International Journal of Computer Assisted Radiology and Surgery最新文献

{"title":"Breaking barriers: noninvasive AI model for BRAF^V600E mutation identification.","authors":"Fan Wu, Xiangfeng Lin, Yuying Chen, Mengqian Ge, Ting Pan, Jingjing Shi, Linlin Mao, Gang Pan, You Peng, Li Zhou, Haitao Zheng, Dingcun Luo, Yu Zhang","doi":"10.1007/s11548-024-03290-0","DOIUrl":"https://doi.org/10.1007/s11548-024-03290-0","url":null,"abstract":"<p><strong>Objective: </strong>BRAF^V600E is the most common mutation found in thyroid cancer and is particularly associated with papillary thyroid carcinoma (PTC). Currently, genetic mutation detection relies on invasive procedures. This study aimed to extract radiomic features and utilize deep transfer learning (DTL) from ultrasound images to develop a noninvasive artificial intelligence model for identifying BRAF^V600E mutations.</p><p><strong>Materials and methods: </strong>Regions of interest (ROI) were manually annotated in the ultrasound images, and radiomic and DTL features were extracted. These were used in a joint DTL-radiomics (DTLR) model. Fourteen DTL models were employed, and feature selection was performed using the LASSO regression. Eight machine learning methods were used to construct predictive models. Model performance was primarily evaluated using area under the curve (AUC), accuracy, sensitivity and specificity. The interpretability of the model was visualized using gradient-weighted class activation maps (Grad-CAM).</p><p><strong>Results: </strong>Sole reliance on radiomics for identification of BRAF^V600E mutations had limited capability, but the optimal DTLR model, combined with ResNet152, effectively identified BRAF^V600E mutations. In the validation set, the AUC, accuracy, sensitivity and specificity were 0.833, 80.6%, 76.2% and 81.7%, respectively. The AUC of the DTLR model was higher than that of the DTL and radiomics models. Visualization using the ResNet152-based DTLR model revealed its ability to capture and learn ultrasound image features related to BRAF^V600E mutations.</p><p><strong>Conclusion: </strong>The ResNet152-based DTLR model demonstrated significant value in identifying BRAF^V600E mutations in patients with PTC using ultrasound images. Grad-CAM has the potential to objectively stratify BRAF mutations visually. The findings of this study require further collaboration among more centers and the inclusion of additional data for validation.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143426641","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":"Leveraging deep learning for nonlinear shape representation in anatomically parameterized statistical shape models.","authors":"Behnaz Gheflati, Morteza Mirzaei, Sunil Rottoo, Hassan Rivaz","doi":"10.1007/s11548-025-03330-3","DOIUrl":"https://doi.org/10.1007/s11548-025-03330-3","url":null,"abstract":"<p><strong>Purpose: </strong>Statistical shape models (SSMs) are widely used for morphological assessment of anatomical structures. However, a key limitation is the need for a clear relationship between the model's shape coefficients and clinically relevant anatomical parameters. To address this limitation, this paper proposes a novel deep learning-based anatomically parameterized SSM (DL-ANAT_SSM) by introducing a nonlinear relationship between anatomical parameters and bone shape information.</p><p><strong>Methods: </strong>Our approach utilizes a multilayer perceptron model trained on a synthetic femoral bone population to learn the nonlinear mapping between anatomical measurements and shape parameters. The trained model is then fine-tuned on a real bone dataset. We compare the performance of DL-ANAT_SSM with a linear ANAT_SSM generated using least-squares regression for baseline evaluation.</p><p><strong>Results: </strong>When applied to a previously unseen femoral bone dataset, DL-ANAT_SSM demonstrated superior performance in predicting 3D bone shape based on anatomical parameters compared to the linear baseline model. The impact of fine-tuning was also investigated, with results indicating improved model performance after this process.</p><p><strong>Conclusion: </strong>The proposed DL-ANAT_SSM is therefore a more precise and interpretable SSM, which is directly controlled by clinically relevant parameters. The proposed method holds promise for applications in both morphometry analysis and patient-specific 3D model generation without preoperative images.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143426645","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":"Double-mix pseudo-label framework: enhancing semi-supervised segmentation on category-imbalanced CT volumes.","authors":"Luyang Zhang, Yuichiro Hayashi, Masahiro Oda, Kensaku Mori","doi":"10.1007/s11548-024-03281-1","DOIUrl":"https://doi.org/10.1007/s11548-024-03281-1","url":null,"abstract":"<p><strong>Purpose: </strong>Deep-learning-based supervised CT segmentation relies on fully and densely labeled data, the labeling process of which is time-consuming. In this study, our proposed method aims to improve segmentation performance on CT volumes with limited annotated data by considering category-wise difficulties and distribution.</p><p><strong>Methods: </strong>We propose a novel confidence-difficulty weight (CDifW) allocation method that considers confidence levels, balancing the training across different categories, influencing the loss function and volume-mixing process for pseudo-label generation. Additionally, we introduce a novel Double-Mix Pseudo-label Framework (DMPF), which strategically selects categories for image blending based on the distribution of voxel-counts per category and the weight of segmentation difficulty. DMPF is designed to enhance the segmentation performance of categories that are challenging to segment.</p><p><strong>Result: </strong>Our approach was tested on two commonly used datasets: a Congenital Heart Disease (CHD) dataset and a Beyond-the-Cranial-Vault (BTCV) Abdomen dataset. Compared to the SOTA methods, our approach achieved an improvement of 5.1% and 7.0% in Dice score for the segmentation of difficult-to-segment categories on 5% of the labeled data in CHD and 40% of the labeled data in BTCV, respectively.</p><p><strong>Conclusion: </strong>Our method improves segmentation performance in difficult categories within CT volumes by category-wise weights and weight-based mixture augmentation. Our method was validated across multiple datasets and is significant for advancing semi-supervised segmentation tasks in health care. The code is available at https://github.com/MoriLabNU/Double-Mix .</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143392507","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":"Development and validation of a surgical robot system for orbital decompression surgery.","authors":"Yanping Lin, Shiqi Peng, Siqi Jiao, Yi Wang, Yinwei Li, Huifang Zhou","doi":"10.1007/s11548-025-03322-3","DOIUrl":"https://doi.org/10.1007/s11548-025-03322-3","url":null,"abstract":"<p><strong>Purpose: </strong>Orbital decompression surgery, which expands the volume of the orbit by removing sections of the orbital walls with a drill and saw, is an important treatment option for thyroid-associated ophthalmopathy. However, it is often limited by physical factors such as a narrow operating space and instability of the manual holding of surgical instruments, which constrains doctors from accurately executing surgical planning.</p><p><strong>Methods: </strong>To overcome these limitations, we designed a surgical robot comprising position adjustment, remote center of motion, and end-effector with a rapid surgical instrument assembly mechanisms. Additionally, to guide surgical robots in precisely performing preoperative surgical planning, we constructed a surgical navigation system comprising preoperative surgical planning and intraoperative optical navigation subsystems. An internally complementary orbital surgical robot system in which the navigation system, optical tracker, and surgical robot and its motion control system serve as the decision-making, perception, and execution layers of the system, respectively, was developed.</p><p><strong>Results: </strong>The results of precision measurement experiments revealed that the absolute and repeated pose accuracies of the surgical robot satisfied the design requirements. As verified by animal experiments, the precision of osteotomy and bone drilling operation of orbital surgical robot system can meet the clinical technical indicators.</p><p><strong>Conclusion: </strong>The developed orbital surgical robotic system for orbital decompression surgery could perform routine operations such as drilling and sawing on the orbital bone with assistance and supervision from surgeons. The feasibility and reliability of the orbital surgical robot system were comprehensively verified through accuracy measurements and animal experiments.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143392506","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":"Intraoperative adaptive eye model based on instrument-integrated OCT for robot-assisted vitreoretinal surgery.","authors":"Marius Briel, Ludwig Haide, Maximilian Hess, Jan Schimmelpfennig, Philipp Matten, Rebekka Peter, Matthias Hillenbrand, Eleonora Tagliabue, Franziska Mathis-Ullrich","doi":"10.1007/s11548-025-03325-0","DOIUrl":"https://doi.org/10.1007/s11548-025-03325-0","url":null,"abstract":"<p><strong>Purpose: </strong>Pars plana vitrectomy (PPV) is the most common surgical procedure performed by retinal specialists, highlighting the need for model-based assistance and automation in surgical treatment. An intraoperative retinal model provides precise anatomical information relative to the surgical instrument, enhancing surgical precision and safety.</p><p><strong>Methods: </strong>This work focuses on the intraoperative parametrization of retinal shape using 1D instrument-integrated optical coherence tomography distance measurements combined with a surgical robot. Our approach accommodates variability in eye geometries by transitioning from an initial spherical model to an ellipsoidal representation, improving accuracy as more data is collected through sensor motion.</p><p><strong>Results: </strong>We demonstrate that ellipsoid fitting outperforms sphere fitting for regular eye shapes, achieving a mean absolute error of less than 40  <math><mrow><mi>μ</mi> <mtext>m</mtext></mrow> </math> in simulation and below 200  <math><mrow><mi>μ</mi> <mtext>m</mtext></mrow> </math> on 3D printed models and ex vivo porcine eyes. The model reliably transitions from a spherical to an ellipsoidal representation across all six tested eye shapes when specific criteria are satisfied.</p><p><strong>Conclusion: </strong>The adaptive eye model developed in this work meets the accuracy requirements for clinical application in PPV within the central retina. Additionally, the global model effectively extrapolates beyond the scanned area to encompass the retinal periphery.This capability enhances PPV procedures, particularly through virtual boundary assistance and improved surgical navigation, ultimately contributing to safer surgical outcomes.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143374209","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":"A deep learning-driven method for safe and effective ERCP cannulation.","authors":"Yuying Liu, Xin Chen, Siyang Zuo","doi":"10.1007/s11548-025-03329-w","DOIUrl":"https://doi.org/10.1007/s11548-025-03329-w","url":null,"abstract":"<p><strong>Purpose: </strong>In recent years, the detection of the duodenal papilla and surgical cannula has become a critical task in computer-assisted endoscopic retrograde cholangiopancreatography (ERCP) cannulation operations. The complex surgical anatomy, coupled with the small size of the duodenal papillary orifice and its high similarity to the background, poses significant challenges to effective computer-assisted cannulation. To address these challenges, we present a deep learning-driven graphical user interface (GUI) to assist ERCP cannulation.</p><p><strong>Methods: </strong>Considering the characteristics of the ERCP scenario, we propose a deep learning method for duodenal papilla and surgical cannula detection, utilizing four swin transformer decoupled heads (4STDH). Four different prediction heads are employed to detect objects of different sizes. Subsequently, we integrate the swin transformer module to identify attention regions to explore prediction potential deeply. Moreover, we decouple the classification and regression networks, significantly improving the model's accuracy and robustness through the separation prediction. Simultaneously, we introduce a dataset on papilla and cannula (DPAC), consisting of 1840 annotated endoscopic images, which will be publicly available. We integrated 4STDH and several state-of-the-art methods into the GUI and compared them.</p><p><strong>Results: </strong>On the DPAC dataset, 4STDH outperforms state-of-the-art methods with an mAP of 93.2% and superior generalization performance. Additionally, the GUI provides real-time positions of the papilla and cannula, along with the planar distance and direction required for the cannula to reach the cannulation position.</p><p><strong>Conclusion: </strong>We validate the GUI's performance in human gastrointestinal endoscopic videos, showing deep learning's potential to enhance the safety and efficiency of clinical ERCP cannulation.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143371421","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":"German surgeons' perspective on the application of artificial intelligence in clinical decision-making.","authors":"Jonas Henn, Tijs Vandemeulebroucke, Simon Hatterscheidt, Jonas Dohmen, Jörg C Kalff, Aimee van Wynsberghe, Hanno Matthaei","doi":"10.1007/s11548-025-03326-z","DOIUrl":"https://doi.org/10.1007/s11548-025-03326-z","url":null,"abstract":"<p><strong>Purpose: </strong>Artificial intelligence (AI) is transforming clinical decision-making (CDM). This application of AI should be a conscious choice to avoid technological determinism. The surgeons' perspective is needed to guide further implementation.</p><p><strong>Methods: </strong>We conducted an online survey among German surgeons, focusing on digitalization and AI in CDM, specifically for acute abdominal pain (AAP). The survey included Likert items and scales.</p><p><strong>Results: </strong>We analyzed 263 responses. Seventy-one percentage of participants were male, with a median age of 49 years (IQR 41-57). Seventy-three percentage of participants carried out a senior role, with a median of 22 years of work experience (IQR 13-28). AI in CDM was seen as helpful for workload management (48%) but not for preventing unnecessary treatments (32%). Safety (95%), evidence (94%), and usability (96%) were prioritized over costs (43%) for the implementation. Concerns included the loss of practical CDM skills (81%) and ethical issues like transparency (52%), patient trust (45%), and physician integrity (44%). Traditional CDM for AAP was seen as experience-based (93%) and not standardized (31%), whereas AI was perceived to assist with urgency triage (60%) and resource management (59%). On median, generation Y showed more confidence in AI for CDM (P = 0.001), while participants working in primary care hospitals were less confident (P = 0.021).</p><p><strong>Conclusion: </strong>Participants saw the potential of AI for organizational tasks but are hesitant about its use in CDM. Concerns about trust and performance need to be addressed through education and critical evaluation. In the future, AI might provide sufficient decision support but will not replace the human component.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191258","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":"An intuitive guidewire control mechanism for robotic intervention.","authors":"Rohit Dey, Yichen Guo, Yang Liu, Ajit Puri, Luis Savastano, Yihao Zheng","doi":"10.1007/s11548-024-03279-9","DOIUrl":"10.1007/s11548-024-03279-9","url":null,"abstract":"<p><strong>Purpose: </strong>Teleoperated Interventional Robotic systems (TIRs) are developed to reduce radiation exposure and physical stress of the physicians and enhance device manipulation accuracy and stability. Nevertheless, TIRs are not widely adopted, partly due to the lack of intuitive control interfaces. Current TIR interfaces like joysticks, keyboards, and touchscreens differ significantly from traditional manual techniques, resulting in a shallow, longer learning curve. To this end, this research introduces a novel control mechanism for intuitive operation and seamless adoption of TIRs.</p><p><strong>Methods: </strong>An off-the-shelf medical torque device augmented with a micro-electromagnetic tracker was proposed as the control interface to preserve the tactile sensation and muscle memory integral to interventionalists' proficiency. The control inputs to drive the TIR were extracted via real-time motion mapping of the interface. To verify the efficacy of the proposed control mechanism to accurately operate the TIR, evaluation experiments using industrial grade encoders were conducted.</p><p><strong>Results: </strong>A mean tracking error of 0.32 ± 0.12 mm in linear and 0.54 ± 0.07° in angular direction were achieved. The time lag in tracking was found to be 125 ms on average using pade approximation. Ergonomically, the developed control interface is 3.5 mm diametrically larger, and 4.5 g. heavier compared to traditional torque devices.</p><p><strong>Conclusion: </strong>With uncanny resemblance to traditional torque devices while maintaining results comparable to state-of-the-art commercially available TIRs, this research successfully provides an intuitive control interface for potential wider clinical adoption of robot-assisted interventions.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"333-344"},"PeriodicalIF":2.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142382319","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":"MINARO DRS: usability study of a robotic-assisted laminectomy.","authors":"Manuel Vossel, Lukas Theisgen, Noah Wickel, Lovis Phlippen, Rastislav Pjontek, Sergey Drobinsky, Hans Clusmann, Klaus Radermacher, Christian Blume, Matías de la Fuente","doi":"10.1007/s11548-024-03285-x","DOIUrl":"10.1007/s11548-024-03285-x","url":null,"abstract":"<p><strong>Purpose: </strong>Although the literature shows that robotic assistance can support the surgeon, robotic systems are not widely spread in clinics. They often incorporate large robotic arms adopted from the manufacturing industry, imposing safety hazards when in contact with the patient or surgical staff. We approached this limitation with a modular dual robot consisting of an ultra-lightweight carrier robot for rough prepositioning and small, highly dynamic, application-specific, interchangeable tooling robots.</p><p><strong>Methods: </strong>A formative usability study with N = 10 neurosurgeons was conducted using a prototype of a novel tooling robot for laminectomy to evaluate the system's usability. The participants were asked to perform three experiments using the robotic system: (1) prepositioning with the carrier robot and milling into (2) a block phantom as well as (3) a spine model.</p><p><strong>Results: </strong>All neurosurgeons could perform a simulated laminectomy on a spine phantom using the robotic system. On average, they rated the usability of this first prototype already between good and excellent (SUS-Score above 75%). Eight out of the ten participants preferred robotic-assisted milling over manual milling. For prepositioning, the developed haptic guidance showed significantly higher effectiveness and efficiency than visual navigation.</p><p><strong>Conclusion: </strong>The proposed dual robot system showed the potential to increase safety in the operating room because of the synergistic hands-on control and the ultra-lightweight design of the carrier robot. The modular design allows for easy adaptation to various surgical procedures. However, improvements are needed in the ergonomics of the tooling robot and the complexity of the virtual fixtures. The cooperative dual robot system can subsequently be tested in a cadaver laboratory and in vivo on animals.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"357-367"},"PeriodicalIF":2.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11807922/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142632280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classification of speech arrests and speech impairments during awake craniotomy: a multi-databases analysis.","authors":"Ilias Maoudj, Atsushi Kuwano, Céline Panheleux, Yuichi Kubota, Takakazu Kawamata, Yoshihiro Muragaki, Ken Masamune, Romuald Seizeur, Guillaume Dardenne, Manabu Tamura","doi":"10.1007/s11548-024-03301-0","DOIUrl":"10.1007/s11548-024-03301-0","url":null,"abstract":"<p><strong>Purpose: </strong>Awake craniotomy presents a unique opportunity to map and preserve critical brain functions, particularly speech, during tumor resection. The ability to accurately assess linguistic functions in real-time not only enhances surgical precision, but also contributes significantly to improving postoperative outcomes. However, today, its evaluation is subjective as it relies on a clinician's observations only. This paper explores the use of a deep learning based model for the objective assessment of speech arrest and speech impairments during awake craniotomy.</p><p><strong>Methods: </strong>We extracted 1883 3-second audio clips containing the patient's response following direct electrical stimulation from 23 awake craniotomies recorded from two operating rooms of the Tokyo Women's Medical University Hospital (Japan) and two awake craniotomies recorded from the University Hospital of Brest (France). A Wav2Vec2-based model has been trained and used to detect speech arrests and speech impairments. Experiments were performed with different datasets settings and preprocessing techniques and the performances of the model were evaluated using the F1-score.</p><p><strong>Results: </strong>The F1-score was 84.12% when the model was trained and tested on Japanese data only. In a cross-language situation, the F1-score was 74.68% when the model was trained on Japanese data and tested on French data.</p><p><strong>Conclusions: </strong>The results are encouraging even in a cross-language situation but further evaluation is required. The integration of preprocessing techniques, in particular noise reduction, improved the results significantly.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"217-224"},"PeriodicalIF":2.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142802925","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}