arXiv subjects

Moon Kim

Publications and source records attributed to Moon Kim.

18 recordsLinked to original sources

arXiv2026

Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why

Patient contexts span hundreds of heterogeneous documents and thousands of structured data points, yet the document-level metadata that AI systems need for retrieval and triage is absent or incomplete. Standard retrieval-augmented generation fails on this data, mishandling temporal reasoning, cross-document dependencies, and missing metadata. We deploy ACIE (Agentic Clinical Information Extraction) at University Medicine Essen: an on-premise agentic RAG pipeline that reasons over complete patient contexts and grounds every answer in source passages for clinician verification. We quantify the metadata gap, trace the architectural decisions it shaped, and evaluate extraction alongside an independent retrospective lymphoma registry study, in which nuclear-medicine physicians verify every extracted value against its cited sources. Across 7,326 judgments, clinicians accepted 96.5\% of extractions, with per-type acceptance ranging from 80\% to 99\%.

cs.AI↗

arXiv2026

Non-local low energy neutral excitations in a strongly disordered triangular Mott magnet Cr$_3$Se$_2$Br$_5$

Understanding if low-energy excitations can remain itinerant in the presence of strong disorder remains a central challenge in frustrated quantum magnets, where disorder is generally expected to localize excitations through Anderson-like mechanisms. Here we report the emergence of charge-neutral itinerant excitations in a van der Waals compound Cr$_3$Se$_2$Br$_5$, a strongly disordered $S = 3/2$ Mott insulator with a frustrated triangular lattice. Structural analysis reveals substantial intrinsic disorder arising from Cr-site deficiency and Se/Br-site mixing, which appear to be fixed and cannot be readily tuned. No long-range magnetic order or conventional glassy behavior is observed. In addition to its highly insulating nature, the magnetic specific heat C_mag/T and thermal conductivity \k{appa}_xx/T both exhibit linear temperature dependencies with substantial finite intercepts. In particular, a sizeable field-independent residual term $\kappa/T \approx 0.03~\mathrm{W\,m^{-1}\,K^{-2}}$ is observed, providing compelling evidence of itinerant low-energy excitations that carry entropy without charge. These findings conceptually advance our understanding of quantum matter by demonstrating a rare regime where the interplay of disorder, frustration, and electronic correlations actively reshapes the nature of low-energy excitations, allowing itinerant neutral excitations to coexist with strong intrinsic disorder.

cond-mat.str-el↗

arXiv2025

Beyond the Desktop: XR-Driven Segmentation with Meta Quest 3 and MX Ink

Medical imaging segmentation is essential in clinical settings for diagnosing diseases, planning surgeries, and other procedures. However, manual annotation is a cumbersome and effortful task. To mitigate these aspects, this study implements and evaluates the usability and clinical applicability of an extended reality (XR)-based segmentation tool for anatomical CT scans, using the Meta Quest 3 headset and Logitech MX Ink stylus. We develop an immersive interface enabling real-time interaction with 2D and 3D medical imaging data in a customizable workspace designed to mitigate workflow fragmentation and cognitive demands inherent to conventional manual segmentation tools. The platform combines stylus-driven annotation, mirroring traditional pen-on-paper workflows, with instant 3D volumetric rendering. A user study with a public craniofacial CT dataset demonstrated the tool's foundational viability, achieving a System Usability Scale (SUS) score of 66, within the expected range for medical applications. Participants highlighted the system's intuitive controls (scoring 4.1/5 for self-descriptiveness on ISONORM metrics) and spatial interaction design, with qualitative feedback highlighting strengths in hybrid 2D/3D navigation and realistic stylus ergonomics. While users identified opportunities to enhance task-specific precision and error management, the platform's core workflow enabled dynamic slice adjustment, reducing cognitive load compared to desktop tools. Results position the XR-stylus paradigm as a promising foundation for immersive segmentation tools, with iterative refinements targeting haptic feedback calibration and workflow personalization to advance adoption in preoperative planning.

cs.HC↗

arXiv2025

Frequency Automata: A novel formal model of hybrid systems in combined time and frequency domains

Hybrid systems are mostly modelled, simulated, and verified in the time domain by computer scientists. Engineers, however, use both frequency and time domain modelling due to their distinct advantages. For example, frequency domain modelling is better suited for control systems, using features such as spectra of the signal. Considering this, we introduce, for the first time, a formal model called frequency automata for hybrid systems modelling and simulation, which are represented in combined time and frequency domains. We propose a sound translation from Hybrid Automata (HA) to Frequency Automata (FA). We also develop a numerical simulator for FA and compare it with the performance of HA. Our approach provides precise level crossing detection and efficient simulation of hybrid systems. We provide empirical results comparing simulation of HA via its translation to FA and its simulation via Matlab Simulink/Stateflow. The results show clear superiority of the proposed technique with the execution times of the proposed technique 118x to 1129x faster compared to Simulink/Stateflow. Moreover, we also observe that the proposed technique is able to detect level crossing with complex guards (including equality), which Simulink/Stateflow fail.

cs.FL↗

arXiv2024

Regulating radiology AI medical devices that evolve in their lifecycle

Over time, the distribution of medical image data drifts due to factors such as shifts in patient demographics, acquisition devices, and disease manifestations. While human radiologists can adjust their expertise to accommodate such variations, deep learning models cannot. In fact, such models are highly susceptible to even slight variations in image characteristics. Consequently, manufacturers must conduct regular updates to ensure that they remain safe and effective. Performing such updates in the United States and European Union required, until recently, obtaining re-approval. Given the time and financial burdens associated with these processes, updates were infrequent, and obsolete systems remained in operation for too long. During 2024, several regulatory developments promised to streamline the safe rollout of model updates: The European Artificial Intelligence Act came into effect last August, and the Food and Drug Administration (FDA) issued final marketing submission recommendations for a Predetermined Change Control Plan (PCCP) in December. We provide an overview of these developments and outline the key building blocks necessary for successfully deploying dynamic systems. At the heart of these regulations - and as prerequisites for manufacturers to conduct model updates without re-approval - are clear descriptions of data collection and re-training processes, coupled with robust real-world quality monitoring mechanisms.

cs.CY↗

arXiv2024

LIMIS: Towards Language-based Interactive Medical Image Segmentation

Within this work, we introduce LIMIS: The first purely language-based interactive medical image segmentation model. We achieve this by adapting Grounded SAM to the medical domain and designing a language-based model interaction strategy that allows radiologists to incorporate their knowledge into the segmentation process. LIMIS produces high-quality initial segmentation masks by leveraging medical foundation models and allows users to adapt segmentation masks using only language, opening up interactive segmentation to scenarios where physicians require using their hands for other tasks. We evaluate LIMIS on three publicly available medical datasets in terms of performance and usability with experts from the medical domain confirming its high-quality segmentation masks and its interactive usability.

cs.CV↗

arXiv2024

ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics

Given the rapidly expanding capabilities of generative AI models for radiology, there is a need for robust metrics that can accurately measure the quality of AI-generated radiology reports across diverse hospitals. We develop ReXamine-Global, a LLM-powered, multi-site framework that tests metrics across different writing styles and patient populations, exposing gaps in their generalization. First, our method tests whether a metric is undesirably sensitive to reporting style, providing different scores depending on whether AI-generated reports are stylistically similar to ground-truth reports or not. Second, our method measures whether a metric reliably agrees with experts, or whether metric and expert scores of AI-generated report quality diverge for some sites. Using 240 reports from 6 hospitals around the world, we apply ReXamine-Global to 7 established report evaluation metrics and uncover serious gaps in their generalizability. Developers can apply ReXamine-Global when designing new report evaluation metrics, ensuring their robustness across sites. Additionally, our analysis of existing metrics can guide users of those metrics towards evaluation procedures that work reliably at their sites of interest.

cs.LG↗

arXiv2024

Anatomy-guided Pathology Segmentation

Pathological structures in medical images are typically deviations from the expected anatomy of a patient. While clinicians consider this interplay between anatomy and pathology, recent deep learning algorithms specialize in recognizing either one of the two, rarely considering the patient's body from such a joint perspective. In this paper, we develop a generalist segmentation model that combines anatomical and pathological information, aiming to enhance the segmentation accuracy of pathological features. Our Anatomy-Pathology Exchange (APEx) training utilizes a query-based segmentation transformer which decodes a joint feature space into query-representations for human anatomy and interleaves them via a mixing strategy into the pathology-decoder for anatomy-informed pathology predictions. In doing so, we are able to report the best results across the board on FDG-PET-CT and Chest X-Ray pathology segmentation tasks with a margin of up to 3.3% as compared to strong baseline methods. Code and models will be publicly available at github.com/alexanderjaus/APEx.

cs.CV↗

arXiv2024

Solid-State Reactions at Niobium-Germanium Interfaces in Hybrid Superconductor-Semiconductor Devices

Hybrid Superconductor-Semiconductor (S-Sm) materials systems are promising candidates for quantum computing applications. Their integration into superconducting electronics has enabled on-demand voltage tunability at millikelvin temperatures. Ge quantum wells (Ge QWs) have been among the semiconducting platforms interfaced with superconducting Al to realize voltage tunable Josephson junctions. Here, we explore Nb as a superconducting material in direct contact with Ge channels by focusing on the solid-state reactions at the Nb/Ge interfaces. We employ Nb evaporation at cryogenic temperatures (100 K) to establish a baseline structure with atomically and chemically abrupt Nb/Ge interfaces. By conducting systematic photoelectron spectroscopy and transport measurements on Nb/Ge samples across varying annealing temperatures, we elucidated the influence of Ge out-diffusion on the ultimate performance of superconducting electronics. This study underlines the need for low-temperature growth to minimize chemical intermixing and band bending at the Nb/Ge interfaces.

cond-mat.supr-con↗

arXiv2024

Real-World Federated Learning in Radiology: Hurdles to overcome and Benefits to gain

Objective: Federated Learning (FL) enables collaborative model training while keeping data locally. Currently, most FL studies in radiology are conducted in simulated environments due to numerous hurdles impeding its translation into practice. The few existing real-world FL initiatives rarely communicate specific measures taken to overcome these hurdles, leaving behind a significant knowledge gap. Minding efforts to implement real-world FL, there is a notable lack of comprehensive assessment comparing FL to less complex alternatives. Materials & Methods: We extensively reviewed FL literature, categorizing insights along with our findings according to their nature and phase while establishing a FL initiative, summarized to a comprehensive guide. We developed our own FL infrastructure within the German Radiological Cooperative Network (RACOON) and demonstrated its functionality by training FL models on lung pathology segmentation tasks across six university hospitals. We extensively evaluated FL against less complex alternatives in three distinct evaluation scenarios. Results: The proposed guide outlines essential steps, identified hurdles, and proposed solutions for establishing successful FL initiatives conducting real-world experiments. Our experimental results show that FL outperforms less complex alternatives in all evaluation scenarios, justifying the effort required to translate FL into real-world applications. Discussion & Conclusion: Our proposed guide aims to aid future FL researchers in circumventing pitfalls and accelerating translation of FL into radiological applications. Our results underscore the value of efforts needed to translate FL into real-world applications by demonstrating advantageous performance over alternatives, and emphasize the importance of strategic organization, robust management of distributed data and infrastructure in real-world settings.

cs.CV↗

arXiv2024

Rethinking Annotator Simulation: Realistic Evaluation of Whole-Body PET Lesion Interactive Segmentation Methods

Interactive segmentation plays a crucial role in accelerating the annotation, particularly in domains requiring specialized expertise such as nuclear medicine. For example, annotating lesions in whole-body Positron Emission Tomography (PET) images can require over an hour per volume. While previous works evaluate interactive segmentation models through either real user studies or simulated annotators, both approaches present challenges. Real user studies are expensive and often limited in scale, while simulated annotators, also known as robot users, tend to overestimate model performance due to their idealized nature. To address these limitations, we introduce four evaluation metrics that quantify the user shift between real and simulated annotators. In an initial user study involving four annotators, we assess existing robot users using our proposed metrics and find that robot users significantly deviate in performance and annotation behavior compared to real annotators. Based on these findings, we propose a more realistic robot user that reduces the user shift by incorporating human factors such as click variation and inter-annotator disagreement. We validate our robot user in a second user study, involving four other annotators, and show it consistently reduces the simulated-to-real user shift compared to traditional robot users. By employing our robot user, we can conduct more large-scale and cost-efficient evaluations of interactive segmentation models, while preserving the fidelity of real user studies. Our implementation is based on MONAI Label and will be made publicly available.

eess.IV↗

arXiv2023

Sliding Window FastEdit: A Framework for Lesion Annotation in Whole-body PET Images

Deep learning has revolutionized the accurate segmentation of diseases in medical imaging. However, achieving such results requires training with numerous manual voxel annotations. This requirement presents a challenge for whole-body Positron Emission Tomography (PET) imaging, where lesions are scattered throughout the body. To tackle this problem, we introduce SW-FastEdit - an interactive segmentation framework that accelerates the labeling by utilizing only a few user clicks instead of voxelwise annotations. While prior interactive models crop or resize PET volumes due to memory constraints, we use the complete volume with our sliding window-based interactive scheme. Our model outperforms existing non-sliding window interactive models on the AutoPET dataset and generalizes to the previously unseen HECKTOR dataset. A user study revealed that annotators achieve high-quality predictions with only 10 click iterations and a low perceived NASA-TLX workload. Our framework is implemented using MONAI Label and is available: https://github.com/matt3o/AutoPET2-Submission/

eess.IV↗

arXiv2023

Multilingual Natural Language Processing Model for Radiology Reports -- The Summary is all you need!

The impression section of a radiology report summarizes important radiology findings and plays a critical role in communicating these findings to physicians. However, the preparation of these summaries is time-consuming and error-prone for radiologists. Recently, numerous models for radiology report summarization have been developed. Nevertheless, there is currently no model that can summarize these reports in multiple languages. Such a model could greatly improve future research and the development of Deep Learning models that incorporate data from patients with different ethnic backgrounds. In this study, the generation of radiology impressions in different languages was automated by fine-tuning a model, publicly available, based on a multilingual text-to-text Transformer to summarize findings available in English, Portuguese, and German radiology reports. In a blind test, two board-certified radiologists indicated that for at least 70% of the system-generated summaries, the quality matched or exceeded the corresponding human-written summaries, suggesting substantial clinical reliability. Furthermore, this study showed that the multilingual model outperformed other models that specialized in summarizing radiology reports in only one language, as well as models that were not specifically designed for summarizing radiology reports, such as ChatGPT.

cs.CL↗

arXiv2023

Why does my medical AI look at pictures of birds? Exploring the efficacy of transfer learning across domain boundaries

It is an open secret that ImageNet is treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit that pretraining on data from the domain of the downstream task should almost always be preferred instead. We leverage RadNet-12M, a dataset containing more than 12 million computed tomography (CT) image slices, to explore the efficacy of self-supervised pretraining on medical and natural images. Our experiments cover intra- and cross-domain transfer scenarios, varying data scales, finetuning vs. linear evaluation, and feature space analysis. We observe that intra-domain transfer compares favorably to cross-domain transfer, achieving comparable or improved performance (0.44% - 2.07% performance increase using RadNet pretraining, depending on the experiment) and demonstrate the existence of a domain boundary-related generalization gap and domain-specific learned features.

cs.CV↗

arXiv2023

Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labeling

Purpose: Interpreting chest radiographs (CXR) remains challenging due to the ambiguity of overlapping structures such as the lungs, heart, and bones. To address this issue, we propose a novel method for extracting fine-grained anatomical structures in CXR using pseudo-labeling of three-dimensional computed tomography (CT) scans. Methods: We created a large-scale dataset of 10,021 thoracic CTs with 157 labels and applied an ensemble of 3D anatomy segmentation models to extract anatomical pseudo-labels. These labels were projected onto a two-dimensional plane, similar to the CXR, allowing the training of detailed semantic segmentation models for CXR without any manual annotation effort. Results: Our resulting segmentation models demonstrated remarkable performance on CXR, with a high average model-annotator agreement between two radiologists with mIoU scores of 0.93 and 0.85 for frontal and lateral anatomy, while inter-annotator agreement remained at 0.95 and 0.83 mIoU. Our anatomical segmentations allowed for the accurate extraction of relevant explainable medical features such as the cardio-thoracic-ratio. Conclusion: Our method of volumetric pseudo-labeling paired with CT projection offers a promising approach for detailed anatomical segmentation of CXR with a high agreement with human annotators. This technique may have important clinical implications, particularly in the analysis of various thoracic pathologies.

eess.IV↗

arXiv2023

Multimodal Interactive Lung Lesion Segmentation: A Framework for Annotating PET/CT Images based on Physiological and Anatomical Cues

Recently, deep learning enabled the accurate segmentation of various diseases in medical imaging. These performances, however, typically demand large amounts of manual voxel annotations. This tedious process for volumetric data becomes more complex when not all required information is available in a single imaging domain as is the case for PET/CT data. We propose a multimodal interactive segmentation framework that mitigates these issues by combining anatomical and physiological cues from PET/CT data. Our framework utilizes the geodesic distance transform to represent the user annotations and we implement a novel ellipsoid-based user simulation scheme during training. We further propose two annotation interfaces and conduct a user study to estimate their usability. We evaluated our model on the in-domain validation dataset and an unseen PET/CT dataset. We make our code publicly available: https://github.com/verena-hallitschke/pet-ct-annotate.

cs.CV↗

arXiv2019

Formation of Graphene atop a Si adlayer on the C-face of SiC

The structure of the SiC(000-1) surface, the C-face of the {0001} SiC surfaces, is studied as a function of temperature and of pressure in a gaseous environment of disilane (Si2H6). Various surface reconstructions are observed, both with and without the presence of an overlying graphene layer (which spontaneously forms at sufficiently high temperatures). Based on cross-sectional scanning transmission electron microscopy measurements, the interface structure that forms in the presence of the graphene is found to contain 1.4 - 1.7 monolayers (ML) of Si, a somewhat counter-intuitive result since, when the graphene forms, the system is actually under C-rich conditions. Using ab initio thermodynamics, it is demonstrated that there exists a class of Si-rich surfaces containing about 1.3 ML of Si that are stable on the surface (even under C-rich conditions) at temperatures above about 400 K. The structures that thus form consist of Si adatoms atop a Si adlayer on the C-face of SiC, with or without the presence of overlying graphene.

cond-mat.mes-hall↗

arXiv2019

Spacing Dependent and Doping Independent Superconductivity in Intercalated 1T Two Dimensional SnSe2

The weak van der Waals interlayer interactions in the transition metal dichalcogenide (TMD) materials have created a rich platform to study their exotic electronic properties through chemical doping or physical gating techniques. We reported bulk superconductivity up to 7.6 K through careful manipulation of the charge carrier density and interlayer spacing d in the chemically intercalated two dimensional 1T-SnSe2 phase. We found, for the first time in the two dimensional SnSe2, that polar organic molecules cointercalated with the alkali metal Li into the basal layers, thus significantly enhancing the superconducting Tc. We observed that the Tc scales with the basal spacing distance, meanwhile being almost independent of x in Lix(THF)ySnSe2 system. Our results offers a new general chemical route to study the rich electron correlations and the interplay of charge density wave and unconventional superconductivity in the two dimensional material.

cond-mat.supr-con↗