arXiv subjects

Marta Kersten-Oertel

Publications and source records attributed to Marta Kersten-Oertel.

18 recordsLinked to original sources

arXiv2026

Data-driven registration and modeling of brain deformation for image-guided neurosurgery

Accurate compensation of brain deformation is critical for reliable image-guided neurosurgery. Surgical manipulation and tumor resection induce tissue motion, causing preoperative planning images to become misaligned with the intraoperative anatomy. In this review, we examine data-driven methods developed between 2020 and 2025 for brain deformation registration and modeling, with a particular focus on learning-based approaches. A comprehensive literature search was conducted in PubMed, IEEE Xplore, Scopus, and Web of Science using predefined inclusion and exclusion criteria for computational methods addressing brain deformation in neurosurgical imaging, resulting in 46 eligible studies. We provide a unified analysis of methodological strategies, including deep learning-based image registration, direct deformation field regression, synthesis-driven multimodal alignment, resection-aware architectures for handling missing correspondences, and hybrid models integrating biomechanical priors. We also examine dataset utilization, evaluation metrics, validation protocols, and the assessment of uncertainty and generalization across studies. While learning-based methods demonstrate promising accuracy and computational efficiency, current approaches remain limited by out-of-distribution robustness, standardized benchmarking, interpretability, and readiness for clinical deployment. Our review highlights these gaps and outlines future directions toward more robust, generalizable, and clinically translatable solutions for neurosurgical guidance. By organizing recent advances and critically assessing evaluation practices, this work provides a comprehensive reference for researchers and clinicians working on data-driven registration and modeling of brain deformation.

eess.IV↗

arXiv2026

NeuroVase: A Tangible Mobile Augmented Reality Learning System for Neurovascular Anatomy and Stroke Education

Stroke remains a leading cause of mortality and disability worldwide, requiring rapid and informed clinical decision-making. A solid spatial understanding of cerebrovascular anatomy and vascular territories in relation to stroke symptoms and severity is critical for timely clinical decision and patient care. However, this knowledge is typically conveyed through static 2D diagrams and printed materials, which can hinder mastery of the complex neurovascular system and their clinical implications. Mobile augmented reality (AR) offers an accessible medium for delivering intuitive 3D anatomical education, yet applications focused on the neurovascular system and stroke remain limited despite the demand. To address this, we propose NeuroVase, a tablet-based mobile AR platform within a structured pedagogical framework that enhances stroke-related neuroanatomy learning by providing an interactive, engaging, and accessible alternative to traditional methods. NeuroVase features a dual-mode setup, using tangible cue cards as standalone study aids while also serving as interactive markers for AR content delivery. A custom learning curriculum focused on cerebrovascular anatomy and stroke supports exploration of vascular territories, stroke syndromes, and arterial occlusions, in the context of annotated 3D anatomical models in NeuroVase. A controlled user study with 40 participants revealed that NeuroVase is an effective and user-friendly AR platform to facilitate complex anatomical and physiological education, compared with traditional learning.

cs.HC↗

arXiv2026

Shades of Uncertainty: How AI Uncertainty Visualizations Affect Trust in Alzheimer's Predictions

Artificial intelligence (AI) is increasingly used to support prognosis in Alzheimer's disease (AD), but adoption remains limited due to a lack of transparency and interpretability, particularly for long-term predictions where uncertainty is intrinsic and outcomes may not be known for years. We position uncertainty visualization as an explainable AI (XAI) technique and examine how it shapes trust, confidence, and reliance when users interpret AI-generated forecasts of future cognitive decline transitions. We conducted two studies, one with general participants (N=37) and one with experts in neuroimaging and neurology (N=10), to compare binary (present/absent) and continuous (saturation) uncertainty encodings. Continuous encodings improved perceived reliability and helped users recognize model limitations, while binary encodings increased momentary confidence, revealing expertise-dependent trade-offs in interpreting future predictions under high uncertainty. These findings surface key challenges in designing uncertainty representations for prognostic AI and culminate in a set of empirically grounded guidelines for creating trustworthy, user-appropriate clinical decision support tools.

cs.HC↗

arXiv2025

MRI-Based Brain Age Estimation with Supervised Contrastive Learning of Continuous Representation

MRI-based brain age estimation models aim to assess a subject's biological brain age based on information, such as neuroanatomical features. Various factors, including neurodegenerative diseases, can accelerate brain aging and measuring this phenomena could serve as a potential biomarker for clinical applications. While deep learning (DL)-based regression has recently attracted major attention, existing approaches often fail to capture the continuous nature of neuromorphological changes, potentially resulting in sub-optimal feature representation and results. To address this, we propose to use supervised contrastive learning with the recent Rank-N-Contrast (RNC) loss to estimate brain age based on widely used T1w structural MRI for the first time and leverage Grad-RAM to visually explain regression results. Experiments show that our proposed method achieves a mean absolute error (MAE) of 4.27 years and an $R^2$ of 0.93 with a limited dataset of training samples, significantly outperforming conventional deep regression with the same ResNet backbone while performing better or comparably with the state-of-the-art methods with significantly larger training data. Furthermore, Grad-RAM revealed more nuanced features related to age regression with the RNC loss than conventional deep regression. As an exploratory study, we employed the proposed method to estimate the gap between the biological and chronological brain ages in Alzheimer's Disease and Parkinson's disease patients, and revealed the correlation between the brain age gap and disease severity, demonstrating its potential as a biomarker in neurodegenerative disorders.

cs.CV↗

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

AnatomyCarve: A VR occlusion management technique for medical images based on segment-aware clipping

Visualizing 3D medical images is challenging due to self-occlusion, where anatomical structures of interest can be obscured by surrounding tissues. Existing methods, such as slicing and interactive clipping, are limited in their ability to fully represent internal anatomy in context. In contrast, hand-drawn medical illustrations in anatomy books manage occlusion effectively by selectively removing portions based on tissue type, revealing 3D structures while preserving context. This paper introduces AnatomyCarve, a novel technique developed for a VR environment that creates high-quality illustrations similar to those in anatomy books, while remaining fast and interactive. AnatomyCarve allows users to clip selected segments from 3D medical volumes, preserving spatial relations and contextual information. This approach enhances visualization by combining advanced rendering techniques with natural user interactions in VR. Usability of AnatomyCarve was assessed through a study with non-experts, while surgical planning effectiveness was evaluated with practicing neurosurgeons and residents. The results show that AnatomyCarve enables customized anatomical visualizations, with high user satisfaction, suggesting its potential for educational and clinical applications.

cs.HC↗

arXiv2025

Clinically-Inspired Hierarchical Multi-Label Classification of Chest X-rays with a Penalty-Based Loss Function

In this work, we present a novel approach to multi-label chest X-ray (CXR) image classification that enhances clinical interpretability while maintaining a streamlined, single-model, single-run training pipeline. Leveraging the CheXpert dataset and VisualCheXbert-derived labels, we incorporate hierarchical label groupings to capture clinically meaningful relationships between diagnoses. To achieve this, we designed a custom hierarchical binary cross-entropy (HBCE) loss function that enforces label dependencies using either fixed or data-driven penalty types. Our model achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.903 on the test set. Additionally, we provide visual explanations and uncertainty estimations to further enhance model interpretability. All code, model configurations, and experiment details are made available.

cs.CV↗

arXiv2024

iSurgARy: A mobile augmented reality solution for ventriculostomy in resource-limited settings

Global disparities in neurosurgical care necessitate innovations addressing affordability and accuracy, particularly for critical procedures like ventriculostomy. This intervention, vital for managing life-threatening intracranial pressure increases, is associated with catheter misplacement rates exceeding 30% when using a freehand technique. Such misplacements hold severe consequences including haemorrhage, infection, prolonged hospital stays, and even morbidity and mortality. To address this issue, we present a novel, stand-alone mobile-based augmented reality system (iSurgARy) aimed at significantly improving ventriculostomy accuracy, particularly in resource-limited settings such as those in low- and middle-income countries. iSurgARy uses landmark based registration by taking advantage of Light Detection and Ranging (LiDaR) to allow for accurate surgical guidance. To evaluate iSurgARy, we conducted a two-phase user study. Initially, we assessed usability and learnability with novice participants using the System Usability Scale (SUS), incorporating their feedback to refine the application. In the second phase, we engaged human-computer interaction (HCI) and clinical domain experts to evaluate our application, measuring Root Mean Square Error (RMSE), System Usability Scale (SUS) and NASA Task Load Index (TLX) metrics to assess accuracy usability, and cognitive workload, respectively

cs.HC↗

arXiv2024

Virtual Reality-Based Preoperative Planning for Optimized Trocar Placement in Thoracic Surgery: A Preliminary Study

Video-assisted thoracic surgery (VATS) is a minimally invasive approach for treating early-stage non-small-cell lung cancer. Optimal trocar placement during VATS ensures comprehensive access to the thoracic cavity, provides a panoramic endoscopic view, and prevents instrument crowding. While established principles such as the Baseball Diamond Principle (BDP) and Triangle Target Principle (TTP) exist, surgeons mainly rely on experience and patient-specific anatomy for trocar placement, potentially leading to sub-optimal surgical plans that increase operative time and fatigue. To address this, we present the first virtual reality (VR)-based pre-operative planning tool with tailored data visualization and interaction designs for efficient and optimal VATS trocar placement, following the established surgical principles and consultation with an experienced surgeon. In our preliminary study, we demonstrate the system's application in right upper lung lobectomy, a common thoracic procedure typically using three trocars. A preliminary user study of our system indicates it is efficient, robust, and user-friendly for planning optimal trocar placement, with a great promise for clinical application while offering potentially valuable insights for the development of other surgical VR systems.

cs.HC↗

arXiv2024

CT-based brain ventricle segmentation via diffusion Schrödinger Bridge without target domain ground truths

Efficient and accurate brain ventricle segmentation from clinical CT scans is critical for emergency surgeries like ventriculostomy. With the challenges in poor soft tissue contrast and a scarcity of well-annotated databases for clinical brain CTs, we introduce a novel uncertainty-aware ventricle segmentation technique without the need of CT segmentation ground truths by leveraging diffusion-model-based domain adaptation. Specifically, our method employs the diffusion Schrödinger Bridge and an attention recurrent residual U-Net to capitalize on unpaired CT and MRI scans to derive automatic CT segmentation from those of the MRIs, which are more accessible. Importantly, we propose an end-to-end, joint training framework of image translation and segmentation tasks, and demonstrate its benefit over training individual tasks separately. By comparing the proposed method against similar setups using two different GAN models for domain adaptation (CycleGAN and CUT), we also reveal the advantage of diffusion models towards improved segmentation and image translation quality. With a Dice score of 0.78$\pm$0.27, our proposed method outperformed the compared methods, including SynSeg-Net, while providing intuitive uncertainty measures to further facilitate quality control of the automatic segmentation outcomes. The implementation of our proposed method is available at: https://github.com/HealthX-Lab/DiffusionSynCTSeg.

eess.IV↗

arXiv2024

Architecture Analysis and Benchmarking of 3D U-shaped Deep Learning Models for Thoracic Anatomical Segmentation

Recent rising interests in patient-specific thoracic surgical planning and simulation require efficient and robust creation of digital anatomical models from automatic medical image segmentation algorithms. Deep learning (DL) is now state-of-the-art in various radiological tasks, and U-shaped DL models have particularly excelled in medical image segmentation since the inception of the 2D UNet. To date, many variants of U-shaped models have been proposed by the integration of different attention mechanisms and network configurations. Systematic benchmark studies which analyze the architecture of these models by leveraging the recent development of the multi-label databases, can provide valuable insights for clinical deployment and future model designs, but such studies are still rare. We conduct the first systematic benchmark study for variants of 3D U-shaped models (3DUNet, STUNet, AttentionUNet, SwinUNETR, FocalSegNet, and a novel 3D SwinUnet with four variants) with a focus on CT-based anatomical segmentation for thoracic surgery. Our study systematically examines the impact of different attention mechanisms, the number of resolution stages, and network configurations on segmentation accuracy and computational complexity. To allow cross-reference with other recent benchmarking studies, we also included a performance assessment of the BTCV abdominal structural segmentation. With the STUNet ranking at the top, our study demonstrated the value of CNN-based U-shaped models for the investigated tasks and the benefit of residual blocks in network configuration designs to boost segmentation performance.

eess.IV↗

arXiv2023

ESPiM: Eye-Strain Probation Model, An Eye-Tracking Analysis Measure for Digital Displays

Eye-strain is a common issue among computer users due to the prolonged periods they spend working in front of digital displays. This can lead to vision problems, such as irritation and tiredness of the eyes and headaches. We propose the Eye-Strain Probation Model (ESPiM), a computational model based on eye-tracking data that measures eye-strain on digital displays based on the spatial properties of the user interface and display area for a required period of time. As well as measuring eye-strain, ESPiM can be applied to compare (a) different user interface designs, (b) different display devices, and (c) different interaction techniques. Two user studies were conducted to evaluate the effectiveness of ESPiM. The first was conducted in the form of an in-person study with an infrared eye-tracking sensor with 32 participants. The second was conducted in the form of an online study with a video-based eye-tracking technique via webcams on users' computers with 13 participants. Our analysis showed significantly different eye-strain patterns based on the video gameplay frequency of participants. Further, we found distinctive patterns among users on a regular 9-to-5 routine versus those with more flexible work hours in terms of (a) error rates and (b) reported eye-strain symptoms.

cs.HC↗

arXiv2023

Breamy: An augmented reality mHealth prototype for surgical decision-making in breast cancer

In 2020, according to WHO, breast cancer affected 2.3 million women worldwide, resulting in 685,000 fatalities. By the end of the year, approximately 7.8 million women worldwide had survived their breast cancer making it the most widespread form of cancer globally. Surgical treatment decisions, including choosing between oncoplastic options, often require quick decision-making within an 8-week time frame. However, many women lack the necessary knowledge and preparation for making such complex informed decisions. Anxiety and unsatisfactory outcomes can result from inadequate decision-making processes, leading to complications and the need for revision surgeries. Shared decision-making and personalized decision aids have shown positive effects on patient satisfaction and treatment outcomes. This paper introduces Breamy, a prototype mobile health (mHealth) application that utilizes augmented reality (AR) technology to assist breast cancer patients in making informed decisions. The app provides 3D visualizations of different oncoplastic procedures, aiming to improve confidence in surgical decision-making, reduce decisional regret, and enhance patient well-being after surgery. To determine the perception of the usefulness of Breamy, we collected data from 166 participants through an online survey. The results suggest that Breamy has the potential to reduce patient's anxiety levels and assist them during the decision-making process.

cs.HC↗

arXiv2023

VesselShot: Few-shot learning for cerebral blood vessel segmentation

Angiography is widely used to detect, diagnose, and treat cerebrovascular diseases. While numerous techniques have been proposed to segment the vascular network from different imaging modalities, deep learning (DL) has emerged as a promising approach. However, existing DL methods often depend on proprietary datasets and extensive manual annotation. Moreover, the availability of pre-trained networks specifically for medical domains and 3D volumes is limited. To overcome these challenges, we propose a few-shot learning approach called VesselShot for cerebrovascular segmentation. VesselShot leverages knowledge from a few annotated support images and mitigates the scarcity of labeled data and the need for extensive annotation in cerebral blood vessel segmentation. We evaluated the performance of VesselShot using the publicly available TubeTK dataset for the segmentation task, achieving a mean Dice coefficient (DC) of 0.62(0.03).

eess.IV↗

arXiv2022

Assessment of user-interaction strategies for neurosurgical data navigation and annotation in virtual reality

While virtual-reality (VR) has shown great promise in radiological tasks, effective user-interaction strategies that can improve efficiency and ergonomics are still under-explored and systematic evaluations of VR interaction techniques in the context of complex anatomical models are rare. Therefore, our study aims to identify the most effective interaction techniques for two common neurosurgical planning tasks in VR (point annotation and note-taking) from the state-of-the-arts, and propose a novel technique for efficient sub-volume selection necessary in neuroanatomical navigation. We assessed seven user-interaction methods with multiple input modalities (gaze, head motion, controller, and voice) for point placement and note-taking in the context of annotating brain aneurysms for cerebrovascular surgery. Furthermore, we proposed and evaluated a novel technique, called magnified selection diorama (Maserama) for easy navigation and selection of complex 3D anatomies in VR. Both quantitative and semi-quantitative (i.e., NASA Task Load Index) metrics were employed through user studies to reveal the performance of each interaction scheme in terms of accuracy, efficiency, and usability. Our evaluations demonstrated that controller-based interaction is preferred over eye-tracking-based methods for point placement while voice recording and virtual keyboard typing are better than freehand writing for note-taking. Furthermore, our new Maserama sub-volume selection technique was proven to be highly efficient and easy-to-use. Our study is the first to provide a systematic assessment of existing and new VR interaction schemes for neurosurgical data navigation and annotation. It offers valuable insights and tools to guide the design of future VR systems for radiological and surgical applications.

cs.HC↗

arXiv2021

Precision-Weighted Federated Learning

Federated Learning using the Federated Averaging algorithm has shown great advantages for large-scale applications that rely on collaborative learning, especially when the training data is either unbalanced or inaccessible due to privacy constraints. We hypothesize that Federated Averaging underestimates the full extent of heterogeneity of data when the aggregation is performed. We propose Precision-weighted Federated Learning a novel algorithm that takes into account the variance of the stochastic gradients when computing the weighted average of the parameters of models trained in a Federated Learning setting. With Precision-weighted Federated Learning, we provide an alternate averaging scheme that leverages the heterogeneity of the data when it has a large diversity of features in its composition. Our method was evaluated using standard image classification datasets with two different data partitioning strategies (IID/non-IID) to measure the performance and speed of our method in resource-constrained environments, such as mobile and IoT devices. We obtained a good balance between computational efficiency and convergence rates with Precision-weighted Federated Learning. Our performance evaluations show 9% better predictions with MNIST, 18% with Fashion-MNIST, and 5% with CIFAR-10 in the non-IID setting. Further reliability evaluations ratify the stability in our method by reaching a 99% reliability index with IID partitions and 96% with non-IID partitions. In addition, we obtained a 20x speedup on Fashion-MNIST with only 10 clients and up to 37x with 100 clients participating in the aggregation concurrently per communication round. The results indicate that Precision-weighted Federated Learning is an effective and faster alternative approach for aggregating private data, especially in domains where data is highly heterogeneous.

cs.LG↗

arXiv2020

Towards a Computed Collateral Circulation Score in Ischemic Stroke

Stroke is the second leading cause of disability worldwide. In order to minimize disability, the goal of stroke treatment is to preserve tissue in the area where blood supply is decreased but sufficient to stave off cell death. Thrombectomy has been shown to offer fast and efficient reperfusion with high recanalization rates. However, due to the inherent risks of thrombectomy, indications including evidence of good collateral circulation should be present. Currently, methods for evaluating collateral circulation are limited. In this work, we present an automated technique to compute a collateral circulation score based on differences seen in mean intensities between left and right cerebral hemispheres in 4D angiography images. In this preliminary study, we analyzed scans of 28 subjects: 4 with normal collateral circulation, 7 with good, 10 with intermediate, and 7 with poor collateral circulation, (based on radiologist score) and found a good correlation between the computed score and radiologist score (r2 = 0.71) and good separation between good and intermediate/poor groups. This work shows promise as the first step in building an automated collateral circulation score.

physics.med-ph↗

arXiv2019

A Conceptual Marketplace Model for IoT Generated Personal Data

We propose a decentralized conceptual marketplace model for IoT generated personal data. Our model is based on a thorough analysis of personal data in a marketplace context, with specific focus on the challenges presented by commercializing IoT generated personal data. Our model introduces a novel perspective on the commercialization of personal data for a marketplace context via risk evaluation and a data licensing framework. We have designed our model to be centered around protecting the privacy and data rights of data generators through model components that effectively assess and modify transaction risks, and formalize transaction agreements by establishing rights of data use and access between buyer and seller. Our model could serve as a blueprint to inform the implementation of a personal data marketplace that respects privacy and ownership.

cs.CY↗