International Journal of Computer Assisted Radiology and Surgery最新文献

{"title":"A real-time metric for quantifying registration stability in mixed reality neurosurgical navigation.","authors":"Carlotta Fontana, Matteo De Notaris, Giorgio Iaconetta, Nicola Cappetti","doi":"10.1007/s11548-026-03792-z","DOIUrl":"https://doi.org/10.1007/s11548-026-03792-z","url":null,"abstract":"<p><strong>Objective: </strong>Mixed reality (MR) guidance enables real-time superimposition of virtual anatomical models onto the surgical field but is inherently affected by spatial instability due to tracking limitations, sensor noise and head-mounted display dynamics. These frame-to-frame fluctuations may lead to transient mislocalisation of neuroanatomical structures and are not adequately captured by conventional static registration metrics. This study aimed to develop and validate a clinically interpretable metric for continuous assessment of registration stability in MR-guided neurosurgery.</p><p><strong>Methods: </strong>The Registration Quality Index (RQI) was introduced as an automated, surface-based metric quantifying virtual-physical alignment through pixel-level boundary proximity analysis. A higher RQI value indicates greater boundary displacement, corresponding to worse registration quality. Validation was performed using a rigid skull phantom, a Varjo XR-3 mixed reality headset and ArUco-based optical tracking across fifteen experimental trials and seventy-five viewing configurations. RQI values were compared with established neuronavigation accuracy metrics, including Fiducial Registration Error (FRE) and Target Registration Error (TRE).</p><p><strong>Results: </strong>Strong correlations were observed between RQI and FRE (r = 0.89 (95% CI 0.69-0.96), p < 0.001) and between RQI and TRE (r = 0.93 (95% CI 0.80-0.98), p < 0.001). Regression analysis demonstrated that each 1% increase in RQI corresponded to a 0.195 mm increase in FRE and a 0.244 mm increase in TRE. Real-time computation at 30 Hz was achieved without workflow disruption. RQI variability was significantly influenced by viewing angle, with lateral perspectives yielding higher displacement values than frontal views.</p><p><strong>Conclusions: </strong>As a technical proof of concept, RQI enables continuous, automated monitoring of registration stability in MR-guided neurosurgical navigation, addressing a critical limitation of current static accuracy assessments. While the current proof-of-concept validation on rigid phantoms demonstrates strong construct validity, the interpretability ranges reported here are exploratory and further clinical studies involving in vivo conditions are required to establish clinically actionable decision boundaries and assess performance in the presence of brain shift and soft tissue deformation.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148921309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic probe guidance for volumetric liver ultrasound acquisition via imitation learning from a virtual expert.","authors":"Taiyu Han, Hanying Liang, Qi Zeng, Yan Kang, Hongen Liao, Guochen Ning, Septimiu E Salcudean","doi":"10.1007/s11548-026-03787-w","DOIUrl":"https://doi.org/10.1007/s11548-026-03787-w","url":null,"abstract":"<p><strong>Purpose: </strong>Volumetric liver ultrasound (US) plays an important role in clinical diagnosis but remains highly dependent on operator expertise, particularly during target view localization. This study aims to develop an automatic probe guidance framework that reduces reliance on manual demonstrations and additional sensing hardware, while supporting robust volumetric liver US acquisition.</p><p><strong>Methods: </strong>We propose an image-based imitation learning framework that learns probe guidance policies from a virtual expert in a simulated US scanning environment. A simulation pipeline is constructed using cross-modal medical images and a hybrid US simulator that combines physics-based ray casting with generation-based image synthesis to produce anatomically consistent and acoustically realistic US images. Optimal scanning trajectories are generated based solely on target views typically available in clinical practice. To improve robustness, pose-level and image-level data augmentations are introduced, and US observations are encoded into an anatomy-aware state representation for intercostal liver scanning.</p><p><strong>Results: </strong>Experimental results in simulation and real clinical data demonstrate that the proposed framework achieves accurate and stable target view localization for volumetric liver US acquisition. Compared with baseline and ablated models, the method shows improved localization accuracy, increased liver coverage, and reduced rib interference, while maintaining robustness across different anatomical conditions.</p><p><strong>Conclusion: </strong>This work presents a data-efficient and clinically practical solution for automatic probe guidance in volumetric liver US. By leveraging realistic simulation, virtual expert demonstrations, and anatomy-aware image representations, the proposed framework enables effective learning of probe movements without requiring manual trajectory annotations or additional sensors. The results suggest strong potential for integration into computer-assisted and robotic US systems.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148901558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Anticipating the hospital of the future: stakeholder perspectives on 6G technology requirements in health care.","authors":"Anna Schatz, Matthias Rüb, Henriette Hegermann, Meike Hiddemann, Dario Wieschebrock, Dominik Stegemann, Jan Herbst, Christoph Lipps, Clemens Möllenhoff, Thomas Petzold, Ralf Irmer, Friedrich Köhler, Max Rockstroh, Tobias Pabst, Thomas Neumuth, Hans D Schotten, Sascha Treskatsch","doi":"10.1007/s11548-026-03776-z","DOIUrl":"https://doi.org/10.1007/s11548-026-03776-z","url":null,"abstract":"<p><strong>Purpose: </strong>The ongoing 6G standardization process is largely driven by technical advancements, but with limited consideration of sector-specific needs, particularly in health care. The current scientific literature primarily focuses on technical aspects, offering minimal empirical input from healthcare professionals, patient representatives, or medical device manufacturers. This neglects clinical acceptance and applicability as a critical factor in technology adoption. The objective of this study is to explore the hopes and concerns of healthcare stakeholders in the context of 6G standardization, to support improved alignment between technological development and clinical practice.</p><p><strong>Methods: </strong>To address this gap, we conducted semi-structured interviews with key healthcare stakeholders in Germany and derived recommendations for technology providers.</p><p><strong>Results: </strong>The findings highlight insufficient interoperability, fragmented systems, and inadequate network coverage as central challenges in today's daily practice. Manual documentation and data transfers further burden staff under conditions of shortage and time pressure. A robust infrastructure, particularly in rural areas where telemedicine is growing, is considered essential. Concerns persist regarding data protection and security, alongside unresolved liability for automated systems and skepticism about increasing technological dependence. Nevertheless, stakeholders see substantial opportunities in 6G for simplifying workflows, enabling seamless device integration, and supporting use cases such as real-time imaging, remote monitoring, and cross-institutional data sharing.</p><p><strong>Conclusion: </strong>This study contributes to the 6G standardization by integrating the healthcare perspectives of medtech stakeholders and clinical end users, thereby supporting the development of patient-centered and clinically relevant communication solutions. The findings provide practical guidance for aligning future 6G solutions with real-world clinical requirements.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and development of an endoscopic robotic system and deep reinforcement learning path planning algorithm for fine-needle biopsy of liver lesions.","authors":"Raghav Khanna, Nikola Fischer, Zhenting Du, Christos Bergeles","doi":"10.1007/s11548-026-03779-w","DOIUrl":"https://doi.org/10.1007/s11548-026-03779-w","url":null,"abstract":"<p><p>This paper presents the design, development and evaluation of a novel robotic platform for endoscopic ultrasound-guided fine-needle biopsy of liver lesions. The system combines a four degrees-of-freedom (DoF) two-segment tendon-driven continuum robot (TDCR) endoscope with a two DoF superelastic nickel-titanium bevel-tip steerable needle. Needle path planning is achieved using NeedleNav, a soft actor-critic (SAC) deep reinforcement learning (DRL) model that generates collision-free trajectories to deep-seated lesions. This represents one of the first integrated systems combining a TDCR, steerable needle and DRL-based navigation, and the first application of a SAC to liver lesion targeting. Evaluation of the TDCR through tip tracking of circular, diamond-shaped and arc trajectories demonstrated a mean absolute error (MAE) of 13.19 mm. NeedleNav converged to obstacle avoidance trajectories in <math><mo>∼</mo></math> 2500 training episodes. Needle curvature was augmented by hand-fabricating notches on its distal section. Two needles with a 3-cm and 8-cm notched section were evaluated in a gelatine liver phantom, achieving an MAE of 21.78 mm and 14.86 mm, respectively, for obstacle avoidance trajectories. The system demonstrated observable path deflection compared to obstacle-free trajectories for the same targets. Together, these findings suggest the feasibility of our proposed solution, expanding the reach of endoscopic needle interventions to deep-seated lesions in the right lobe.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal HSI-MRI system for tumor delineation in neurosurgical guidance.","authors":"Manuel Villa, Jaime Sancho, Gonzalo Rosa-Olmeda, Aure Enkaoua, Miguel Chavarrías, Eduardo Juarez","doi":"10.1007/s11548-026-03664-6","DOIUrl":"10.1007/s11548-026-03664-6","url":null,"abstract":"<p><strong>Purpose: </strong>This study proposes the fusion of hyperspectral imaging (HSI) and magnetic resonance imaging (MRI) for tumor delineation in image-guided neurosurgery, comparing three clinically inspired registration strategies and presenting a novel visualization for tumor resection guidance from both imaging modalities under controlled phantom conditions.</p><p><strong>Methods: </strong>A multimodal brain phantom dataset acquired with a 9.4T preclinical MRI scanner and an HSI camera was used. MRI tissues were segmented using a Segment Anything Model, while HSI data were classified with supervised XGBoost, SVM, and RF models. Three registration strategies were evaluated: surface-based registration, rigid landmark-based registration, and ArUco marker-based registration. Accuracy was assessed using fiducial registration error (FRE) and target registration error (TRE), and the overlap between modalities was quantified by the Dice similarity coefficient (DICE) and average surface distance (ASD).</p><p><strong>Results: </strong>Rigid landmark-based registration achieved the best performance (FRE of 1.7 mm, DICE of 85.4%), closely followed by the ArUco-based method, which required minimal infrastructure. Surface-based registration showed higher variability due to manual point acquisition. Overall, a high overlap between MRI and HSI tumor segmentations was observed and further enriching the information by integrating both approaches CONCLUSIONS: The proposed framework enables a reproducible evaluation of HSI-MRI fusion strategies and highlights the complementary value of volumetric MRI and surface-based HSI. Future work will focus on multimodal tissue classification, improved phantom designs, and validation with patient data.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"2021-2034"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147788621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transient numerical simulation of hemodynamics in bioprosthetic heart valves: insights into valve sizing and thrombosis risk.","authors":"M Berger, J Golks, L Gleissner, T Senfter, Ch Mayerl, N Bonaros, C G Tepeköylü, L Stastny, M Grimm, M Pillei","doi":"10.1007/s11548-026-03577-4","DOIUrl":"10.1007/s11548-026-03577-4","url":null,"abstract":"<p><strong>Purpose: </strong>This study aims to evaluate the hemodynamic effect of tilting after implantation of a bioprosthetic heart valve in an enlarged aortic annulus using computational fluid dynamics (CFD). The objective is to define the cost of excessive enlargement in transprosthetical flow and identify the optimal prosthesis size and implantation angle to reduce thrombosis and early degeneration.</p><p><strong>Methods: </strong>Virtual implantation of a 23-mm bioprosthetic model was conducted in a prespecified virtual aortic annulus of 23 mm. CFD simulations were conducted to analyze the hemodynamic parameters, including wall shear stress and turbulent kinetic energy, for bioprosthetic heart valves of the 23 mm (perpendicular implantation), 25 mm, and 27 mm (tilted implantation at different angles) after virtual annular enlargement. The simulations utilized transient flow models and mesh convergence studies, to ensure numerical accuracy and clinical relevance.</p><p><strong>Results: </strong>The 23-mm valve implanted without annular enlargement and in an aligned fashion to the annulus exhibited higher wall shear stress (WSS) and shear stress (SS) values than the 25-mm valve implanted at 12° tilted position and better hemodynamics than the 27-mm valve at 25° tilted position. The 25-mm valve after annular enlargement and implantation at 12° tilted position achieved the best hemodynamic performance together with a 23% and 7% reduction of WSS and SS as compared to the 23-mm valve.</p><p><strong>Conclusions: </strong>Slight oversizing and tilting after annular enlargement yields the best performance of an aortic bioprosthetic valve with lowest WSS and balanced turbulence.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"1949-1962"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146087889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safe and usable ensemble formation for networked medical devices: a comparative study of 5G, NFC and pop-up pairing.","authors":"Okan Yilmaz, Simon Kißmann, Marlene Goschkowski, Philipp Schollmaier, Frank Beger, Dario Wieschebrock, Philipp Feodorovici, Jan C Arensmeyer, Detlef Fleer, Dubravka Maljevic, Klaus Radermacher, Armin Janß","doi":"10.1007/s11548-026-03618-y","DOIUrl":"10.1007/s11548-026-03618-y","url":null,"abstract":"<p><strong>Purpose: </strong>Incorrectly formed medical device ensembles can cause therapy to be performed at the wrong site or display safety-critical data from the wrong patient. This early, exploratory study investigates which wireless ensemble-creation techniques minimize risk while remaining safe and usable in intraoperative workflows. The goal is to identify the most promising methods among 5G, NFC, and pop-up pairing.</p><p><strong>Methods: </strong>Eight techniques (5G proximity/location, pop-up pairing, QR Code, Near-Field Communication (NFC) Tag and Reader, device-ID copying, manual selection, device interaction, and SDC context lookup) and five clinical situations (patient bedside, transport, prep room, operating room (OR), post OR) were examined. Five interoperability and clinical experts rated the importance of risk- and usability-related criteria for each situation, as well as how well the criteria are being fulfilled by the different methods. The criteria weights and the method-specific ratings were combined in a quantitative decision matrix to identify the three most promising approaches, which were implemented in a click-dummy prototype and evaluated through formative testing with two clinicians.</p><p><strong>Results: </strong>The analysis rated 5G, NFC, and pop-up pairing the highest when combining all categories. Subsequent formative tests with clinicians from the University Hospital Bonn support technical feasibility and highlight clear trade-offs. In this small sample (n = 2), NFC was perceived as the safest and most preferred technique. 5G offered speed and automation potential, but raised critical concerns regarding accuracy. Pop-up pairing was considered flexible yet error-prone when multiple devices entered pairing mode simultaneously.</p><p><strong>Conclusion: </strong>This is a systematic comparison of wireless SDC-ensemble techniques. Early clinical feedback favors NFC for its perceived safety, while 5G and pop-up pairing approaches require additional refinements to mitigate residual risks. As one participant pointed out: \"I prefer a reliable and slower over an automated but error-prone method\".</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"1911-1918"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147678277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving hand-eye-coordination in laparoscopy using a virtual endoscope monitor.","authors":"Bernhard Michael Weber, Mathilde Connan, Alexander Kirst, Dominik Schneider, Luca Wegener, Maximilian Berlet, Jonas Fuchtmann, Dirk Wilhelm, Julian Klodmann","doi":"10.1007/s11548-026-03620-4","DOIUrl":"10.1007/s11548-026-03620-4","url":null,"abstract":"<p><strong>Purpose: </strong>While laparoscopic procedures offer considerable advantages for the patient, they pose substantial challenges for the surgeon, whose hand-eye coordination is impaired. One reason for this is the surgeon's lost visual access to the surgical field, who is instead provided with an endoscopic image on a stationary monitor. In the present study, an optical see-through head-mounted display (OST-HMD) was used to display a virtual endoscope monitor. Unlike stationary monitors, this allows the endoscope image to be projected at arbitrary positions in the room.</p><p><strong>Methods: </strong>The benefits of this approach were evaluated in a user study. N = 10 surgeons carried out a threading task in a pelvic trainer integrated in an operating room setup. Four positions of the endoscope image were compared: frontal view ( <math><msup><mn>0</mn> <mo>∘</mo></msup> </math> ), offset by <math><msup><mn>60</mn> <mo>∘</mo></msup> </math> to the left and right, and projected directly onto the surgical field.</p><p><strong>Results: </strong>The results show that for complex bimanual tasks, projecting the endoscope image onto the surgical field led to a halving of execution times in the study. In addition, the forces applied during threading were measured, but no significant effects of perspective were found. More experienced surgeons also reported significantly lower mental workload with the frontal view ( <math><msup><mn>0</mn> <mo>∘</mo></msup> </math> ) and the projection onto the surgical field compared to the other conditions.</p><p><strong>Conclusion: </strong>This study provides first evidence that an OST-HMD could be a suitable way for flexibly displaying endoscopic images in laparoscopy and could help improve the surgeon's hand-eye coordination, while at the same time being easily integrated into the clinical environment.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"1973-1980"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147788600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unwritten rules of healthcare assistance for robotic systems: multi-method workflow analysis of postoperative wound care treatments for the development of robotic assistive systems.","authors":"Sonja Stabenow, Franziska Jurosch, Alissa Jell, Cristina Piazza, Klaus Bengler, Dirk Wilhelm","doi":"10.1007/s11548-026-03665-5","DOIUrl":"10.1007/s11548-026-03665-5","url":null,"abstract":"<p><strong>Purpose: </strong>Understanding and modeling the context of patient care interventions, such as wound dressing changes, is essential for developing intelligent robotic assistive systems. While context awareness is widely acknowledged as a requirement in robotics research, the specific information needed to create adapted behavior remains insufficiently defined for many clinical tasks. By analyzing the wound dressing procedure, which we take as a model for care provision on a surgical ward, we aim to identify and model the requirements for such systems in terms of time and used materials, as well as other contextual factors that influence the execution of the task.</p><p><strong>Methods: </strong>We collected observational and quantitative data during postoperative wound dressing procedures to capture contextual triggers and task dependencies. Material-use tracking and communication annotations provided the data foundation. Using FRAM, we developed a sociotechnical process model that represents the workflow and its requirements. Expert interviews further contextualize the boundaries for robotic assistance.</p><p><strong>Results: </strong>Human assistance is supportive in the background, and its positive impact is beyond a mere requested helper, taking for instance the mental load of preparation. Good assistance is proactive, consultative, and adapts to the care provider. For robotic systems to become embedded in the environment, they need procedural and patient-adapted behavior to interact during wound dressing.</p><p><strong>Conclusions: </strong>Intelligent robotic systems capable of supporting healthcare professionals during patient interventions have to adapt to the rules of hospital environments. Workflow models, as presented in our work, bring human expertise to robotic autonomy.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"1899-1910"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147977138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-time target tracking using image registration and motion prediction.","authors":"Victoria Buchanan, Elodie Lugez","doi":"10.1007/s11548-026-03634-y","DOIUrl":"10.1007/s11548-026-03634-y","url":null,"abstract":"<p><strong>Purpose: </strong>Real-time tracking of anatomical targets is critical in numerous clinical interventions. In magnetic resonance-guided therapies, targets are typically tracked only in 2D or pseudo-3D, and system latencies from image acquisition and processing introduce delays. This study investigates methods that leverage 2D magnetic resonance images to estimate the real-time displacement of a target from its reference position.</p><p><strong>Methods: </strong>Target displacements from their reference position on a pre-treatment image were measured using image registration. These measurements served as inputs to machine learning models that capture patient-specific motion patterns and predict subsequent displacements. Specifically, the models were trained incrementally as measurements became available, adapting to patient-specific characteristics. LightGBM, linear regression, long short-term memory (LSTM) and support vector regression (SVR) models were evaluated for their ability to perform online updates from sparse measurements and for their accuracy in forecasting upcoming target displacements. Hyperparameters were optimized using five subject datasets representative of those acquired during clinical procedures. The methods were assessed on forty-nine independent datasets.</p><p><strong>Results: </strong>Target tracking achieved a baseline registration error of 1.65 mm. Introducing system latencies ranging from 200 to 600 ms resulted in additional latency-induced errors of 0.81 to 1.98 mm. Linear regression and SVR models provided the greatest accuracy gains, reducing the latency-induced errors by 35 to 57%. In contrast, the LightGBM and LSTM models exhibited comparatively lower predictive performance, likely due to limited training data and the increased model complexity. Linear regression was the most computationally efficient, requiring only 15 ms for combined online retraining and inference in both datasets.</p><p><strong>Conclusions: </strong>Combining image registration with lightweight, patient-specific predictive modeling to mitigate system latencies can enable accurate real-time target tracking. Among the evaluated methods, linear regression and SVR achieved the most favorable balance between prediction accuracy and computational efficiency. These findings support the feasibility of robust real-time tracking without reliance on prior assumptions about target shape or motion.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"2011-2019"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147678282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}