust and fast non-linear convergence. The spatial discretisation method enforces conservation in spatial coordinate up to the machine precision. The numerical scheme demonstrates accurate, stable and fast non-linear convergence in numerical tests using analytical stiff transport model. In particular, the 2nd order accuracy in time stepping significantly improves the overall convergence properties and the accuracy of simulating transient processes in comparison to the 1st order schemes.

Transition path theory (TPT) offers a powerful formalism for extracting the rate and mechanism of rare dynamical transitions between metastable states. Most applications of TPT either focus on systems with modestly sized state spaces or use collective variables to try to tame the curse of dimensionality. Increasingly, expressive function approximators like neural networks and tensor networks have shown promise in computing the central object of TPT, the committor function, even in very high dimensional systems. That progress prompts our consideration of how one could use such a high dimensional function to extract mechanistic insight. Here, we present and illustrate a straightforward but powerful way to track how individual dynamical coordinates evolve during a reactive event. The strategy, which involves marginalizing the reactive ensemble, naturally captures the evolution of the dynamical coordinate's distribution, not just its mean reactive behavior.

The rapid evolution of digital sports media necessitates sophisticated information retrieval systems that can efficiently parse extensive multimodal datasets. This paper demonstrates SoccerRAG, an innovative framework designed to harness the power of Retrieval Augmented Generation (RAG) and Large Language Models (LLMs) to extract soccer-related information through natural language queries. By leveraging a multimodal dataset, SoccerRAG supports dynamic querying and automatic data validation, enhancing user interaction and accessibility to sports archives. We present a novel interactive user interface (UI) based on the Chainlit framework which wraps around the core functionality, and enable users to interact with the SoccerRAG framework in a chatbot-like visual manner., Comment: accepted to CBMI 2024 as a demonstration; https://github.com/simula/soccer-rag. arXiv admin note: text overlap with arXiv:2406.01273

The rapid evolution of digital sports media necessitates sophisticated information retrieval systems that can efficiently parse extensive multimodal datasets. This paper introduces SoccerRAG, an innovative framework designed to harness the power of Retrieval Augmented Generation (RAG) and Large Language Models (LLMs) to extract soccer-related information through natural language queries. By leveraging a multimodal dataset, SoccerRAG supports dynamic querying and automatic data validation, enhancing user interaction and accessibility to sports archives. Our evaluations indicate that SoccerRAG effectively handles complex queries, offering significant improvements over traditional retrieval systems in terms of accuracy and user engagement. The results underscore the potential of using RAG and LLMs in sports analytics, paving the way for future advancements in the accessibility and real-time processing of sports data., Comment: accepted to CBMI 2024 as a regular paper; https://github.com/simula/soccer-rag

We present a generalization of the discrete Lehmann representation (DLR) to three-point correlation and vertex functions in imaginary time and Matsubara frequency. The representation takes the form of a linear combination of judiciously chosen exponentials in imaginary time, and products of simple poles in Matsubara frequency, which are universal for a given temperature and energy cutoff. We present a systematic algorithm to generate compact sampling grids, from which the coefficients of such an expansion can be obtained by solving a linear system. We show that the explicit form of the representation can be used to evaluate diagrammatic expressions involving infinite Matsubara sums, such as polarization functions or self-energies, with controllable, high-order accuracy. This collection of techniques establishes a framework through which methods involving three-point objects can be implemented robustly, with a substantially reduced computational cost and memory footprint.

With the recent advances in machine learning, creating agents that behave realistically in simulated air combat has become a growing field of interest. This survey explores the application of machine learning techniques for modeling air combat behavior, motivated by the potential to enhance simulation-based pilot training. Current simulated entities tend to lack realistic behavior, and traditional behavior modeling is labor-intensive and prone to loss of essential domain knowledge between development steps. Advancements in reinforcement learning and imitation learning algorithms have demonstrated that agents may learn complex behavior from data, which could be faster and more scalable than manual methods. Yet, making adaptive agents capable of performing tactical maneuvers and operating weapons and sensors still poses a significant challenge. The survey examines applications, behavior model types, prevalent machine learning methods, and the technical and human challenges in developing adaptive and realistically behaving agents. Another challenge is the transfer of agents from learning environments to military simulation systems and the consequent demand for standardization. Four primary recommendations are presented regarding increased emphasis on beyond-visual-range scenarios, multi-agent machine learning and cooperation, utilization of hierarchical behavior models, and initiatives for standardization and research collaboration. These recommendations aim to address current issues and guide the development of more comprehensive, adaptable, and realistic machine learning-based behavior models for air combat applications.

We introduce cppdlr, a C++ library implementing the discrete Lehmann representation (DLR) of functions in imaginary time and Matsubara frequency, such as Green's functions and self-energies. The DLR is based on a low-rank approximation of the analytic continuation kernel, and yields a compact and explicit basis consisting of exponentials in imaginary time and simple poles in Matsubara frequency. cppdlr constructs the DLR basis and associated interpolation grids, and implements standard operations. It provides a flexible yet high-level interface, facilitating the incorporation of the DLR into both small-scale applications and existing large-scale software projects.

Surface treatment tasks such as grinding, sanding or polishing are a vital step of the value chain in many industries, but are notoriously challenging to automate. We present RoboGrind, an integrated system for the intuitive, interactive automation of surface treatment tasks with industrial robots. It combines a sophisticated 3D perception pipeline for surface scanning and automatic defect identification, an interactive voice-controlled wizard system for the AI-assisted bootstrapping and parameterization of robot programs, and an automatic planning and execution pipeline for force-controlled robotic surface treatment. RoboGrind is evaluated both under laboratory and real-world conditions in the context of refabricating fiberglass wind turbine blades., Comment: 7 pages, 6 figures, accepted to the 2024 IEEE International Conference on Robotics and Automation (ICRA 2024)

We propose a guidance strategy to optimize real-time synthetic aperture sampling for occlusion removal with drones by pre-scanned point-cloud data. Depth information can be used to compute visibility of points on the ground for individual drone positions in the air. Inspired by Helmholtz reciprocity, we introduce reciprocal visibility to determine the dual situation - the visibility of potential sampling position in the air from given points of interest on the ground. The resulting visibility map encodes which point on the ground is visible by which magnitude from any position in the air. Based on such a map, we demonstrate a first greedy sampling optimization.

Event-based cameras are predestined for Intelligent Transportation Systems (ITS). They provide very high temporal resolution and dynamic range, which can eliminate motion blur and improve detection performance at night. However, event-based images lack color and texture compared to images from a conventional RGB camera. Considering that, data fusion between event-based and conventional cameras can combine the strengths of both modalities. For this purpose, extrinsic calibration is necessary. To the best of our knowledge, no targetless calibration between event-based and RGB cameras can handle multiple moving objects, nor does data fusion optimized for the domain of roadside ITS exist. Furthermore, synchronized event-based and RGB camera datasets considering roadside perspective are not yet published. To fill these research gaps, based on our previous work, we extended our targetless calibration approach with clustering methods to handle multiple moving objects. Furthermore, we developed an early fusion, simple late fusion, and a novel spatiotemporal late fusion method. Lastly, we published the TUMTraf Event Dataset, which contains more than 4,111 synchronized event-based and RGB images with 50,496 labeled 2D boxes. During our extensive experiments, we verified the effectiveness of our calibration method with multiple moving objects. Furthermore, compared to a single RGB camera, we increased the detection performance of up to +9 % mAP in the day and up to +13 % mAP during the challenging night with our presented event-based sensor fusion methods. The TUMTraf Event Dataset is available at https://innovation-mobility.com/tumtraf-dataset., Comment: 18 pages, 10 figures, 6 tables. This work has been submitted to the IEEE for possible publication

This paper investigates the combination of intensity-based distance maps with boundary loss for point-supervised semantic segmentation. By design the boundary loss imposes a stronger penalty on the false positives the farther away from the object they occur. Hence it is intuitively inappropriate for weak supervision, where the ground truth label may be much smaller than the actual object and a certain amount of false positives (w.r.t. the weak ground truth) is actually desirable. Using intensity-aware distances instead may alleviate this drawback, allowing for a certain amount of false positives without a significant increase to the training loss. The motivation for applying the boundary loss directly under weak supervision lies in its great success for fully supervised segmentation tasks, but also in not requiring extra priors or outside information that is usually required -- in some form -- with existing weakly supervised methods in the literature. This formulation also remains potentially more attractive than existing CRF-based regularizers, due to its simplicity and computational efficiency. We perform experiments on two multi-class datasets; ACDC (heart segmentation) and POEM (whole-body abdominal organ segmentation). Preliminary results are encouraging and show that this supervision strategy has great potential. On ACDC it outperforms the CRF-loss based approach, and on POEM data it performs on par with it. The code for all our experiments is openly available.

The inchworm expansion is a promising approach to solving strongly correlated quantum impurity models due to its reduction of the sign problem in real and imaginary time. However, inchworm Monte Carlo is computationally expensive, converging as $1/\sqrt{N}$ where $N$ is the number of samples. We show that the imaginary time integration is amenable to quasi Monte Carlo, with enhanced $1/N$ convergence, by mapping the Sobol low-discrepancy sequence from the hypercube to the simplex with the so-called Root transform. This extends the applicability of the inchworm method to, e.g., multi-orbital Anderson impurity models with off-diagonal hybridization, relevant for materials simulation, where continuous time hybridization expansion Monte Carlo has a severe sign problem.