Joint aortic root segmentation and landmark localization on intraoperative fluoroscopy for TAVI guidance - Takeaways - MDSpire

Joint aortic root segmentation and landmark localization on intraoperative fluoroscopy for TAVI guidance

  • By

  • Nikita V. Laptev

  • Olga M. Gerget

  • Julia K. Panteleeva

  • Mikhail A. Chernyavsky

  • Viacheslav V. Danilov

  • July 15, 2026

Share

  • 1

    The study developed a multitask deep learning model, BAMNet, for simultaneous aortic root segmentation and anatomical landmark localization during TAVI.

  • 2

    BAMNet was validated using a dataset of 2,895 fluoroscopic frames from 83 patients who underwent TAVI between 2018 and 2024.

  • 3

    The model achieved high performance metrics, including Dice and IoU scores, and maintained real-time inference at approximately 63 FPS.

  • 4

    Landmark localization errors were reported as median and mean values of 2.03 mm and 2.66 mm, respectively, after pixel-spacing conversion.

  • 5

    The study addresses the challenges of low soft-tissue contrast and motion in fluoroscopy, enhancing real-time visualization for TAVI procedures.

Original Source(s)

Joint aortic root segmentation and landmark localization on intraoperative fluoroscopy for TAVI guidance

  • by Nikita V. Laptev, Olga M. Gerget, Julia K. Panteleeva, Mikhail A. Chernyavsky, Viacheslav V. Danilov

  • July 15, 2026

Related Content

Association of the C-reactive protein-triglyceride glucose index with microvascular obstruction and long-term prognosis in patients with acute myocardial infarction: a CMR-based study

Effects of postoperative educational interventions on psychological, self-management, and quality-of-life outcomes after coronary artery bypass grafting: a systematic review and meta-analysis

Development and validation of a deep neural network for predicting coronary heart disease in hypertensive patients using 24-hour ambulatory blood pressure monitoring: a retrospective study