arXiv subjects

Pascal Spiegler

Publications and source records attributed to Pascal Spiegler.

4 recordsLinked to original sources

arXiv2026

Beyond Score-Based Gamification: Designing Spatiotemporal and Musical Experiences for VR Neck Rehabilitation

Pain-related anxiety and fear of movement are major barriers to adherence and therapeutic outcomes in rehabilitation exercises for chronic neck pain. Virtual reality enables the design of immersive experiences that can transform repetitive therapeutic movements into engaging and emotionally supportive interactions. In this exploratory work, we investigate how experience-oriented gamification can reduce anxiety and improve user experience during VR-based neck range-of-motion exercises. We introduce two novel interaction paradigms that embed therapeutic neck movements within multisensory VR experiences. The first paradigm, Spatiotemporal Progression, couples head-tracked trajectories with environmental progression in a tropical island setting, where movement segments dynamically transform time of day, weather, and spatial location as experiential rewards. The second paradigm, Musical Interaction, maps movement segments to meditative music notes layered with relaxing ambient soundscapes. We evaluate these designs against a conventional score-based gamification baseline in a controlled user study with 20 non-patient participants. We assess usability and user experience through subjective measures, exercise performance with motion tracking, and anxiety modulation using the Subjective Units of Distress Scale, heart rate, and skin conductance. Our findings suggest that, in comparison with traditional score-based gamification design, immersive environmental and musical feedback show better potential to reduce anxiety and improve user experience, with little to no impact on successful performance of the exercise. Our preliminary results highlight the potential value of experience-based interaction design for VR rehabilitation, suggesting an alternative to performance-centric gamification that prioritizes emotional engagement without compromising therapeutic efficacy.

cs.HC↗

arXiv2025

TextSAM-EUS: Text Prompt Learning for SAM to Accurately Segment Pancreatic Tumor in Endoscopic Ultrasound

Pancreatic cancer carries a poor prognosis and relies on endoscopic ultrasound (EUS) for targeted biopsy and radiotherapy. However, the speckle noise, low contrast, and unintuitive appearance of EUS make segmentation of pancreatic tumors with fully supervised deep learning (DL) models both error-prone and dependent on large, expert-curated annotation datasets. To address these challenges, we present TextSAM-EUS, a novel, lightweight, text-driven adaptation of the Segment Anything Model (SAM) that requires no manual geometric prompts at inference. Our approach leverages text prompt learning (context optimization) through the BiomedCLIP text encoder in conjunction with a LoRA-based adaptation of SAM's architecture to enable automatic pancreatic tumor segmentation in EUS, tuning only 0.86% of the total parameters. On the public Endoscopic Ultrasound Database of the Pancreas, TextSAM-EUS with automatic prompts attains 82.69% Dice and 85.28% normalized surface distance (NSD), and with manual geometric prompts reaches 83.10% Dice and 85.70% NSD, outperforming both existing state-of-the-art (SOTA) supervised DL models and foundation models (e.g., SAM and its variants). As the first attempt to incorporate prompt learning in SAM-based medical image segmentation, TextSAM-EUS offers a practical option for efficient and robust automatic EUS segmentation. Code is available at https://github.com/HealthX-Lab/TextSAM-EUS .

cs.CV↗

arXiv2025

Towards user-centered interactive medical image segmentation in VR with an assistive AI agent

Crucial in disease analysis and surgical planning, manual segmentation of volumetric medical scans (e.g. MRI, CT) is laborious, error-prone, and challenging to master, while fully automatic algorithms can benefit from user feedback. Therefore, with the complementary power of the latest radiological AI foundation models and virtual reality (VR)'s intuitive data interaction, we propose SAMIRA, a novel conversational AI agent for medical VR that assists users with localizing, segmenting, and visualizing 3D medical concepts. Through speech-based interaction, the agent helps users understand radiological features, locate clinical targets, and generate segmentation masks that can be refined with just a few point prompts. The system also supports true-to-scale 3D visualization of segmented pathology to enhance patient-specific anatomical understanding. Furthermore, to determine the optimal interaction paradigm under near-far attention-switching for refining segmentation masks in an immersive, human-in-the-loop workflow, we compare VR controller pointing, head pointing, and eye tracking as input modes. With a user study, evaluations demonstrated a high usability score (SUS=90.0 $\pm$ 9.0), low overall task load, as well as strong support for the proposed VR system's guidance, training potential, and integration of AI in radiological segmentation tasks.

cs.HC↗

arXiv2024

Weakly Supervised Intracranial Hemorrhage Segmentation with YOLO and an Uncertainty Rectified Segment Anything Model

Intracranial hemorrhage (ICH) is a life-threatening condition that requires rapid and accurate diagnosis to improve treatment outcomes and patient survival rates. Recent advancements in supervised deep learning have greatly improved the analysis of medical images, but often rely on extensive datasets with high-quality annotations, which are costly, time-consuming, and require medical expertise to prepare. To mitigate the need for large amounts of expert-prepared segmentation data, we have developed a novel weakly supervised ICH segmentation method that utilizes the YOLO object detection model and an uncertainty-rectified Segment Anything Model (SAM). In addition, we have proposed a novel point prompt generator for this model to further improve segmentation results with YOLO-predicted bounding box prompts. Our approach achieved a high accuracy of 0.933 and an AUC of 0.796 in ICH detection, along with a mean Dice score of 0.629 for ICH segmentation, outperforming existing weakly supervised and popular supervised (UNet and Swin-UNETR) approaches. Overall, the proposed method provides a robust and accurate alternative to the more commonly used supervised techniques for ICH quantification without requiring refined segmentation ground truths during model training.

cs.CV↗