Key result
BAMNet accurately segments the aortic root with a ~2.7 mm landmark error on real-time fluoroscopy.
Why the study?
Intraoperative delineation of the aortic root and landmark localization during TAVI remain difficult due to low soft-tissue contrast, motion, and device overlap on fluoroscopy.
A multitask deep learning model can accurately and simultaneously segment the aortic root and localize key anatomical landmarks on intraoperative fluoroscopy in real-time to support TAVI guidance.
May enhance TAVI fluoroscopic guidance; leaves open prospective validation before clinical use.
Accurate intraoperative delineation of the aortic root and localization of key anatomical landmarks during transcatheter aortic valve implantation (TAVI) remain difficult because fluoroscopy provides low soft-tissue contrast and is frequently degraded by motion and overlap from catheters and delivery systems. This study developed and validated a multitask deep learning model for simultaneous aortic root segmentation and landmark localization on fluoroscopic images to support image-guided TAVI. A retrospective dataset of 2,895 fully anonymized fluoroscopic frames from 83 patients who underwent TAVI between 2018 and 2024 was used. Expert annotations included binary masks of the contrast-enhanced aortic root and four anatomical landmarks: two aortic annulus points (AA1, AA2) and two sinotubular junction points near the coronary ostia (STJ1, STJ2). We developed BoundaryAwareMANet (BAMNet), a multitask architecture combining an EfficientNet-V2 encoder, an MA-Net-inspired decoder, a coordinate-aware landmark head, and an auxiliary boundary-guidance pathway. Model performance was evaluated using patient-level five-fold cross-validation. Across five folds, BAMNet achieved Dice 0.916 ± 0.011 , IoU 0.850 ± 0.018 , and Surface Dice@4 mm 0.845 ± 0.031 . Landmark localization reached median and mean errors of 7.64 ± 0.33 px and 10.02 ± 0.17 px, corresponding to fold-weighted millimeter errors of 2.03 mm and 2.66 mm after image-specific pixel-spacing conversion. The model produced both segmentation masks and landmark coordinates in a single forward pass, maintaining real-time inference at approximately 63 FPS. Joint segmentation of the aortic root and localization of anatomical landmarks on intraoperative fluoroscopy is feasible.
No takes yet. Share an insight, caveat, or question.
Laptev et al. (2026) studied Severe aortic stenosis (n=83). BoundaryAwareMANet (BAMNet) deep learning model vs. Single-task baseline models (e.g., MA-Net, YOLO, Swin-Unet) was evaluated on Aortic root segmentation (Dice score) and landmark localization error. BAMNet achieved a Dice score of 0.916 and a mean landmark localization error of 2.66 mm for joint aortic root segmentation and landmark localization on intraoperative fluoroscopy at 63 frames per second.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: