International Journal of Computer Assisted Radiology and Surgery最新文献

{"title":"A fully automated CT-based pelvimetry pipeline for quantifying mid-pelvic surgical workspace in rectal cancer.","authors":"Shih-Feng Huang, Hsin-Ping Tseng, Chao-Wen Hsu","doi":"10.1007/s11548-026-03606-2","DOIUrl":"10.1007/s11548-026-03606-2","url":null,"abstract":"<p><strong>Purpose: </strong>Pelvimetry may aid preoperative planning in rectal cancer surgery, yet manual measurements are time-consuming and MRI-based methods require dedicated protocols. We developed a fully automated CT-based pipeline for quantifying mid-pelvic geometry and soft tissue occupancy at the ischial spine level, the narrowest corridor encountered during total mesorectal excision.</p><p><strong>Methods: </strong>This retrospective feasibility study included 73 patients with mid-to-low rectal cancer who underwent contrast-enhanced staging CT. Automated segmentation was performed using TotalSegmentator. The pipeline extracted interspinous distance (ISD) via an anatomically anchored search strategy with valley detection, constructed a posterior pelvic triangle bounded by the bilateral ischial spines and anterior sacrum, and quantified bowel and fat occupancy within this region. Automated measurements were validated against blinded manual annotations by two independent raters. Pipeline success rates, failure taxonomy, and agreement between contrast-enhanced and non-contrast acquisitions (n = 69 paired cases) were evaluated using intraclass correlation coefficients (ICC) and Bland-Altman analysis.</p><p><strong>Results: </strong>The pipeline achieved complete ISD extraction in 100% of contrast-enhanced and 95.8% of non-contrast cases. In blinded validation (n = 70), automated ISD agreement against manual reference (ICC = 0.977; bias = 0.45 mm) exceeded inter-rater reliability (ICC = 0.962), and triangle-derived metrics showed a good-to-excellent agreement (ICC = 0.86-0.89, auto vs. manual). ISD measurements showed excellent agreement across contrast conditions (ICC = 0.99; mean bias = 0.09 mm; 95% limits of agreement: - 2.51 to 2.69 mm). Bone-derived triangle metrics demonstrated strong concordance (ICC = 0.90-0.93). Fat-related metrics showed systematic differences between contrast conditions but maintained good agreement (ICC = 0.87-0.91). Sex-based differences were consistent with known pelvic dimorphism.</p><p><strong>Conclusion: </strong>This fully automated pipeline reliably extracts mid-pelvic geometry and soft tissue metrics from routine staging CT, with measurement agreement matching or exceeding manual inter-rater variability, offering a standardized, practical, and reproducible approach for characterizing the surgical workspace in rectal cancer patients.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"1999-2010"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147624684","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":"Couinaud segment-aware deep learning on point clouds for major liver resection planning.","authors":"Joy Rakshit, Janine Rothert, Georg Hille, Tobias Huber, Hauke Lang, Rabea Margies, Florentine Huettl, Sylvia Saalfeld","doi":"10.1007/s11548-026-03663-7","DOIUrl":"10.1007/s11548-026-03663-7","url":null,"abstract":"<p><strong>Purpose: </strong>In this study, we address the problem of automatic liver resection planning for major surgical procedures, including hemi-hepatectomy and extended hemi-hepatectomy, using deep learning. Motivated by clinical practice, where Couinaud liver segments are routinely used to describe tumor location and guide surgical decision-making, we investigate whether incorporating this anatomical information can improve model performance and clinical relevance.</p><p><strong>Methods: </strong>We propose a point cloud-based geometric deep learning approach based on a modified RandLA-Net architecture to predict liver resection zones. The model was trained and evaluated on 70 hemi-hepatectomy cases from Johannes Gutenberg University, Mainz, Germany (internal dataset). Two composite loss functions were evaluated: cross-entropy (CE) combined with intersection over union (IoU) and CE combined with Dice loss. For each loss function, models were trained with and without Couinaud segment information. Generalizability was assessed on an external dataset of 30 hemi-hepatectomy cases from the colorectal liver metastases (CRLM) cohort.</p><p><strong>Results: </strong>Both loss functions achieved comparable performance across the evaluated datasets, with CE <math><mo>+</mo></math> IoU consistently outperforming CE <math><mo>+</mo></math> Dice. On the internal test set, incorporating Couinaud segment information increased the IoU_mean from 0.787 to 0.804 and the F1-score from 0.864 to 0.870. A Wilcoxon signed-rank test on 15 paired cases confirmed a statistically significant improvement in IoU_mean (p = 0.030), with 80% of cases showing improvement. On the external dataset, IoU_mean improved from 0.666 to 0.702 and F1-score from 0.786 to 0.799 when Couinaud information was included. Excluding five anatomically complex cases, a Wilcoxon signed-rank test on the remaining 25 paired cases showed a significant improvement in IoU_mean (p = 0.019), with 68% of cases demonstrating improved performance.</p><p><strong>Conclusion: </strong>Explicit integration of Couinaud segment information improves both quantitative performance and clinical relevance in automatic major liver resection planning, particularly by better preserving critical vascular structures.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"1939-1948"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13694551/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147857683","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":"A usability-driven workflow for virtual fracture reduction using an open platform with ICP.","authors":"Costanza Manfredi, Gabriele Vanni, Marina Carbone, Eleonora Tiribilli, Elena Denisova, Vincenzo Ferrari","doi":"10.1007/s11548-026-03621-3","DOIUrl":"10.1007/s11548-026-03621-3","url":null,"abstract":"<p><strong>Purpose: </strong>Virtual surgical planning can support fracture reduction, but its routine use remains limited by the time and interaction burden associated with manually manipulating fragments in six degrees of freedom. This work presents a CBCT-based workflow designed to minimise user interaction by replacing continuous manual manipulation with a small number of point-based initialisation steps.</p><p><strong>Methods: </strong>Fragment alignment through a sequential rigid registration strategy based on the iterative closest point (ICP) algorithm. The largest fragment is initialised manually. Subsequent fragments inherit the transformation estimated in the previous step and are refined automatically through ICP, although additional initialisation may be required in unfavourable configurations. Reduction accuracy was assessed using surface-to-surface distance analysis. The workflow is implemented using fully open-source tools ensuring reproducibility and accessibility without proprietary dependencies.</p><p><strong>Results: </strong>The workflow was evaluated on experimentally induced bovine femur fractures comprising two to four fragments by users with heterogeneous backgrounds. Compared to manual alignment, the proposed approach significantly reduced reduction time (Wilcoxon signed-rank paired test, p = 0.022), corresponding to an average reduction of approximately 63%. Surface-to-surface analysis showed mean alignment errors of approximately 1.5-1.8 mm, with consistent results across users.</p><p><strong>Conclusion: </strong>A usability-driven workflow that constrains interaction to a limited number of discrete steps can substantially improve the efficiency of virtual fracture reduction while maintaining user control. The open-source pipeline provides an accessible solution for preoperative fracture reduction planning and should be regarded as a foundation for further developments in usability-driven virtual fracture reduction.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"1963-1972"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147724480","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":"Surgical bleeding prediction using transformer: an application to laparoscopic cholecystectomy.","authors":"Yiyu Wang, Vincent Augusto, Canan Pehlivan, Julia Fleck, Nesrine Mekhenane","doi":"10.1007/s11548-026-03667-3","DOIUrl":"10.1007/s11548-026-03667-3","url":null,"abstract":"<p><strong>Purpose: </strong>Surgical bleeding is often associated with the surgeon's actions during procedures and may be preventable if high-risk behaviors are identified in advance. Here, we aim to develop a real-time tool for predicting intraoperative bleeding risk using an event-log-based framework, and we demonstrate its feasibility in laparoscopic cholecystectomy with potential for broader generalization.</p><p><strong>Methods: </strong>We represent the surgeon's workflow as an event log composed of triplets (action, instrument, target), their durations, recent bleeding history, and surgical phase information extracted from the preceding minutes of the procedure. Using real-time event logs from laparoscopic cholecystectomy procedures in the CholecTrack20 and CholecT50 datasets, we preprocess these data and train a Transformer-based model to estimate the probability of bleeding in the immediate future.</p><p><strong>Results: </strong>Our Transformer-based model outperforms LSTM- and TCN-based approaches, achieving its best performance for short-term bleeding prediction. For 30-60 s ahead, the F1-score reaches 68.6%, surpassing TCN (60.1%) by 8%. For 60-90 s, it remains competitive at 64.4%, about 6% higher than TCN, with performance gradually declining over longer horizons.</p><p><strong>Conclusions: </strong>Predicting bleeding events from real-time event logs based on recent surgical activity shows strong potential for effective intraoperative decision support. To further enhance model relevance and enable reliable real-time deployment, additional data (i.e., more surgical procedures) and more detailed bleeding annotations (e.g., bleeding intensity, the location of the bleeding, and whether the bleeding is active) will be beneficial.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"1929-1938"},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147823345","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":"Virtual intraoperative CT (viCT): sequential anatomic updates for modeling tissue resection throughout endoscopic sinus surgery.","authors":"Nicole M Gunderson, Graham J Harris, Jeremy S Ruthberg, Pengcheng Chen, Di Mao, Randall A Bly, Waleed M Abuzeid, Eric J Seibel","doi":"10.1007/s11548-026-03783-0","DOIUrl":"https://doi.org/10.1007/s11548-026-03783-0","url":null,"abstract":"<p><strong>Purpose: </strong>Incomplete dissection is a common cause of persistent disease and revision endoscopic sinus surgery (ESS) in chronic rhinosinusitis. Current image-guided surgery systems typically reference static preoperative CT (pCT) and do not model evolving resection boundaries. We present Virtual Intraoperative CT (viCT), a method for sequentially updating pCT throughout ESS using intraoperative 3D reconstructions from monocular endoscopic video to enable visualization of evolving anatomy in CT format.</p><p><strong>Methods: </strong>Monocular endoscopic video is processed using a depth-supervised NeRF framework with virtual stereo synthesis to generate metrically scaled 3D reconstructions at multiple surgical intervals. Reconstructions undergo rigid, landmark-based registration in 3D Slicer guided by anatomical correspondences and are then voxelized into the pCT grid. viCT volumes were generated using a ray-based voxel occupancy comparison between pCT and reconstruction to delete outdated voxels and remap preserved anatomy and updated boundaries. Performance is evaluated in a cadaveric feasibility study of four specimens across four ESS stages using volumetric overlap (DSC and Jaccard) and surface metrics (HD95, Chamfer, MSD, and RMSD), alongside qualitative slice comparisons with ground-truth interval CT.</p><p><strong>Results: </strong>viCT updates show high volumetric agreement and submillimeter mean global surface error. The Dice Similarity Coefficient was <math><mrow><mn>0.88</mn> <mo>±</mo> <mn>0.05</mn></mrow> </math> , and the Jaccard Index was <math><mrow><mn>0.79</mn> <mo>±</mo> <mn>0.07</mn></mrow> </math> . The 95th-percentile Hausdorff distance (HD95) was <math><mrow><mn>0.69</mn> <mo>±</mo> <mn>0.28</mn></mrow> </math>  mm, Chamfer distance was <math><mrow><mn>0.09</mn> <mo>±</mo> <mn>0.05</mn></mrow> </math>  mm, mean surface distance (MSD) was <math><mrow><mn>0.11</mn> <mo>±</mo> <mn>0.05</mn></mrow> </math>  mm, and root-mean-square distance (RMSD) was <math><mrow><mn>0.32</mn> <mo>±</mo> <mn>0.10</mn></mrow> </math>  mm.</p><p><strong>Conclusion: </strong>viCT enables CT-format, sequential anatomic updating in an ESS setting without external tracking or additional intraoperative imaging. Future work will focus on fully automating registration, expanding validation in live cases, and optimizing runtime for intraoperative deployment.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148867745","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":"BirthARssistant: a childbirth delivery training simulator integrating microsoft HoloLens2, 3D-printing and electromagnetic tracking.","authors":"Ana González Aranda, Mónica Sevilla-García, Juan de León Luis, Javier Pascau, Alicia Pose-Díez-de-la-Lastra","doi":"10.1007/s11548-026-03780-3","DOIUrl":"https://doi.org/10.1007/s11548-026-03780-3","url":null,"abstract":"<p><strong>Purpose: </strong>Manual assistance during vaginal delivery requires precise hand coordination to guide fetal emergence while protecting the maternal perineum. However, these hands-on skills cannot be acquired through theoretical instruction alone, while conventional mannequin-based training requires continuous expert supervision and relies largely on subjective feedback, limiting opportunities for standardized practice. This work presents BirthARssistant, an augmented reality simulator that integrates obstetric mannequins, Microsoft HoloLens 2, 3D-printing, electromagnetic tracking and real-time hand tracking to provide measurable guidance during childbirth training.</p><p><strong>Methods: </strong>The simulator registers and overlays virtual anatomical models onto obstetric mannequins using QR markers and real-time electromagnetic tracking. Tracking data is processed in 3D Slicer and streamed to Unity through OpenIGTLink. Reference hand postures were recorded from experts for seven stages of vaginal delivery and compared with participants' performance. Eleven participants completed pre- and post- training assessments based on hand placement accuracy, positional and angular errors, questionnaires, and paired statistical analyses.</p><p><strong>Results: </strong>After training, correct hand positioning increased by 57.1% and correct dominant-hand use increased by 30.6%, with statistically significant improvements in both variables. Mean positional error decreased from 64.7 ± 30.1 to 47.1 ± 36.2 mm, while mean angular error decreased from 11.9 ± 11.1° to 8.4 ± 8.2°. Questionnaire responses indicated favorable perceptions of the simulator's usability and educational value.</p><p><strong>Conclusions: </strong>BirthARssistant provides an interactive and measurable approach to obstetric simulation by combining mannequin-based training with AR guidance and real-time motion tracking. The overall findings suggest that the simulator can help reduce inter- and intra-participant variability in performance, support error identification and facilitate skill acquisition by reinforcing the correct sequence and execution of the required maneuvers.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148841843","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":"Systematic evaluation of foundation models for organ-level classification on CT scans.","authors":"Jan Tagscherer, Sarah de Boer, Fennie van der Graaf, Lena Philipp, Colin Jacobs, Ewoud J Smit, Alessa Hering","doi":"10.1007/s11548-026-03786-x","DOIUrl":"https://doi.org/10.1007/s11548-026-03786-x","url":null,"abstract":"<p><strong>Purpose: </strong>Foundation models are increasingly used as frozen feature extractors for CT classification tasks, yet the determinants of their downstream performance remain unclear. We assess how foundation model choice, feature aggregation strategy, and abnormality type are associated with performance in organ-level abnormality classification. We further evaluate whether more expressive aggregation strategies outperform simple pooling, and whether performance varies by abnormality type.</p><p><strong>Methods: </strong>We evaluate five state-of-the-art medical imaging foundation models on binary organ-level abnormality classification (normal vs. abnormal) across six abdominal organs. Local patch-level embeddings are aggregated using six strategies, including simple pooling methods (e.g., mean pooling) and attention-based multiple instance learning. A linear classifier is trained on feature embeddings, and performance is evaluated on an annotated test set of 200 CT scans.</p><p><strong>Results: </strong>Among the evaluated models, 3D CT-native models generally outperformed 2D multi-modal models. None of the tested aggregation strategies significantly outperformed mean pooling, including attention-based multiple instance learning (best-performing aggregation vs. mean: <math><mi>Δ</mi></math> AUC = 0.008, 95% CI <math><mrow><mo>[</mo> <mo>-</mo> <mn>0.002</mn> <mo>,</mo> <mn>0.022</mn> <mo>]</mo></mrow> </math> ). In our organ-level classification setting, performance differed between abnormality type for all well-performing models (SPECTRE, TAP-CT, CT-FM), with lower AUCs observed for focal abnormalities compared to diffuse abnormalities (largest difference: <math><mi>Δ</mi></math> AUC = 0.108, 95% CI [0.080, 0.135]). This gap was not reduced by the evaluated aggregation strategies.</p><p><strong>Conclusion: </strong>In our experiments, downstream performance varied more across foundation models than across aggregation strategies. The choice of aggregation strategy, including attention-based multiple instance learning, did not significantly impact performance in this setting. The persistent gap for focal abnormalities suggests that current representations may insufficiently encode localized disease patterns, motivating the development of localization-aware pre-training approaches.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148841917","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":"SurgAnt-ViVQA: learning to anticipate surgical events through GRU-driven temporal cross-attention.","authors":"Shreyas C Dhake, Jiayuan Huang, Runlong He, Danyal Z Khan, Evangelos B Mazomenos, Sophia Bano, Hani J Marcus, Danail Stoyanov, Matthew J Clarkson, Mobarak I Hoque","doi":"10.1007/s11548-026-03784-z","DOIUrl":"https://doi.org/10.1007/s11548-026-03784-z","url":null,"abstract":"<p><strong>Purpose: </strong>Anticipating forthcoming surgical events is vital for real-time assistance in endonasal transsphenoidal pituitary surgery, where visibility is limited and workflow changes rapidly. Most visual question answering (VQA) systems reason on isolated frames with static vision-language alignment, providing limited support for forecasting forthcoming steps, instrument needs, or remaining procedure time. Existing surgical VQA datasets likewise focus primarily on the current scene rather than the near future.</p><p><strong>Methods: </strong>We introduce PitVQA-Anticipation, a VQA dataset designed for forward-looking surgical reasoning. It comprises 33.5 h of operative video and 734,769 question-answer pairs built from temporally grouped clips and expert annotations across four tasks: predicting the future phase, next step, upcoming instrument, and remaining duration. We further propose SurgAnt-ViVQA, a video-language model that adapts a large language model using a GRU-Gated Temporal Cross-Attention module. A bidirectional GRU encodes frame-to-frame dynamics, while an adaptive gate injects visual context into the language stream at the token level. Parameter-efficient fine-tuning customizes the language backbone to the surgical domain.</p><p><strong>Results: </strong>On PitVQA-Anticipation, SurgAnt-ViVQA achieved BLEU-4 72.38, ROUGE-L 84.94, and METEOR 87.05, outperforming the evaluated image-based and video-based baselines. It also generalized to the EndoVis18-VQA benchmark. The ablation results support the effectiveness of the combined GRU-gated temporal fusion module for anticipatory VQA, while further controlled experiments are required to fully disentangle the independent contributions of recurrence and adaptive gating. A frame-budget study indicates a trade-off: 8 frames maximize linguistic overlap metrics, whereas 32 frames slightly reduce BLEU but improve numeric time estimation.</p><p><strong>Conclusion: </strong>By pairing a temporally aware encoder with fine-grained gated cross-attention, SurgAnt-ViVQA advances surgical VQA from retrospective description toward proactive anticipation. PitVQA-Anticipation provides a computational benchmark for future-aware surgical reasoning; prospective clinical utility requires further validation with surgeons and operating-room staff.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148834536","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":"AMR-VSF: an adaptive memory correction framework for robust 3D CT aorta segmentation.","authors":"Yingjie Zhang, Yuxiang Ma, Kang Li, Lixu Gu","doi":"10.1007/s11548-026-03662-8","DOIUrl":"https://doi.org/10.1007/s11548-026-03662-8","url":null,"abstract":"<p><strong>Purpose: </strong>Accurate 3D aortic segmentation in CT images is vital for cardiovascular disease diagnosis, surgical planning, and intraoperative navigation. Existing aortic segmentation methods suffer from 3D incoherence (frame-level models) or cumulative memory drift (memory-based video models), failing to meet real-time clinical demands for surgical planning. This study developed the Adaptive Memory Rectification Video Segmentation Framework (AMR-VSF) to integrate both models' strengths, optimizing single-frame anatomical accuracy and cross-frame temporal stability while meeting real-time demands.</p><p><strong>Methods: </strong>AMR-VSF uses a 4-stage modular architecture: (1) Frame-level models generate anatomically complete initial masks; (2) MedSAM2 enables cross-frame mask propagation for temporal consistency; (3) Dual \"coverage-diameter deviation rate\" metrics detect drift, with segmented memory reset (partial clearing for stable areas, full clearing for complex ones) to correct it; (4) Dynamic weight fusion balances local accuracy and global consistency. TensorRT optimized MedSAM2, and the framework was validated on 92 patients' CT aortic data (≈76,000 slices).</p><p><strong>Results: </strong>AMR-VSF (nnUNet-based) achieved optimal performance: Dice Similarity Coefficient (DSC) 0.963 (5.1% higher than MedSAM2 alone), 95% Hausdorff Distance (HD95) 3.32 mm (38.2% lower), and Average Surface Distance (ASD) 0.61 mm (38.4% lower than the latter). TensorRT cut MedSAM2's single-frame inference time from 73.1 to 31.2 ms with no accuracy loss. Its outputs enabled 3D reconstruction of the aorta (complete \"aortic arch-thoracic aorta-abdominal aorta-branch vessels\" topological connection, anatomy-matched smooth edges), and the framework showed strong compatibility with diverse models, with potential extension to other long-sequence luminal structure segmentation.</p><p><strong>Conclusion: </strong>AMR-VSF addresses existing limitations by combining frame-level and video models, achieving high accuracy and stability. TensorRT enables real-time use, and its 3D models support tasks like aneurysm measurement. It is compatible and extensible, supporting precise cardiovascular care.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148820167","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":"Clinical outcome prediction of Contour Neurovascular System treatment based on pre-treatment geometric and hemodynamic characteristics.","authors":"Fina Gießler, Anna Bernovskis, Franziska Gaidzik, Jana Korte, Philipp Berg, Sönke Peters, Naomi Larsen, Sylvia Saalfeld","doi":"10.1007/s11548-026-03777-y","DOIUrl":"https://doi.org/10.1007/s11548-026-03777-y","url":null,"abstract":"<p><strong>Purpose: </strong>The contour neurovascular system (CNS) is increasingly used for endovascular treatment of intracranial aneurysms, but outcome and post-treatment device behavior vary between patients. This study investigated whether pre-treatment geometric and hemodynamic characteristics from image-based blood flow simulations are associated with clinical outcome and follow-up CNS shape modifications.</p><p><strong>Methods: </strong>Pre-treatment vascular geometries and blood flow simulations were analyzed in 39 CNS-treated cases. Geometric, hemodynamic, and ostium-flow clustering features were extracted, followed by global feature thinning to reduce redundancy. Associations with binary clinical outcome and follow-up shape modifications (SM1-SM3) were assessed using nonparametric univariate statistics with false discovery rate correction. Exploratory outcome discrimination was evaluated using a support vector machine classifier.</p><p><strong>Results: </strong>Aneurysm geometry showed the strongest association with clinical outcome. Smaller dome and ostium areas were associated with positive outcome (Cliff's δ =  - 0.57 and - 0.43), while hemodynamic parameters showed weaker but directionally consistent trends, including lower peak outflow velocity, and reduced inflow intensity. Shape-modification patterns differed across deformation classes. SM1 and SM2 showed no FDR-significant features but moderate effects for aneurysm geometry and selected hemodynamic metrics. SM3 showed the strongest associations with oscillatory flow characteristics (δ ≈ 0.56-0.57) and peripheral outflow dominance. Exploratory machine learning showed limited, non-significant outcome discrimination (mean AUC = 0.57), with selected features consistent with univariate findings.</p><p><strong>Conclusion: </strong>Pre-treatment geometric and hemodynamic characteristics are linked not only to clinical outcome but also to post-treatment CNS shape modifications. By linking pre-operative flow conditions to follow-up device behavior, this study improves the understanding of hemodynamic factors associated with CNS shape modifications and suggests that simulation-based analysis may support future patient-specific treatment planning using exclusively pre-operative data.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801236","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}